AI Technologies for

Tactical Edge Networks

Karen Zita Haigh

Raytheon BBN Technologies
May 2011

Page 1
 What is AI?
Economics
Natural
Language
Mathematics Processing
Artificial Speech
Psychology Intelligence Recognition
Machine Vision
Control Theory Robotics

The Odd Paradox

Practical AI successes … were soon assimilated into whatever
application domain they were found to be useful in, and became silent
partners …, which left AI researchers to deal only with the failures.”
[McCorduck, 2004]

Karen Zita Haigh Page 2

 Joe Mitola’s OOPDAL Loop

Joseph Mitola III, Cognitive Radio: An Integrated Agent Architecture for Software
Defined Radio, Phd Thesis, Royal Institute of Technology (KTH), 2000
Karen Zita Haigh Page 3
 Joe Mitola’s OOPDAL Loop (2)

Orient
Assess situation
Infer Intent
Impact Analysis Plan
Select Goals
Generate Plans
Observe Learn Schedule

Collect
Update
Validate
Models
Decide
Select Plan
Act Allocate Resources

Implement

Karen Zita Haigh Page 4

 Roles for AI in Networking
• Cyber Security • Sensor fusion /
• Network Configuration situation assessment
(which modules to use) • Planning
• Network Control (which • Coordination
parameter settings to • Optimization
use) • Constraint reasoning
• Policy Management • Learning (Modelling)
• Traffic Analysis – Complex Domain
• Performance Analysis – Dynamic Domain
 Unpredictable by
Experts

AI enables real-time, context-aware adaptivity

Page 5
 MANET Characteristics
What AI is good at Main challenges for AI
• Dynamic • Ambiguous feedback
• Diverse • High-latency feedback
• Massive Scale
• Resource Constrained
• Complex Parameter
Interactions • Heterogeneous
• Partially-observable Intercommunication
feedback
• Complex Access Policies
• Multi-objective
performance requirements

Cross-Layer Optimization on Steroids

Karen Zita Haigh Page 6
 Knowledge Engineering
• Captures knowledge so that a computer system
can solve complex problems, e.g.
– models of physics and signal propagation, constraints
on the system, analysis of interactions, and rules of
thumb (e.g., about how to configure the system).
• A formal ontology may help a cognitive system
reason about how and when capabilities are
interchangeable
• Knowledge bases can help optimize the network
– e.g. By biasing a learning algorithm
– e.g. By constraining a planner

Karen Zita Haigh Page 7

 Planning and Scheduling
• Organizes tasks to meet performance objectives
under resource constraints
– Multi-agent planning, dynamic programming, constraint
satisfaction, and distributed or combinatorial
optimization algorithms
• Planning and scheduling techniques in networks
can decide what content to move, where, when,
and how
– Prefetch / prepush data
– Power-aware computing
– Node activity and task scheduling
– Network management
– Server placement; when to handle queries

Karen Zita Haigh Page 8

 Multi-Agent Systems
• Traditional MAS approaches fail in MANET
because they assume that communications are (a)
infinite and (b) always available
• Biologically-inspired approaches have done better.
• Demonstrated Applications:
– Routing: AntHocNet uses both proactive and reactive
schemes to update the routing tables, and outperforms
AODV.
– Network connectivity
– Dynamic load balancing
– Service placement

Karen Zita Haigh Page 9

 Machine Learning
• ML improves the performance of a system by
observing the environment and updating models
– the learner must generalize so that the learned model is
useful for new (previously unseen) situations.
– Artificial neural networks, support vector machines,
clustering, explanation-based learning, induction,
reinforcement learning, genetic algorithms, nearest
neighbour methods, and case-based learning.
• Demonstrated Applications
– Routing
– Energy management
– Node mobility
– Parameter interaction

Karen Zita Haigh Page 10

 Concrete Example: ML in
ADROIT
• Adaptive Dynamic Radio Open-source Intelligent
Team (ADROIT)
• Create cognitive radio teams that
– Recognize that the situation has changed
– Anticipates changes in networking needs
– Adapts the network, in real-time, for improved
performance
• Real-time composability of the stack
• Real-time control of parameters
• On one node and across the network

Page 11
 ADROIT’s Experimental
Testbed

Maximize %
of shared
map of the
environment
Page 12
 Experimental Results
Training Run: Real-time learning run:
• In first run nodes learn • In second run, nodes adapt
about environment behaviour to perform
• Train neural nets with better.
(Conditions,Strategy)Performance • Adapt each minute by
tuples changing strategy
– Every 5s, measure and according to current
record progress, conditions, conditions
& strategy
– Observations are local, so
each node learns different
model!

