Community Cloud Computing

Alexandros Marinos Gerard Briscoe

Department of Computing Department of Media and Communications
University of Surrey London School of Economics and Political Science
United Kingdom United Kingdom
e-mail: [email protected] e-mail: [email protected]

Abstract—. Cloud Computing is rising fast, with its data II. C LOUD C OMPUTING
centres growing at an unprecedented rate. However, this has
come with concerns over privacy, efficiency at the expense Cloud Computing is the use of Internet-based technolo-
of resilience, and environmental sustainability, because of gies for the provision of services [1], originating from the
the dependence on Cloud vendors such as Google, Amazon cloud as a metaphor for the Internet, based on depictions in
and Microsoft. Our response is an alternative model for the
Cloud conceptualisation, providing a paradigm for Clouds in
computer network diagrams to abstract the complex infras-
tructure it conceals [8]. It can also be seen as a commercial
arXiv:0907.2485v3 [cs.NI] 12 Oct 2009

the community, utilising networked personal computers for

liberation from the centralised vendor model. Community evolution of the academic-oriented Grid Computing [9],
Cloud Computing (C3) offers an alternative architecture, succeeding where Utility Computing struggled [10], [11],
created by combing the Cloud with paradigms from Grid while making greater use of the self-management advances
Computing, principles from Digital Ecosystems, and sus-
tainability from Green Computing, while remaining true to
of Autonomic Computing [12]. It offers the illusion of
the original vision of the Internet. It is more technically infinite computing resources available on demand, with
challenging than Cloud Computing, having to deal with the elimination of upfront commitment from users, and
distributed computing issues, including heterogeneous nodes, payment for the use of computing resources on a short-
varying quality of service, and additional security constraints. term basis as needed [3]. Furthermore, it does not require
However, these are not insurmountable challenges, and with
the need to retain control over our digital lives and the
the node providing a service to be present once its service
potential environmental consequences, it is a challenge we is deployed [3]. It is being promoted as the cutting-edge
must pursue. of scalable web application development [3], in which
Index Terms—. Cloud Computing, Community Cloud, dynamically scalable and often virtualised resources are
Community Cloud Computing, Green Computing, Sustain- provided as a service over the Internet [13], [1], [14],
ability. [15], with users having no knowledge of, expertise in, or
control over the technology infrastructure of the Cloud
supporting them [16]. It currently has significant momen-
I. I NTRODUCTION tum in two extremes of the web development industry [3],
[1]: the consumer web technology incumbents who have
The recent development of Cloud Computing provides resource surpluses in their vast data centres1 , and various
a compelling value proposition for organisations to out- consumers and start-ups that do not have access to such
source their Information and Communications Technology computational resources. Cloud Computing conceptually
(ICT) infrastructure [1]. However, there are growing con- incorporates Software-as-a-Service (SaaS) [18], Web 2.0
cerns over the control ceded to large Cloud vendors [2], [19] and other technologies with reliance on the Internet,
especially the lack of information privacy [3]. Also, the providing common business applications online through
data centres required for Cloud Computing are growing web browsers to satisfy the computing needs of users,
exponentially [4], creating an ever-increasing carbon foot- while the software and data are stored on the servers.
print and therefore raising environmental concerns [5], [6]. Figure 1 shows the typical configuration of Cloud Com-
The distributed resource provision from Grid Com- puting at run-time when consumers visit an application
puting, distributed control from Digital Ecosystems, and served by the central Cloud, which is housed in one
sustainability from Green Computing, can remedy these or more data centres [20]. Green symbolises resource
concerns. So, Cloud Computing combined with these consumption, and yellow resource provision. The role of
approaches would provide a compelling socio-technical coordinator for resource provision is designated by red,
conceptualisation for sustainable distributed computing, and is centrally controlled. Even if the central node is
utilising the spare resources of networked personal com- implemented as a distributed grid, which is the usual
puters collectively to provide the facilities of a virtual incarnation of a data centre, control is still centralised.
data centre and form a Community Cloud. Therefore, Providers, who are the controllers, are usually companies
essentially reformulating the Internet to reflect its current with other web activities that require large computing
uses and scale, while maintaining the original intentions
[7] for sustainability in the face of adversity. Including 1 A data centre is a facility, with the necessary security devices and
extra capabilities embedded into the infrastructure which environmental systems (e.g. air conditioning and fire suppression),
for housing a server farm, a collection of computer servers that can
would become as fundamental and invisible as moving accomplish server needs far beyond the capability of one machine
packets is today. [17].
 SaaS Consume
(Software as a Service)

End Users
Provide Support Provide

Provide PaaS Consume

(Platform as a Service)

Vendor Developers
Provide Support Consume

Figure 1. Cloud Computing: Typical configuration when consumers

visit an application served by the central Cloud, which is housed in one
IaaS
or more data centres [20]. Green symbolises resource consumption, and (Infrastructure as a Service)
yellow resource provision. The role of coordinator for resource provision
is designated by red, and is centrally controlled.
Figure 2. Abstractions of Cloud Computing: While there is a significant
buzz around Cloud Computing, there is little clarity over which offerings
qualify or their interrelation. The key to resolving this confusion is
resources, and in their efforts to scale their primary busi- the realisation that the various offerings fall into different levels of
nesses have gained considerable expertise and hardware. abstraction, aimed at different market segments.
For them, Cloud Computing is a way to resell these
as a new product while expanding into a new market.
Consumers include everyday users, Small and Medium users online resources and storage. This differentiates
sized Enterprises (SMEs), and ambitious start-ups whose SaaS from traditional websites or web applications which
innovation potentially threatens the incumbent providers. do not interface with user information (e.g. documents)
or do so in a limited manner. Popular examples include
A. Layers of Abstraction Microsoft’s (Windows Live) Hotmail, office suites such
While there is a significant buzz around Cloud Comput- as Google Docs and Zoho, and online business software
ing, there is little clarity over which offerings qualify or such as Salesforce.com.
their interrelation. The key to resolving this confusion is To better understand Cloud Computing we can cat-
the realisation that the various offerings fall into different egorise the roles of the various actors. The vendor as
levels of abstraction, as shown in Figure 2, aimed at resource provider has already been discussed. The ap-
different market segments. plication developers utilise the resources provided, build-
1) Infrastructure-as-a-Service (IaaS) [21]: At the most ing services for the end users. This separation of roles
basic level of Cloud Computing offerings, there are helps define the stakeholders and their differing interests.
providers such as Amazon [22] and Mosso [23], who However, actors can take on multiple roles, with vendors
provide machine instances to developers. These instances also developing services for the end users, or developers
essentially behave like dedicated servers that are controlled utilising the services of others to build their own services.
by the developers, who therefore have full responsibility Yet, within each Cloud the role of provider, and therefore
for their operation. So, once a machine reaches its perfor- controller, can only be occupied by the vendor providing
mance limits, the developers have to manually instantiate the Cloud.
another machine and scale their application out to it.
B. Concerns
This service is intended for developers who can write
arbitrary software on top of the infrastructure with only The Cloud Computing model is not without concerns, as
small compromises in their development methodology. others have noted [29], [3], and we consider the following
2) Platform-as-a-Service (PaaS) [24]: One level of ab- as primary:
straction above, services like Google App Engine [25] pro- 1) Failure of Monocultures: The uptime3 of Cloud
vide a programming environment that abstracts machine Computing based solutions is an advantage, when com-
instances and other technical details from developers. The pared to businesses running their own infrastructure, but
programs are executed over data centres, not concerning often overlooked is the co-occurrence of downtime in
the developers with matters of allocation. In exchange for vendor-driven monocultures. The use of globally decen-
this, the developers have to handle some constraints that tralised data centres for vendor Clouds minimises failure,
the environment imposes on their application design, for aiding its adoption. However, when a cloud fails, there
example the use of key-value stores2 instead of relational is a cascade effect crippling all organisations dependent
databases. on that Cloud, and all those dependent upon them. This
3) Software-as-a-Service (SaaS) [18]: At the was illustrated by the Amazon (S3) Cloud outage [31],
consumer-facing level are the most popular examples of which disabled several other dependent businesses. So,
Cloud Computing, with well-defined applications offering failures are now system-wide, instead of being partial or

