CHAPTER-I

INTRODUCTION

As the level of air pollution continually rises and the degradation of

the environment increases, the entire world is searching for different ways
to tackle this problem. One of the best ways to control air pollution is to
reduce vehicular pollution. Electric vehicles (EVs) are a ground-breaking
step taken in this direction. And the use of IoT can help companies to get
various insights about Electric Vehicles and help them to improve
customers’ experience.
Electric vehicles are hi-tech machines that collect a lot of data to deliver
optimum performance to the users. IoT plays a vital role in monitoring
performance parameters, including speed monitoring, acceleration,
mileage, battery management, charging, fault alert, and service
maintenance system.-
In this chapter, we explore ‌the aspects of an IoT for electric vehicle
monitoring & management system.

Figure 2.1 Benefit of IoT in Electrical Vehicles

1
2.1 Benefits of IoT in Monitoring & Management
Let’s take a look at some key features of IoT in electric vehicle
monitoring & management system, and the different ways in which they
increase the overall performance of electric vehicles

2.1.1 IoT in Battery Management System

Battery Management System (BMS) is mainly used to monitor and
control the process of the battery. The BMS helps to monitor the charging
and discharging cycle of the battery and ensures the battery’s health and
also minimizes the risk of damage by confirming that enhanced energy is
being delivered to power the electric vehicle.

In the Battery Management System (BMS), the monitoring circuit

monitors the key parameters of the battery. This will include the voltage,
current, temperature, and temperature during the charging and discharging
of the battery. It also evaluates the key parameters of the battery such as
the power, State of Charge (SoC), and State of Health (SoH) and enables
healthy life of the battery based on the measurement. Internet of Things.
(IoT) plays a vital role in monitoring and controlling the battery lifecycle
as it enables the remote data logging facility for battery parameters,
conditions, etc.

2.1.2 IoT in Safe and Smart Driving

We can monitor the real-time data of the vehicles and their key
components. It provides users with a bunch of information offered by the
technology, making the users find it more reliable.
IoT devices embedded in Electric Vehicles can provide users with the
following information:

2
  It helps in monitoring the driver’s performance and the key
parameters like the speed of the vehicle, acceleration, and
temperature, and provides real-time tips to ensure better
performance.
 We can prevent the theft of vehicles through real-time tracking, geo-
fencing, and immobilization. Thus, IoT provides better safety and
security and reduces the dependency on insurance.
 IoT will monitor the performance data of the vehicle based on which
EV and battery manufacturing companies can improve their
products. The data provided by IoT includes a range for each charge,
battery life cycle, utilization of a vehicle, performance differences
based on geography, weather conditions, age, and change in range
for each charge over a certain period of time.

2.1.3 Theft Proofing

The current prices of Electric Vehicles are more expensive than the
normal petrol or diesel engine-based vehicles. Two Wheelers are more
prone to theft, as the cost of a battery is expensive, and IoT could help in
more effective tracking. The cost of the battery alone is 40% of the total
cost of EVs. So, it is very necessary to protect them from theft. Electric
Vehicles are also used by on-demand Apps Companies for food delivery,
cargo delivery, bike-sharing, hyper-local delivery etc. In such situations,
IoT can be used to track down the real-time location of EVs in case they
are stolen. These IoT devices can also raise an alarm and notify the owner
about the theft.

2.1.4 Fall Down / Crash Detection

Most IoT devices have built-in accelerometers which can monitor
the acceleration and angle of the vehicle. So, if there is a sudden change in

3
acceleration and angle of the vehicle can be detected easily by IoT, and it
notifies the owner about a fall down or crash. This can also be very useful
to inform about severe accidents.

2.1.5 Ease of Leasing Batteries

The performance and location tracking of batteries are one of the
most important features for battery swapping and leasing companies. The
swapping of batteries can be easily tracked and monitored from the
swapping stations. To track or monitor the batteries IoT can play a major
role and also prevent the theft and loss of the battery.

2.1.6 Fault Alert and Predictive Maintenance System

An electric vehicle, being a high-tech machine, is bound to
experience technical faults. Using IoT Fault alert systems, it alerts vehicle
drivers regarding the faults or glitches and gives them enough time to act
and address them.
By using an IoT we can detect the charge cycle of the vehicle,
kilometres travelled, the temperature of the battery, etc. and we can use this
data for regular maintenance of the tires, lubrication cycle, battery life, and
monitoring other wear and tear parts of the vehicles and replacing them on
the time. This could help in averting the damage to the vehicle and also
helps in increasing the life of the vehicle and its batteries. This will help in
better customer experience as they will find it to be more reliable.