Real-time cognitive control of a

real-world wireless network
Page 13
 Observations from Learning
System performed better with learning
• Selected configurations explainable but not
predictable
– Farthest-refraining was usually better
• congestion, not loss dominated
– Unicast/Multicast was far more complex
• close: unicast wins (high data rates)
• medium: multicast wins (sharing gain)
• far: unicast wins (reliability)

14
Page 14
 Biggest remaining challenges
• Social engineering
– the human-to-human interaction of the AI
community differs dramatically from that of the
networking community
• Software architecture
– Network architectures are traditionally tightly
coupled; we need to provide hooks
Module 2
Module 2

Broker
Module 1
Module 1

May 2011 Karen Zita Haigh Page 15

 SOFTWARE
ARCHITECTURE

May 2011 Karen Zita Haigh Page 16

 A Need for Restructuring
• SDR gives opportunity to create highly-
adaptable systems, BUT
– They usually require network experts to exploit
the capabilities! Module 2
– They usually rely on module APIs that are
carefully designed to expose each parameter
separately. Module 1

• This approach is not maintainable

– e.g. as protocols are redesigned or new
parameters are exposed.

• This approach is not amenable to real-time

cognitive control
– Hard to upgrade
– Conflicts between module & AI

Page 17
 A Need for Restructuring
• We need one consistent, generic, interface
for all modules to expose their parameters
and dependencies.

Module 2

Module 1

Page 18
 A Generic Network
Architecture
Network Stack Broker Applications / QoS

Registering
- Assigns Modules &
Registering
handles Parameters
Modules Cognitive Control
Network Module

- Provides
directory
Re/Setting services
Modules Re/Setting Network Management
- Sets up event Modules
monitors
- Pass through
Network Module
Observing get/set Observing Command Line
Params Interface
Params

exposeParameter( parameter_name, parameter_properties )

setValue( parameter_handle, parameter_value )
getValue( parameter_handle )

Page 19
 Benefits of a Generic
Architecture
• It supports network architecture design &
maintenance
– Solves the nхm problem (upgrades or
replacements of network modules)
• It doesn’t restrict the form of cognition
– Open to just about any form of cognition you
can imagine
– Supports multiple forms of cognition on each
node
– Supports different forms across nodes
• It doesn’t mandate cognition
20
Page 20
 SOCIAL ENGINEERING

May 2011 Karen Zita Haigh Page 21

 Cultural Issues: But why?
• Benefits and scope of • Traditional network
cross-layer design: design includes
– More than 2 layers! adaptation
– More than 2-3 – But this works against
parameters per layer cognition: it is hard to
manage global scope
 Drill-down walkthroughs – AI people want to control
highlighted benefits to everything
networking folks; – But network module may
explained restrictions to be better at doing
AI folks something focussed
 Simulation results for
specific scenarios  Design must include
demonstrated the power constraining how a
protocol adapts
Page 22
 Cultural Issues: But how?
• Reliance on centralized • Asynchrony and
Broker: Threading:
– Networking folks don’t – AI people tend to like
like the single bottleneck blocking calls.
 Design must have fail- • e.g. to ensure that
safe default operation everything is consistent
– Networking folks outright
rejected it.
 Design must include
reporting and alerting

Page 23
 Cultural Issues: But it’ll
break!?!
• Relinquishing control • Heterogeneous and
outside the stack: non-interoperable
– Outside controller nodes
making decisions scares – Networks usually have
networking folks homogeneous
– AI folks say “give me configurations to
everything & I’ll solve maintain
your problem” communications
– AI likes heterogeneity
 Architecture includes because of the benefit
“failsafe” mechanisms to • But always assumes safe
limit both sides communications!

 “Orderwire” bootstrap
channel as backup
Page 24
 Cultural Issues: New horizons?
• Capability Boundaries
– Traditional Networking has very clear boundary
between “network” and “application”
– Generic architecture blurs that boundary
• AI folks like the benefit
• Networking folks have concerns about complexity
Removing this conceptual restriction will
result in interesting and significant new
ideas.

Page 25
 Conclusion
• AI techniques are ready to be
challenged with this complex real-world
domain, just as Networking
requirements are reaching the limits of
what can be done without AI.

• To demonstrate the power of cognitive

networking, both AI folks & Networking
folks need to recognize and adapt
Page 26