2 A distributed storage system for structured data that focuses on 3 Uptime is a measure of the time a computer system has been running,
scalability, at the expense of the other benefits of relational databases i.e. up. It came into use to describe the opposite of downtime, times
[26], e.g. Google’s BigTable [27] and Amazon’s SimpleDB [28]. when a system was not operational [30].
localised. Therefore, the efficiencies gained from central-
ising infrastructure for Cloud Computing are increasingly
at the expense of the Internet’s resilience.
2) Convenience vs Control: The growing popularity of
Cloud Computing comes from its convenience, but also
brings vendor control, an issue of ever-increasing concern.
For example, Google Apps for in-house e-mail typically
provides higher uptime [32], but its failure [33] highlights
the issue of lock-in that comes from depending on vendor
Clouds. The even greater concern is the loss of information
privacy, with vendors having full access to the resources
stored on their Clouds. So much so the British government Figure 3. Grid Computing: Typical configuration in which resource
provision is managed by a group of distributed nodes [47]. Green
is considering a ‘G Cloud’ for government business appli- symbolises resource consumption, and yellow resource provision. The
cations [34]. In particularly sensitive cases of SMEs and role of coordinator for resource provision is designated by red, and is
start-ups, the provider-consumer relationship that Cloud centrally controlled.
Computing fosters between the owners of resources and
their users could potentially be detrimental, as there is a
potential conflict of interest for the providers. They profit of networked, loosely coupled computers, acting in concert
by providing resources to up-and-coming players, but also to perform very large tasks [47]. It has been applied
wish to maintain dominant positions in their consumer- to computationally intensive scientific, mathematical, and
facing industries. academic problems through volunteer computing, and used
3) Environmental Impact: The other major concern is in commercial enterprise for such diverse applications as
the ever-increasing carbon footprint from the exponential drug discovery, economic forecasting, seismic analysis,
growth [4] of the data centres required for Cloud Com- and back-office processing to support e-commerce and
puting. With the industry expected to exceed the airline web services [47].
industry by 2020 [6], raising sustainability concerns [5]. What distinguishes Grid Computing from cluster com-
The industry is being motivated to address the problem puting is being more loosely coupled, heterogeneous, and
by legislation [6], [35], the operational limit of power geographically dispersed [47]. Also, grids are often con-
grids (being unable to power anymore servers in their structed with general-purpose grid software libraries and
data centres) [36], and the potential financial benefits of middleware, dividing and apportioning pieces of a program
increased efficiency [37], [6]. Their primary solution is to potentially thousands of computers [47]. However, what
the use of virtualisation4 to maximise resource utilisation distinguishes Cloud Computing from Grid Computing is
[39], but the problem remains [40], [41]. being web-centric, despite some of its definitions being
While these issues are endemic to Cloud Computing, conceptually similar (such as computing resources being
they are not flaws in the Cloud conceptualisation, but the consumed as electricity is from power grids) [9].
vendor provision and implementation of Clouds [25], [22],
[42]. There are attempts to address some of these concerns, IV. D IGITAL E COSYSTEMS : D ISTRIBUTING C ONTROL
such as a portability layer between vendor Clouds to avoid Digital Ecosystems are distributed adaptive open socio-
lock-in [43]. However, this will not alleviate issues such as technical systems, with properties of self-organisation,
inter-Cloud latency [44]. An open source implementation scalability and sustainability, inspired by natural ecosys-
of the Amazon (EC2) Cloud [22], called Eucalyptus [45], tems [48], [49]. Emerging as a novel approach to the
allows a data centre to execute code compatible with catalysis of sustainable regional development driven by
Amazon’s Cloud. Allowing for the creation of private SMEs [50]. Aiming to help local economic actors become
internal Clouds, avoiding vendor lock-in and providing active players in globalisation [51], valorising their local
information privacy, but only for those with their own data culture and vocations, and enabling them to interact and
centre and so is not really Cloud Computing (which by create value networks at the global level [52]. Increas-
definition is to avoid owning data centres [1]). Therefore, ingly this approach, dubbed glocalisation, is being consid-
vendor Clouds remain synonymous with Cloud Computing ered a successful strategy of globalisation that preserves
[13], [1], [14], [15]. Our response is an alternative model regional growth and identity [53], [54], [55], and has
for the Cloud conceptualisation, created by combining the been embraced by the mayors and decision-makers of
Cloud with paradigms from Grid Computing, principles thousands of municipalities [56]. The community focused
from Digital Ecosystems, and sustainability from Green on the deployment of Digital Ecosystems, REgions for
Computing, while remaining true to the original vision of Digital Ecosystems Network (REDEN) [50], is supported
the Internet [46]. by projects such as the Digital Ecosystems Network of
III. G RID C OMPUTING : D ISTRIBUTING P ROVISION regions for (4) DissEmination and Knowledge Deployment
(DEN4DEK) [57]. This thematic network that aims to
Grid Computing is a form of distributed computing in share experiences and disseminate knowledge to let re-
which a virtual super computer is composed from a cluster gions effectively deploy of Digital Ecosystems at all levels
4
(economic, social, technical and political) to produce real
Virtualisation is the creation of a virtual version of a resource, such as a
server, which can then be stored, migrated, duplicated, and instantiated impacts in the economic activities of European regions
as needed, improving scalability and work load management [38]. through the improvement of SME business environments.
 In a traditional market-based economy, made up of VI. C OMMUNITY C LOUD
sellers and buyers, the parties exchange property, while C3 arises from concerns over Cloud Computing, specif-
in a new network-based economy, made up of servers and ically control by vendors and lack of environmental sus-
clients, the parties share access to services and experiences tainability. The Community Cloud aspires to combine
[58]. Digital Ecosystems aim to support network-based distributed resource provision from Grid Computing, dis-
economies reliant on next-generation ICT that will extend tributed control from Digital Ecosystems and sustainability
the Service-Oriented Architecture (SOA) concept [59] from Green Computing, with the use cases of Cloud
with the automatic combining of available and applicable Computing, while making greater use of self-management
services in a scalable architecture, to meet business user advances from Autonomic Computing. Replacing vendor
requests for applications that facilitate business processes. Clouds by shaping the underutilised resources of user
Digital Ecosystems research is yet to consider scalable re- machines to form a Community Cloud, with nodes po-
source provision, and therefore risks being subsumed into tentially fulfilling all roles, consumer, producer, and most
vendor Clouds at the infrastructure level, while striving for importantly coordinator, as shown in Figure 4.
decentralisation at the service level. So, the realisation of
their vision requires a form of Cloud Computing, but with
their principle of community-based infrastructure where
individual users share ownership [48].