2.2 IoT’s Disadvantages in Electric Vehicle Management and Monitoring

As we already saw the advantages of IoT in Electric Vehicle
Monitoring & Management, now we must also address possible challenges:

4
Figure 2.2 Disadvantages of IoT in Electric Vehicle Monitoring

2.2.1 Risk of Cyber Attack

Since we have added so many devices to the Internet and the use of a
high amount of data sent over a network makes this data more vulnerable
to cyber-attacks and data thefts. Hackers may access the system and steal
personal information and it can be misused. Therefore, the IoT devices
connected to the EV and collecting the overall data should be strengthened
and made more hackproof.

2.2.2 High Cost of Electric Vehicles

IoT systems used in Electric Vehicles are quite advanced and have
high installation and running costs, so it makes the overall EV more
expensive. In the near future, there is a possibility to reduce the overall
costs by doing more R&D in this area.

2.2.3Technical complexity

5
 In the IoT System, the designing, developing, maintaining, and
enabling the extensive technology is quite complicated thus the overall
design of EVs becomes more complex and not easy to handle.

2.2.4 Connectivity and power dependence

IoT devices used in EVs have a dependency on the internet and
continuous power to function and provide real-time data properly. When
either goes down, so does the device and anything connected to it will also
go down. So, it will also affect the overall performance of EVs.

2.3 Block Diagram of IoT Based Electrical Vehicle Monitoring System

Figure 2.3 Block Diagram of IoT based Electric Vehicle Monitoring

CHAPTER-II

6
 LITERATURE REVIEW

2.1 IOT based Electric Vehicles – Implementation- October 2022

In today's world, autonomous automation is inspiring researchers,
and growing human needs are driving students and scientists to build new
automation devices. This paper will help you understand the changing
trends in self-driving car technology. Advances and upgrades in technology
have improved their performance and usage. The most important
requirement for an automated device or vehicle is the Communication
between them. In addition, the Government of India attaches great
importance to military progress. In this regard, this paper focuses on a
perfect connection system between remote controlled bots, as long as the
connection is not an obstacle. To achieve this goal, the relay device (with
Raspberry Pi) is configured as a repeater of the connection network that
connects the remote control to the vehicle (bot). In this project, the Wi-Fi
adapter will act as a beacon or extender to extend the connectivity and
range of remote vehicles. This connection allows the bot to easily capture
live feeds and send data for face recognition on the receiving side. This
project leverages advanced research on network configurations and
intercommunication schemes for IoT devices. The range of remote
connections is Extended by the relay chain method. This further improves
the connection with the bot through subsequent relay bots, making data
transmissions untraceable and encrypted. By using existing algorithms,
obstacles and Suspicious activity can be easily detected and sent to military
bases.
2.2 AI and IoT-based Electric Vehicle Monitoring System- December
2022
In this technology world, technology is increasing by giving
solutions to many problems. By using this technology, a solution for

7
decreasing air pollution is implemented. The main cause of increasing air
pollution is using various kinds of vehicles that run on combustion engines
for transportation utilities. The implementation of Electric Vehicle (EVs)
can resolve this air pollution problem and keeps the environment as
pollution-free air and the world can survive in pure air. EVs are like
machines that run on a charging battery. An EV’s condition is depending
on the battery’s performance. The parameters for the battery’s condition
the voltage, current, and temperature. By using these parameters State of
Charge (SOC) is determined. These performances are monitored as Battery
Management System (BMS). In this paper, the EV monitoring system is
implemented using the combination of Artificial Intelligence (AI) and
Internet of Things (IoT) interfacing by the sensors in the vehicle’s battery,
and to the cloud. The performance of the battery is monitored using the
mobile application of the cloud.