V. G REEN C OMPUTING : G ROWING S USTAINABLY

Green Computing is the efficient use of computing

resources, with the primary objective being to account for
the triple bottom line5 , an expanded spectrum of values
and criteria for measuring organisational (and societal)
success [61]. Given computing systems existed before con-
cern over their environmental impact, it has generally been
implemented retroactively, but is now being considered
at the development phase [61]. It is systemic in nature, Figure 4. Community Cloud: Created from shaping the underutilised
resources of user machines, with nodes potentially fulfilling all roles,
because ever-increasingly sophisticated modern computer consumer, producer, and most importantly coordinator. Green symbolises
systems rely upon people, networks and hardware. So, resource consumption, yellow resource provision, and red resource
the elements of a green solution may comprise items coordination.
such as end user satisfaction, management restructur-
ing, regulatory compliance, disposal of electronic waste,
A. Conceptualisation
telecommuting, virtualisation of server resources, energy
use, thin client solutions and return on investment [61]. The conceptualisation of the Community Cloud draws
One of the greatest environmental concerns of the indus- upon Cloud Computing [20], Grid Computing [9], Digital
try is their data centres [41], which have increased in num- Ecosystems [48], Green Computing [63] and Autonomic
ber over time as business demands have increased, with Computing [12]. A paradigm for Cloud Computing in the
facilities housing a rising amount of evermore powerful community, without dependence on Cloud vendors, such
equipment [17]. As data centres run into limits related to as Google, Amazon, or Microsoft.
power, cooling and space, their ever-increasing operation 1) Openness: Removing dependence on vendors makes
has created a noticeable impact on power grids [36]. To the the Community Cloud the open equivalent to vendor
extent that data centre efficiency has become an important Clouds, and therefore identifies a new dimension in the
global issue, leading to the creation of the Green Grid open versus proprietary struggle [64] that has emerged in
[62], an international non-profit organisation mandating an code, standards and data, but has yet to be expressed in
increase in the energy efficiency of data centres. Their the realm of hosted services.
approach, virtualisation, has improved efficiency [40], 2) Community: The Community Cloud is as much a
[41], but is optimising a flawed model that does not social structure as a technology paradigm [65], because of
consider the whole system, where resource provision is the community ownership of the infrastructure. Carrying
disconnected from resource consumption. For example, with it a degree of economic scalability, without which
competing vendors must host significant redundancy in there would be diminished competition and potential sti-
their data centres to manage usage spikes and maintain fling of innovation as risked in vendor Clouds.
the illusion of infinite resources. So, we would argue that 3) Individual Autonomy: In the Community Cloud,
an alternative more systemic approach is required, where nodes have their own utility functions in contrast with data
resource consumption and provision are connected, to centres, in which dedicated machines execute software as
minimise the environmental impact and allow sustainable instructed. So, with nodes expected to act in their own self-
growth. interest, centralised control would be impractical, as with
consumer electronics like game consoles [66]. Attempts
to control user machines counter to their self-interest
5 The triple bottom line (people, planet, profit) [60]. results in cracked systems, from black market hardware
modifications and arms races over hacking and securing higher price for their service provision. Interestingly, the
the software (routinely lost by the vendors) [66]. In the Community Cloud could provide a better QoS than vendor
Community Cloud, where no concrete vendors exist, it Clouds, utilising time-based and geographical variations
is even more important to avoid antagonising the users, advantageously in the dynamic scaling of resource provi-
instead embracing their self interest and harnessing it for sion.
the benefit of the community with measures such as a 9) Environmental Sustainability: We expect the Com-
community currency. munity Cloud to have a smaller carbon footprint than
4) Identity: In the Community Cloud each user would vendor Clouds, on the assumption that making use of
inherently possess a unique identity, which combined with underutilised user machines requires less energy than the
the structure of the Community Cloud should lead to dedicated data centres required for vendor Clouds. The
an inversion of the currently predominant membership server farms within data centres are an intensive form
model. So, instead of users registering for each website of computing resource provision, while the Community
(or service) anew, they could simply add the website to Cloud is more organic, growing and shrinking in a symbi-
their identity and grant access. Allowing users to have otic relationship to support the demands of the community,
multiple services connected to their identity, instead of which in turn supports it.
creating new identities for each service. This relationship 10) Service Composition: The great promise of service-
is reminiscent of recent application platforms, such as oriented computing is that the marginal cost of creating the
Facebook’s f8 and Apple’s App Store, but decentralised n-th application will be virtually zero, as all the software
in nature and so free from vendor control. Also, allowing required already exists to satisfy the requirements of other
for the reuse of the connections between users, akin to applications. Only their composition and orchestration are
Google’s Friend Connect, instead of reestablishing them required to produce a new application [70], [71]. Within
for each new application. vendor Clouds it is possible to make services that expose
5) Graceful Failures: The Community Cloud is not themselves for composition and compose these services,
owned or controlled by any one organisation, and therefore allowing the hosting of a complete service-oriented archi-
not dependent on the lifespan or failure of any one tecture [20]. However, current service composition tech-
organisation. It therefore ought be robust and resilient to nologies have not gained widespread adoption [72]. Digital
failure, and immune to the system-wide cascade failures of Ecosystems advocate service composability to avoid cen-
vendor Clouds, because of the diversity of its supporting tralised control by large service providers, because easy
nodes. When occasionally failing doing so gracefully, service composition allows coalitions of SMEs to compete
non-destructively, and with minimal downtime, as the simply by composing simpler services into more complex
unaffected nodes mobilise to compensate for the failure. services that only large enterprises would otherwise be
6) Convenience and Control: The Community Cloud, able to deliver [52]. So, we should extend decentralisation
unlike vendor Clouds, has no inherent conflict between beyond resource provision and up to the service layer, to
convenience and control, resulting from its community enable service composition within the Community Cloud.
ownership providing distributed control, which would
be more democratic. However, whether the Community B. Architecture
Cloud can provide technically quality equivalent or su-
perior to its centralised counterparts is an issue that will
require further research. Service Layer
7) Community Currency: The Community Cloud Repository, Composition, Execution
would require its own currency to support the sharing of
resources, a community currency, which in economics is a Resource Layer
medium (currency), not backed by a central authority (e.g. Computation, Persistence, Bandwidth, Currency
national government), for exchanging goods and services
within a community [67]. It does not need to be restricted
geographically, despite sometimes being called a local Coordination Layer
currency [68]. An example is the Fureai kippu system Virtual Machine, Identity, Networking, Transactions
in Japan, which issues credits in exchange for assistance
to senior citizens [69]. Family members living far from
their parents can earn credits by offering assistance to
the elderly in their local community, which can then be Figure 5. Community Cloud Computing: An architecture in which the
transferred to their parents and redeemed by them for local most fundamental layer deals with distributing coordination. One layer
above, resource provision and consumption are arranged on top of the
assistance [69]. coordination framework. Finally, the service layer is where resources
8) Quality of Service: Ensuring acceptable quality of are combined into end-user accessible services, to then themselves be
service (QoS) in a heterogeneous system will be a chal- composed into higher-level services.
lenge. Not least because achieving and maintaining the
different aspects of QoS will require reaching critical The method of materialising the Community Cloud
mass in the participating nodes and available services. is the distribution of its server functionality amongst a
Thankfully, the community currency could support long- population of nodes provided by user machines, shaping
term promises by resource providers and allow the higher their underutilised resources into a virtual data centre.
quality providers, through market forces, to command a While straightforward in principle, it poses challenges on
many different levels. So, an architecture for C3 can be provision. Such as in the DNS10 , which while nomi-
divided into three layers, dealing with these challenges nally distributed, remains under centralised control both
iteratively. The most fundamental layer deals with dis- technologically and organisationally, permitting numerous
tributing coordination, which is taken for granted in ho- distortions in the network. Including domain squatting11 ,
mogeneous data centres where good connectivity, constant abuses by domain registrars [81], subjection to political
presence and centralised infrastructure can be assumed. control [82], [83] and risks to the infrastructure being
One layer above, resource provision and consumption are compromised [84]. Identity in the Community Cloud has
arranged on top of the coordination framework. Easy in the to arise naturally from the structure of the network, based
homogeneous grid of a data centre where all nodes have on the relation of nodes to each other, so that it can scale
the same interests, but more challenging in a distributed and expand without centralised control. We can utilise the
heterogeneous environment. Finally, the service layer is property that a large enough identifier-space is unlikely to
where resources are combined into end-user accessible suffer collisions. For example, the Git distributed version
services, to then themselves be composed into higher-level control system [85] assigns a universal identifier to each
services. new commission, without coordination with other repos-
1) Coordination Layer: To achieve coordination, the itories. Analogously, assuming each node independently
nodes need to be deployed as isolated virtual machines, produces a private-public key pair, the probability of
forming a fully distributed P2P6 network that can provide public key collision is negligible. Also, from the human
support for distributed identity, trust, and transactions. identification of nodes we can utilise the property that each
node, despite formal identity, possesses a unique position
a) Virtual Machines (VMs): Executing arbitrary code in the network, i.e. set of connections to other nodes.
in the machine of a resource-providing user would require So, combining these two properties provides reasonable
a sandbox7 for the guest code, a VM8 to protect the certainty for a distributed identity model where universal
host. The role of the VM is to make system resources identification can be accomplished without centralised
safely available to the Community Cloud, upon which mediation, but this is still an active area of research.
Cloud processes could be run safely (without danger to c) Networking: At this level, nodes should be inter-
the host machine). Fortunately, feasibility has been proven connected to form a P2P network. Engineered to provide
with heavyweight VMs such as the Java Virtual Machine, high resilience while avoiding single points of control and
lightweight JavaScript VMs present in most modern web failure, which would make decentralised super-peer based
browsers, and new approaches such as Google’s Native control mechanisms [86] insufficient. Newer P2P designs
Client. Furthermore, the age [76] of multi-core processors9 [87] offer sufficient guarantees of distribution, immunity
has resulted in unused and underutilised cores being to super-peer failure, and resistance to enforced control.
commonplace in modern personal computers [78], which For example, in the Distributed Virtual Super-Peer (DVSP)
lend themselves well to the deployment and background model a collection of peers logically combine to form a
execution of Community Cloud facing VMs. Regarding virtual super-peer [87], which dynamically changes over
deployment, users would be required to maintain an active time to facilitate fluctuating demands.
browser window or tab, or install a dedicated application. d) Distributed Transactions: A key element of dis-
While the first would not require installation privileges, tributed coordination is the ability of nodes to jointly
the later would with the benefit of greater functionality. participate in transactions that influence their individual
However, more likely a hybrid of both would occur, facil- state. Appropriately annotated business processes can be
itating the availability and advantages of each in different executed over a distributed network with a transactional
scenarios. model maintaining the ACID12 properties on behalf of the
b) Distributed Identity: In distributed systems with initiator [89]. Newer transaction models maintain these
variable node reliability, historical context is logically properties while increasing efficiency and concurrency.
required to have certainty of node interactions. Funda- Other directions of research include relaxing these prop-
mental to this context is the ability to identify nodes and erties to maximise concurrency [90]. Others still, focus on
therefore reference previous interactions. However, current distributing the coordination of transactions [87]. A feature
identification schemes have identity providers controlling vital for C3, as distributed transaction capabilities are

10 The Domain Name System (DNS) is a hierarchical naming-space for

6 Peer-to-peer (P2P) computing or networking is a distributed applica- computers, services, and other resources participating in the Internet. It
tion architecture that partitions tasks or work loads between service translates domain names meaningful to humans into their counterpart
peers. Peers are equally privileged participants in the application, and numerical identifiers associated with networking equipment to locate
are said to form a peer-to-peer network of nodes [73]. and address these devices world-wide [79]. So, translating human-
friendly computer hostnames into Internet Protocol (IP) addresses, e.g.
7 A sandbox is a security mechanism for safely running programs, often www.example.com translates to 208.77.188.166.
used to execute untested code, or untrusted programs from unverified 11
third-parties, suppliers and untrusted users [74]. Domain squatting (also known as cybersquatting) is registering, traf-
ficking in, or using a domain name in bad faith, with the intent to profit
8 A virtual machine is a software implementation of a machine (com- from the goodwill of a trademark belonging to someone else. The
puter) that executes programs like a real machine [75]. cybersquatter then offers to sell the domain to the person or company
9 who owns a trademark contained within the name at an inflated price
A multi-core processor is an integrated circuit to which two or more [80].
processors have been attached for enhanced performance, reduced
power consumption, and more efficient simultaneous processing of 12 ACID (Atomicity, Consistency, Isolation, Durability) is a set of
multiple tasks [77]. properties that guarantee transactions are processed reliably [88].
fundamental to permitting multi-party service composition erable community currency, which they can then monetise
without centralised mediation. against participants running a community currency deficit
2) Resource layer: With the networking infrastructure (i.e. contributing less then they consume). The relative
now in place, we can consider the first consumer-facing cost of resources (storage, computation, bandwidth) should
uses for the virtual data centre of the Community Cloud. fluctuate based on market demand, not least because of the
Offering the usage experience of Cloud Computing on the impracticality of predicting or hard-coding such ratios. So,
PaaS layer and above, because Cloud Computing is about a node of the network would gather community currency
using resources from the Cloud. So, Utility Computing by performing tasks for the community, which its user
scenarios [91], such as access to raw storage and com- could then use to access resources of the Community
putation, should be available at the PaaS layer. Access to Cloud.
these abstract resources for service deployment would then e) Resource Repository: Given that each node pro-
provide the SaaS layer. viding resources has a different location in the network
a) Distributed Computation: The field has a success- and quality characteristics, a distributed resource reposi-
ful history of centrally controlled incarnations [92]. How- tory would be required that could respond to queries for
ever, C3 should also take inspiration from Grid Computing resources according to desired performance profiles. Such
and Digital Ecosystems to provide distributed coordination a query would have to consider historical performance,
of the computational capabilities that nodes offer to the current availability, projected cost and geographical dis-
Community Cloud. tribution of the nodes to be returned. A constraint opti-
b) Distributed Persistence: The Community Cloud misation problem, the results returned would be a set of
would naturally require storage on its participating nodes, nodes that fit the required profile, proportionally to the
taking advantage of the ever-increasing surplus on most13 availability of suitable nodes.
personal computers [94]. However, the method of infor- 3) Service Layer: Cloud Computing represents a new
mation storage in the Community Cloud is an issue with era for service-oriented architectures, making services
multiple aspects. First, information can be file-based or explicitly dependent on other resource providers instead
structured. Second, while constant and instant availability of building on self-sufficient resource locations. C3 makes
can be crucial, there are scenarios in which recall times this more explicit, breaking down the stand-alone service
can be relaxed. Such varying requirements call for a paradigm, with any service by default being composed
combination of approaches, including distributed storage of resources contributed by multiple participants. So, the
[95], distributed databases [96] and key-value stores [26]. following sections define the core infrastructural services
Information privacy in the Community Cloud should be that the Community Cloud would need to provide.
provided by the encryption of user information when on a) Distributed Service Repository (DSR): The ser-
remote nodes, only being unencrypted when accessed by vice repository of the Community Cloud must provide
the user, allowing for the secure and distributed storage of persistence, as with traditional service repositories [101],
information. for the pointers to services and their semantic descriptions.
c) Bandwidth Management: The Community Cloud To support the absence of service-producing nodes during
would probably require more bandwidth at the user service execution, there must also be persistence of the
nodes than vendor Clouds, but can take advantage of the executable code of services. Naturally, the implementation
ever-increasing bandwidth and deployment of broadband of a distributed service repository is made easier by the
[97]. Also, P2P protocols such as BitTorrent [98] make availability of the distributed storage infrastructure of the
the distribution of information over networks much less Community Cloud.
bandwidth-intensive for content providers, accomplished b) Service Deployment and Execution: When a ser-
by using the downloading peers as repeaters of the infor- vice is required, but is not currently instantiated on a
mation they receive. C3 should adopt such approaches to suitable node, a copy should be retrieved from the DSR
ensure the efficient use of available network bandwidth, and instantiated as necessary, allowing for flexible respon-
avoiding fluctuations and sudden rises in demand (e.g. the siveness and resilience to unpredictable traffic spikes. As
Slashdot effect14 ) burdening parts of the network. nodes are opportunistically interested in executing services
d) Community Currency: An important theme in the to gather community currency for their users, so developers
Community Cloud is that of nodes being contributors as should note the resource cost of their services in their
well as consumers, which would require a community cur- descriptions, allowing for pre-execution resource budget-
rency (redeemable against resources in the community) to ing, and post-execution community currency payments.
reward users for offering resources [100]. This would also Being in a developer’s own interest to mark resource
allow traditional Cloud vendors to participate by offering costs correctly, because over-budgeting would burden their
their resources to the Community Cloud to gather consid- users and under-budgeting would cause premature service
termination. Additionally, developers could add a subsidy
13 The only exception is the recent arrival of Solid-State Drives (SSDs), to promote their services. Remote service execution would
popular for mobile devices because of their lack of moving parts, need to be secured against potentially compromised nodes,
growing in use as their size and price reach that of traditional Hard perhaps through encrypted processing schemes [102]. Oth-
Disk Drives (HDDs) [93].
erwise, such nodes while unable to access a complete
14 The Slashdot effect, also known as slashdotting, is the phenomenon traffic log of the services they execute, could potentially
of a popular website linking to a smaller site, causing the smaller site
to slow down or even temporarily close due to the increased traffic access the business logic; and we would be replacing
[99]. the vendor introspection problem, with an anyone intro-
spection problem. Since delivering a service over large patches and step back through versions of infrastructural
distances in the network comes at a potentially high cost, services would be necessary to maintain the Community
the lack of a central well-connected server calls for a Cloud. Still, without a more granular approach to conflict
fundamental paradigm shift, from pull-oriented approaches resolution from different patching sources, poor developer
to hybrid push/pull-oriented approaches. So, instead of the relations could risk fragmentation of the codebase and
pull-oriented approach of supplying services only upon network. So, an alternative non-centralised software inno-
request [103], service provision should also follow a push- vation model would be required, such as the declarative
oriented approach of preemptive deployment to strategi- generative programming paradigm [104] mentioned.
cally suitable nodes, including modifying their deployment
profile based on the traffic patterns they face at run time. VII. I N T HE C OMMUNITY C LOUD
c) Programming Paradigm: A key innovation of While we have covered the fundamental motivations
Cloud Computing in its PaaS incarnation, is the offer- and architecture of the Community Cloud, its practical
ing of a well-specified context (programming paradigm) application may still be unclear. So, this section discusses
within which the services should be executed [20]. The the cases of Wikipedia and YouTube, where the application
programming paradigm that produces these services is also of C3 would yield significant benefits, because they have
important to C3, because it forms a contract between the unstable funding models, require increasing scalability,
service developers and resource providers. The current and are community oriented.
state-of-the-art requires manipulation of source code in
which each line is context dependent, and so a single A. Wikipedia
intended change may necessitates significant alterations Wikipedia suffers from an ever-increasing demand for
at different locations in the codebase. A paradigm shift resources and bandwidth, without a stable supporting
to declarative generative programming [104] would be revenue source [109]. Their current funding model re-
greatly beneficial, avoiding the need to manually manage quires continuous monetary donations for the maintenance
cascading changes to the codebase. As the requirements and expansion of their infrastructure [110]. The alterna-
behind a service would be made explicit and executable, tive being contentious advertising revenues [109], which
and being human readable could therefore be manipu- caused a long-standing conflict within their community
lated directly as stand-alone artifacts. Additionally, barriers [111]. While it would provide a more scalable funding
to service composition would be significantly decreased model, some fear it would compromise the content and/or
[105], beneficial to C3 and beyond. the public trust in the content [112]. Alternatively, the
Community Cloud could provide a self-sustaining scalable
C. Distributed Innovation resource provision model, without risk of compromising
When considering the Community Cloud over time, cur- the content or public trust in the content, because it
rent software distribution models would cause problems. would be compatible with their communal nature (unlike
Should the infrastructure be dependent on a single provider their current data centre model), with their user base
for updates, they would become a single point of control, accomplishing the resource provision they require.
and possibly failure. Entrusting a single provider with the Were Wikipedia to adopt C3, it would be distributed
power to control the evolution of the architecture, even throughout the Community Cloud alongside other services.
if they are considered benevolent, risks the development With the core operations of Wikipedia, providing web-
goals becoming misaligned with the community. There- pages and executing server-side scripts, being handled as
fore, the Community Cloud should follow an evolutionary service requests. Participants would use their community
software distribution model. Extending an already-growing currency to interact with Wikipedia, performing a search
trend of using distributed code repositories such as Git [85] or retrieving a page, while gaining community currency for
and Mercurial [106], over centralised code repositories helping to host Wikipedia across the Community Cloud.
such as Subversion [107] and CVS [108]. So, modifica- More complicated tasks, such as editing a Wikipedia web-
tions to services, including infrastructural ones, should be page, would require an update to the distributed storage of
distributed locally to migrate over the Community Cloud the Community Cloud, achieved by transmitting the new
from where they are deployed, making use of the existing data through its network of nodes, most likely using an
relationships between users. Users or their nodes (by eventual consistency model [90].
default) could even choose to follow the updates that other
trusted peers adopt. Therefore, new versions of a service B. YouTube
would compete with older versions, and where superior YouTube requires a significant bandwidth for content
(fitter) would distribute more widely, spreading further distribution, significant computational resources for video
across the Community Cloud. So, updates to services transcoding, and is yet to settle on a profitable business
would permeate through the network, in a distributed but model [113], [114]. In the Community Cloud, websites
regulated manner. We could even consider the updates to like YouTube would also have a self-sustaining scalable
services, as the release of patches (modifications), allowing resource provision model, which would significantly re-
for frequent, smaller and iterative releases more akin duce the income required for them to turn a profit.
to an evolutionary software distribution model. Potential Were YouTube to adopt C3, it would also be dis-
speciation (branching) would encourage developers to co- tributed throughout the Community Cloud alongside other
ordinate their releases and ensure their patches are viable services. Updates such as commenting on a YouTube
across different branches. Obviously, the ability to undo video, would similarly need to propagate through the
distributed persistence layer. So, the community would [4] J. Hayes, “Cred - or croak?” IET Knowledge Network, Tech.
provide the bandwidth for content distribution, and the Rep., 2008. [Online]. Available: http://kn.theiet.org/magazine/
issues/0820/cred-croak-0820.cfm?SaveToPDF
computational resources for video transcoding, required [5] P. Mckenna, “Can we stop the internet destroying our planet?”
for YouTube’s service. The QoS requirements for YouTube New Scientist, vol. 197, no. 2637, pp. 20–21, 2008.
are significantly different to those of Wikipedia, because [6] J. Kaplan, W. Forrest, and N. Kindler, “Revolutionizing data center
energy efficiency,” McKinsey & Company, Tech. Rep., 2008.
while constant throughput is desirable for video stream- [Online]. Available: http://www.mckinsey.com/clientservice/bto/
ing, occasional packet loss is tolerable. Also, YouTube’s pointofview/pdf/Revolutionizing Data Center Efficiency.pdf
streaming of live events has necessitated the services of [7] B. Leiner, V. Cerf, D. Clark, R. Kahn, L. Kleinrock, D. Lynch,
J. Postel, L. Roberts, and S. Wolff, “A brief history of the
bespoke content distribution networks [115], a type of internet,” Institute for Information Systems and Computer Media,
service for which the Community Cloud would naturally Tech. Rep., 2001. [Online]. Available: http://www.iicm.tugraz.
excel. at/thesis/cguetl diss/literatur/Kapitel02/References/Leiner et al.
2000/brief.html?timestamp=1197467969844
We have discussed Wikipedia and YouTube in the Com- [8] J. Scanlon and B. Wieners, “The internet cloud,” The
munity Cloud, but other sites such as arXiv and Facebook Industry Standard, Tech. Rep., 1999. [Online]. Available:
would equally benefit. As C3’s organisational model for http://www.thestandard.com/article/0,1902,5466,00.html
[9] I. Foster, Y. Zhao, I. Raicu, and S. Lu, “Cloud Computing
resource provision moves the cost of service provision and Grid Computing 360-degree compared,” in Grid Computing
to the user base, effectively creating a micro-payment Environments Workshop, 2008, pp. 1–10.
scheme, which would dramatically lower the barrier of [10] T. Foremski, “Sun services CTO says utility computing
entry for innovative start-ups. acceptance is slow going,” ZDNet, CBS Interactive, Tech. Rep.,
2006. [Online]. Available: http://blogs.zdnet.com/Foremski/?p=33
[11] A. Orlowski, “The Cell chip - how will MS and Intel face the
VIII. C ONCLUSIONS music?” The Register, Tech. Rep., 2005. [Online]. Available:
We have presented the Community Cloud as an alterna- http://www.theregister.co.uk/2005/02/03/cell analysis part two/
[12] J. Kephart, D. Chess, I. Center, and N. Hawthorne, “The vision
tive to Cloud Computing, created from blending its usage of autonomic computing,” Computer, vol. 36, no. 1, pp. 41–50,
scenarios with paradigms from Grid Computing, principles 2003.
from Digital Ecosystems, self-management from Auto- [13] G. Gruman and E. Knorr, “What Cloud Computing
nomic Computing, and sustainability from Green Com- really means,” InfoWorld Inc., Tech. Rep., 2008.
[Online]. Available: http://www.infoworld.com/article/08/04/07/
puting. So, C3 utilises the spare resources of networked 15FE-cloud-computing-reality 1.html
personal computers to provide the facilities of data centres, [14] Gartner, “Cloud Computing will be as influential as e-
such that the community provides the computing power for business,” Gartner, Tech. Rep., 2008. [Online]. Available:
http://www.gartner.com/it/page.jsp?id=707508
the Cloud they wish to use. A socio-technical conceptual- [15] P. Gaw, “What’s the difference between Cloud Computing
isation for sustainable distributed computing. and SaaS?” Proofpoint, Tech. Rep., 2008. [Online]. Available:
While the Open Cloud Manifesto [116] is well inten- http://blog.fortiva.com/fortivablog/2008/05/what-is-the-dif.html
[16] K. Danielson, “Distinguishing Cloud Computing from
tioned, its promotion of open standards for vendor Cloud Utility Computing,” ebizQ, Tech. Rep., 2008. [On-
interoperability has proved difficult [117]. We believe it line]. Available: http://www.ebizq.net/blogs/saasweek/2008/03/
will continue to prove difficult until a viable alternative, distinguishing cloud computing/
[17] M. Arregoces and M. Portolani, Data center fundamentals. Cisco
such as C3, is developed. Furthermore, we hope that the Press, 2003.
Community Cloud will encourage innovation in vendor [18] M. Turner, D. Budgen, and P. Brereton, “Turning software into a
Clouds, forming a relationship analogous to the creative service,” Computer, vol. 36, no. 10, pp. 38–44, 2003.
[19] T. Oreilly, “What is Web 2.0: Design patterns and business
tension between open source and proprietary software. models for the next generation of software,” O’Reilly Media,
In the future we will continue to refine the vari- Tech. Rep., 2008. [Online]. Available: http://www.oreillynet.com/
ous elements of C3, such as suitable mechanisms for pub/a/oreilly/tim/news/2005/09/30/what-is-web-20.html
[20] R. Buyya, C. Yeo, and S. Venugopal, “Market-oriented cloud
a community currency, distributed alternatives to DNS, computing: Vision, hype, and reality for delivering it services
DVSPs, RESTful Clouds, declarative generative program- as computing utilities,” in Conference on High Performance
ming paradigms, distributed innovation, and the environ- Computing and Communications. IEEE, 2008.
[21] A. Newman, A. Steinberg, and J. Thomas, Enterprise 2.0 Imple-
mental impact of the Community Cloud relative to vendor mentation. McGraw-Hill Osborne Media, 2008.
Clouds. [22] Amazon, “Amazon Elastic Compute Cloud (EC2),” Amazon
Web Services LLC, Tech. Rep., 2009. [Online]. Available:
ACKNOWLEDGEMENTS http://aws.amazon.com/ec2/
[23] Mosso, “Deploy and scale websites, servers and storage in
We would like to thank for comments and helpful minutes,” Rackspace, Tech. Rep., 2009. [Online]. Available:
discussions Paulo Siqueira of the Instituto de Pesquisas http://www.mosso.com/
em Tecnologia e Inovacao, Eva Tallaksen and Alexander [24] R. Buyya, C. Yeo, and S. Venugopal, “Market-oriented Cloud
Deriziotis. Computing: Vision, hype, and reality for delivering it services
as computing utilities,” in High Performance Computing and
Communications. IEEE Press, 2008.
R EFERENCES [25] Google, “Google App Engine: Run your web apps on Google’s
[1] M. Haynie, “Enterprise cloud services: Deriving business value infrastructure.” Google, Tech. Rep., 2009. [Online]. Available:
from Cloud Computing,” Micro Focus, Tech. Rep., 2009. http://code.google.com/appengine/
[2] R. L. Peter Lucas, Joseph Ballay, “The wrong cloud,” MAYA [26] T. Bain, “Is the relational database doomed?” ReadWriteWeb.com,
Design, Inc, Tech. Rep., 2009. [Online]. Available: http://www. 2008. [Online]. Available: http://www.readwriteweb.com/archives/
maya.com/file download/126/The%20Wrong%20Cloud.pdf is the relational database doomed.php
[3] M. Armbrust, A. Fox, R. Griffith, A. Joseph, R. Katz, [27] F. Chang, J. Dean, S. Ghemawat, W. Hsieh, D. Wallach, M. Bur-
A. Konwinski, G. Lee, D. Patterson, A. Rabkin, I. Stoica, rows, T. Chandra, A. Fikes, and R. Gruber, “Bigtable: A dis-
and M. Zaharia, “Above the Clouds: A Berkeley view tributed storage system for structured data,” in USENIX Sympo-
of Cloud Computing,” University of California, Berkeley, sium on Operating Systems Design and Implementation, 2006.
2009. [Online]. Available: http://d1smfj0g31qzek.cloudfront.net/ [28] G. DeCandia, D. Hastorun, M. Jampani, G. Kakulapati, A. Laksh-
abovetheclouds.pdf man, A. Pilchin, S. Sivasubramanian, P. Vosshall, and W. Vogels,
 “Dynamo: Amazon’s highly available key-value store,” in Sympo- [55] H. Khondker, “Glocalization as globalization: Evolution of a
sium on Operating Systems Principles. ACM, 2007, pp. 205–220. sociological concept,” Bangladesh e-Journal of Sociology, vol. 1,
[29] B. Johnson, “Cloud Computing is a trap, warns GNU pp. 1–9, 2004.
founder Richard Stallman,” The Guardian, Tech. Rep., 2008. [56] Glocal Forum and CERFE, “The glocalization manifesto,”
[Online]. Available: http://www.guardian.co.uk/technology/2008/ The Glocal Forum, Tech. Rep., 2004. [Online]. Avail-
sep/29/cloud.computing.richard.stallman able: http://www.glocalforum.org/mediagallery/mediaDownload.
[30] J. McCabe, Network analysis, architecture, and design. Morgan php?mm=/warehouse/documents/the glocalization manifesto.pdf
Kaufmann, 2007. [Online]. Available: http://books.google.co.uk/ [57] L. Rivera León. Digital Ecosystems Network of Regions
books?id=iddGPgR48 MC for Dissemination and Knowledge Deployment (DEN4DEK).
[31] A. Modine, “Web startups crumble under Amazon S3 outage,” [Online]. Available: http://www.den4dek.org
The Register, Tech. Rep., 2008. [Online]. Available: http://www. [58] P. Delcloque and A. Bramoullé, “DISSEMINATE, an initial im-
theregister.co.uk/2008/02/15/amazon s3 outage feb 2008/ plementation proposal: a new point of departue in call for the
[32] J. Montgomery, “Google Apps sees 99.9relia- ‘year 01’?” ReCALL, vol. 13, pp. 277–292, 2001.
bility”,” Tech.Blorge, Tech. Rep., 2008. [On- [59] E. Newcomer and G. Lomow, Understanding SOA with web
line]. Available: http://tech.blorge.com/Structure:%20/2008/11/ services. Addison-Wesley, 2005.
02/google-apps-sees-999-uptime-proves-cloud-reliability/ [60] J. Elkington, Cannibals with forks: the triple bottom line of 21st
[33] J. Perez, “Google Apps customers miffed over down- century business. New Society Publishers, 1998.
time,” IDG News Service, Tech. Rep., 2007. [On- [61] J. Williams and L. Curtis, “Green: The new computing coat of
line]. Available: http://www.pcworld.com/businesscenter/article/ arms?” IT PROFESSIONAL, pp. 12–16, 2008.
130234/google apps customers miffed over downtime.html [62] T. G. Grid, “About the green grid,” The Green Grid, Tech.
[34] Kable, “Carter recommends ’g cloud’ for gov it,” The Register, Rep., 2009. [Online]. Available: http://www.thegreengrid.org/
2009. [Online]. Available: http://www.channelregister.co.uk/2009/ about-the-green-grid
06/17/government cloud computing/ [63] J. Harris, Green Computing and Green It Best Practices on
[35] Environmental Protection Agency, “EPA report to congress on Regulations and Industry. Lulu.com, 2008.
server and data center energy efficiency,” US Congress, Tech. [64] J. West and J. Dedrick, “Proprietary vs. open standards in the
Rep., 2007. network era: An examination of the linux phenomenon,” in System
[36] R. Miller, “NSA maxes out Baltimore power grid,” Sciences. IEEE Press, 2001, p. 10.
Data Center Knowledge, Tech. Rep., 2006. [Online]. [65] Y. Benkler, “Sharing nicely: on shareable goods and the emer-
Available: http://www.datacenterknowledge.com/archives/2006/ gence of sharing as a modality of economic production,” The Yale
08/06/nsa-maxes-out-baltimore-power-grid/ Law Journal, vol. 114, no. 2, pp. 273–359, 2004.
[37] K. McIsaac, “The data centre goes green, the CFO saves money,” [66] J. Grand, F. Thornton, A. Yarusso, and R. Baer, Game Console
Intelligent Business Research Services, Tech. Rep., 2007. Hacking: Have Fun While Voiding You Warranty. Syngress Press,
[38] C. Wolf and E. Halter, Virtualization: from the desktop to the 2004.
enterprise. Apress, 2005. [67] T. Greco, Money: Understanding and creating alternatives to legal
[39] R. Talaber, T. Brey, and L. Lamers, “Using virtualization to tender. Chelsea Green, 2001.
improve data center efficiency,” The Green Grid, Tech. Rep., 2009. [68] A. Doteuchi, “Community currency and NPOs- A model for
solving social issues in the 21st century,” Social Development
[40] K. Brill, “The invisible crisis in the data center: The economic
Research Group, NLI Research, 2002. [Online]. Available: http://
meltdown of Moore’s law,” Uptime Institute, Tech. Rep., 2007.
www.nli-research.co.jp/english/socioeconomics/2002/li0204a.pdf
[41] J. Brodkin, “Gartner in ‘green’ data centre warning,” Techworld,
[69] B. Lietaer, “Complementary currencies in japan today: History,
2008. [Online]. Available: http://www.techworld.com/green-it/
originality and relevance,” International Journal of Community
news/index.cfm?newsid=106292
Currency Research, vol. 8, pp. 1–23, 2004.
[42] Microsoft, “Azure services platform,” Micrsoft, Tech. Rep., 2009. [70] Q. Tang, “Economics of web service provisioning: Optimal market
[Online]. Available: http://www.microsoft.com/azure/ structure and intermediary strategies,” Ph.D. dissertation, Univer-
[43] C. Metz, “The Meta Cloud - flying data centers enter fourth sity of Florida, 2004.
dimension,” The Register, Tech. Rep., 2009. [Online]. Available: [71] G. Modi, “Service oriented architecture & web 2.0,” Guru Tegh
http://www.theregister.co.uk/2009/02/24/the meta cloud/ Bahadur Institute of Technology, Tech. Rep., 2007. [Online].
[44] T. Kulmala, “The cloud’s hidden lock-in: Latency,” Archivd, Available: http://www.gsmodi.com/files/SOA Web2 Report.pdf
2009. [Online]. Available: http://blog.archivd.com/1/post/2009/ [72] B. Violino. (2007) How to navigate a sea of SOA standards.
04/the-clouds-hidden-lock-in-latency.html [Online]. Available: http://www.cio.com/article/104007/How to
[45] D. Nurmi, R. Wolski, C. Grzegorczyk, G. Obertelli, S. Soman, Navigate a Sea of SOA Standards
L. Youseff, and D. Zagorodnov, “The Eucalyptus open-source [73] R. Schollmeier, “A definition of peer-to-peer networking for the
cloud-computing system,” in Cloud Computing and Its Applica- classification of peer-to-peer architectures and applications,” in
tions, 2008. International Conference on Peer-to-Peer Computing. IEEE
[46] J. Abbate, Inventing the internet. MIT press, 1999. Press, 2002, pp. 101–102.
[47] I. Foster and C. Kesselman, The grid: blueprint for a new [74] M. Bishop, Computer Security. Addison-Wesley, 2004.
computing infrastructure. Morgan Kaufmann, 2004. [75] I. Craig, Virtual machines. Springer, 2006.
[48] G. Briscoe and P. De Wilde, “Digital Ecosystems: Evolving [76] D. Geer, “Chip makers turn to multicore processors,” IEEE
service-oriented architectures,” in Conference on Bio Inspired Computer, vol. 38, no. 5, pp. 11–13, 2005.
Models of Network, Information and Computing Systems. IEEE [77] M. Zelkowitz, Advances in Computers: Architectural Issues. Aca-
Press, 2006. [Online]. Available: http://arxiv.org/abs/0712.4102 demic Press, 2007.
[49] G. Briscoe, “Digital ecosystems,” Ph.D. dissertation, Imperial [78] B. Posey, “Multi-core processors: Their implication
College London, 2009. for Windows,” TechTarget, Tech. Rep., 2007. [On-
[50] L. Rivera León. Regions for Digital Ecosystems Network line]. Available: http://searchwindowsserver.techtarget.com/tip/0,
(REDEN). [Online]. Available: http://reden.opaals.org/ 289483,sid68 gci1248527,00.html
[51] P. Dini, G. Lombardo, R. Mansell, A. Razavi, S. Moschoyiannis, [79] P. Mockapetris and K. Dunlap, “Development of the domain name
P. Krause, A. Nicolai, and L. Rivera León, “Beyond interop- system,” Computer Communication Review, vol. 18, no. 4, pp.
erability to digital ecosystems: regional innovation and socio- 123–133, 1988.
economic development led by SMEs,” International Journal of [80] M. Maury and D. Kleiner, “E-commerce, ethical commerce?”
Technological Learning, Innovation and Development, vol. 1, pp. Journal of Business Ethics, vol. 36, no. 1, pp. 21–31, 2002.
410–426, 2008. [81] G. Lyon, “Exposing the many reasons not to trust godaddy with
[52] F. Nachira, A. Nicolai, P. Dini, M. Le Louarn, and L. Rivera León, your domain names,” NoDaddy.com, Tech. Rep., 2009. [Online].
Eds., Digital Business Ecosystems. European Commission, 2007. Available: http://nodaddy.com/
[53] R. Robertson, “Globalisation or glocalisation,” Journal of Inter- [82] M. Mueller, Ruling the root: Internet governance and the taming
national Communication, vol. 1, pp. 33–52, 1994. of cyberspace. MIT press, 2002.
[54] E. Swyngedouw, “The mammon quest. ‘Glocalisation’, interspa- [83] (2006) Chinese walls. [Online]. Available: http://www.economist.
tial competition and the monetary order: the construction of new com/business/displaystory.cfm?story id=5582257
scales,” in Cities and regions in the new Europe: The Global- [84] D. Goodin, “DNS patch averts doomsday scenario,” The Register,
local Interplay and Spatial Development Strategies, M. Dunford Tech. Rep., 2008. [Online]. Available: http://www.theregister.co.
and G. Kafkalas, Eds. Wiley, 1992, pp. 39–67. uk/2008/08/06/kaminsky black hat/
 [85] S. Chacon, “About Git,” GitHub, Tech. Rep., 2009. [Online]. [115] M. Arrington, “Google relies on akamai to stream youtube
Available: http://git-scm.com/about live; 700,000 concurrent viewers,” TechCrunch, 2008.
[86] J. Risson and T. Moors, “Survey of research towards robust peer- [Online]. Available: http://www.techcrunch.com/2008/11/22/
to-peer networks: Search methods,” Computer Networks, vol. 50, google-relies-on-akamai-to-stream-youtube-live-700000-concurrent-viewers/
pp. 3485–3521, 2006. [116] “Open cloud manifesto,” OpenCloudManifesto.org, Tech. Rep.,
[87] A. Razavi, S. Moschoyiannis, and P. Krause, “A scale-free busi- 2009. [Online]. Available: http://www.opencloudmanifesto.org/
ness network for digital ecosystems,” in IEEE Conf. on Digital Open%20Cloud%20Manifesto.pdf
Ecosystems and Technologies, 2008. [117] C. Metz, “What’s an open cloud? the manifesto’s not telling,”
[88] T. Haerder and A. Reuter, “Principles of transaction-oriented The Register, 2009. [Online]. Available: http://www.theregister.
database recovery,” ACM Computing Surveys, vol. 15, no. 4, pp. co.uk/2009/03/31/amazon on cloud manifesto/
287–317, 1983. [118] C. Hewitt, “ORGs for scalable, robust, privacy-friendly client
[89] A. Fox, S. Gribble, Y. Chawathe, E. Brewer, and P. Gauthier, Cloud Computing,” IEEE Internet Computing, vol. 12, no. 5, 2008.
“Cluster-based scalable network services,” ACM SIGOPS Operat- [119] A. Avram, “Architecting for green computing,” InfoQ.com,
ing Systems Review, vol. 31, no. 5, pp. 78–91, 1997. 2008. [Online]. Available: http://www.infoq.com/news/2008/12/
[90] W. Vogels, “Eventually consistent,” ACM Queue, vol. 6, 2008. Architecture-Green-Computing
[91] M. Rappa, “The utility business model and the future of computing [120] A. Weiss, “Computing in the clouds,” netWorker, vol. 11, pp. 16–
services,” IBM Systems Journal, vol. 43, no. 1, pp. 32–42, 2004. 25, ACM Press, 2007.
[92] H. Attiya and J. Welch, Distributed computing: fundamentals, [121] G. Briscoe and A. Marinos, “Digital ecosystems in the clouds:
simulations, and advanced topics. Wiley-Interscience, 2004. Towards community cloud computing,” in Digital Ecosystems
[93] C. Mellor, “Ssd and hdd capacity goes on embiggening,” The and Technologies Conference. IEEE Press, 2009. [Online].
Register, Tech. Rep., 2009. [Online]. Available: http://www. Available: http://arxiv.org/abs/0903.0694
theregister.co.uk/2009/01/09/ssd and hdd capacity increases/
[94] M. Daley, “Software bloat,” MattsComputerTrends.com, Tech.
Rep., 2009. [Online]. Available: http://www.mattscomputertrends.
com/softwarebloat.html
[95] P. Yianilos and S. Sobti, “The evolving field of distributed
storage,” IEEE Internet Computing, vol. 5, pp. 35–39, 2001.
[96] H. Garcia-Molina, J. Ullman, and J. Widom, Database Systems:
The complete book. Prentice Hall, 2008.
[97] “Broadband growth and policies in OECD countries,” Organisa-
tion for Economic Co-operation and Development, Tech. Rep.,
2008.
[98] B. Cohen, “Incentives build robustness in BitTorrent,” in Workshop
on Economics of Peer-to-Peer Systems, vol. 6, 2003.
[99] S. Adler, “The Slashdot effect: An analysis of three internet
publications,” Linux Gazette, vol. 38, 1999.
[100] D. Turner and K. Ross, “A lightweight currency paradigm for the
p2p resource market,” in International Conference on Electronic
Commerce Research, 2004.
[101] M. Papazoglou, “Service-oriented computing: concepts, charac-
teristics and directions,” in International Conference on Web
Information Systems Engineering, T. Catarci, M. Mecella, J. My-
lopoulos, and M. Orlowska, Eds. IEEE Press, 2003, pp. 3–12.
[102] C. Gentry, “Fully homomorphic encryption using ideal lattices,” in
Symposium on Theory of computing. ACM, 2009, pp. 169–178.
[103] M. Singh and M. Huhns, Service-Oriented Computing: Semantics,
Processes, Agents. Wiley, 2005.
[104] A. Marinos and P. Krause, “What, not how: A generative approach
to service composition,” in Digital Ecosystems and Technologies
Conference. IEEE Press, 2009.
[105] ——, “Using sbvr, rest and relational databases to develop in-
formation systems native to the digital ecosystem,” in Digital
Ecosystems and Technologies Conference. IEEE Press, 2009.
[106] S. Arseanrapoj, “Mercurial: Source control management system,”
Mercurial, Tech. Rep., 2009. [Online]. Available: http://mercurial.
selenic.com/wiki/
[107] Tigris, “Subversion: open source version control sys-
tem,” Tigris.org, Tech. Rep., 2009. [Online]. Available:
http://subversion.tigris.org/
[108] D. Price, “Cvs - concurrent versions system,” nongnu.org, Tech.
Rep., 2009. [Online]. Available: http://www.nongnu.org/cvs/
[109] Heebie Blog, “Wikipedia Fundraising: The real truth,” Heebie
Intuitive Design, Tech. Rep., 2009. [Online]. Available: http:
//blog.heebie.co.uk/wikipedia-fundraising-real-truth
[110] A. Modine, “Wales’ personal begging earns last $2m,” The
Register, Tech. Rep., 2009. [Online]. Available: http://www.
theregister.co.uk/2009/01/02/wikipedia fundraising 2m jan 2/
[111] W. Roelf, “Wikipedia founder mulls revenue options,” Reuters,
Tech. Rep., 2007. [Online]. Available: http://www.reuters.com/
article/internetNews/idUSL1964587420070420
[112] H. Leslie, “Wikipedia to run out of money?” Digital-Lifestyles,
Tech. Rep., 2007. [Online]. Available: http://digital-lifestyles.
info/2007/02/12/wikipedia-to-run-out-of-money/
[113] C. Metz, “Google accused of avoiding youtube revenues,” The
Register, 2009. [Online]. Available: http://www.theregister.co.uk/
2009/06/18/google youtube loses/
[114] D. Silversmith, “Google losing up to $1.65m a
day on youtube,” Internet Evolution, 2009. [Online].
Available: http://www.internetevolution.com/author.asp?section
id=715&doc id=175123&