2.3 Research on Intelligent Power Management and Control

Technology of Electric Vehicle Based on Edge Computing- May 2021
With the development of smart grid, Internet of things devices are
widely used in the field of power management and control. The diversity of
IOT equipment types, characteristics and functions not only integrates
detailed big data, but also challenges the real-time, compatibility and big
data processing ability of system management and control. Among them,
electric vehicle is a kind of electrical equipment with random power
consumption and strong impact in the current power grid. This paper
studies an embedded edge computing technology in the power Internet of
things system, proposes an implementation scheme of edge computing
based on vehicle terminal, and designs a vehicle terminal hardware
platform with ArmCortex-A7 and EMMC as the computing core, which is
based on Embedded Linux system and socket virtual machine. The

8
technology develops an edge computing platform to meet the simultaneous
operation of multiple data applications, processes the massive intelligent
power consumption data of electric vehicles nearby, avoids the
communication channel blockage caused by massive data transmission,
and meets the special requirements of power Internet of things for rapid
response and accurate execution. Experiments show that the proposed
technology can not only provide safe and fast control mode, but also make
the system have stronger power consumption information big data
acquisition ability, and has advantages in low bandwidth and low delay
applications.

2.4 Remote Electric Vehicle Battery Monitoring & Life Cycle

Management System- October 2022
The Internet of things (IoT) is one of the most revolutionary
technologies leading experts have created today. The ever-increasing
number of devices and embedded systems has made it a necessity for IoT
to be implemented in every corner of the world. The latest technology for
electric vehicles uses IoT monitoring and life cycle management. Even
though there is a sophisticated battery management system in the present
Electric Vehicles, there is always a chance of battery damage due to
numerous instances caused by battery overcharge and exposure to high/low
temperatures. It may prevent battery damage if the battery level is indicated
well in advance, similar to “reserve” in the petrol car. In this paper, battery
monitoring is implemented using IoT and MQTT protocol based on the
battery levels, and the navigation to the nearest available charging station is
also displayed.

9
2.5 Intelligent monitoring system to help ensure efficient EV
performance- August 2022
Delhi-based Vecmocon Technologies has developed a vehicle
intelligence system with critical battery data collection and monitoring,
such as cell voltages, temperature, and the current health of the
battery. The company, incubated at FITT-IIT Delhi, with seed support
from the Department of Science and Technology, said that it also provides
solutions for intelligent vehicles, including keyless entry, preventive and
predictive maintenance, user-adaptive algorithms, remote diagnostics, fleet
management, and so on. The system can help in estimating the accurate
state of health and state of charge of the battery pack, help fleet operators
in their control and facilitate seamless communication.

2.6 Trusit Shah ; S Venkatesan“Authentication of IoT Device and IoT

Server Using Secure Vaults” 2021 17th IEEE International Conference
On Trust, Security And Privacy In Computing And
Communications, New York, NY, USA-May 2021

Internet of Things is a topic of much interest and, in last few years,

security of the IoT systems is a field of tremendous research activities.
Mutual authentication between IoT devices and IoT servers is an important
part of secure IoT systems. Single password-based authentication
mechanisms, which are widely used, are vulnerable to side-channel and
dictionary attacks. In this paper, we present a multi-key (or multi-
password) based mutual authentication mechanism. In our approach, the
shared secret between the IoT server and the IoT device is called secure
vault, which is a collection of equal sized keys. Initial contents of the
secure vault are shared between the server and the IoT device and contents

10
of the secure vault change after every successful communication session.
We have implemented this mechanism on an Arduino device to prove our
algorithm is feasible on IoT devices with memory and computational
power constraints.

2.7 Anindya Dey ; Kim Stuart ; Matthew E. Tolentino” Characterizing

the impact of topology on IoT stream processing” 2022 IEEE 4th
World Forum on Internet of Things (WF-IoT) Singapore, Singapore
07 May 2022

The Internet of Things (IoT) extends traditional cyber-physical

systems by linking sensor based edge devices to network accessible
services and resources. In most current IoT deployments, sensor data is
streamed from edge devices to servers for storage. Analytical pipelines are
then used to translate this raw sensor data into actionable information in
real-time. As additional IoT devices are deployed, the volume and rate of
data received on the server side can increase dramatically. This has a
possibility of offsetting the response latencies beyond acceptable limits for
IoT analytical systems. In this paper, we compare the impact of alternative
serverside stream processing topologies for ingesting and analyzing IoT
sensor data in real-time. We use real building sensor data with our real-
time IoT platform called Namatad. We have characterized and analyzed the
latency and QoS impact due to the different levels of granularity of the
ingestion and routing process by which we transmit data into the analytical
pipelines. Our results show that as IoT systems continue to scale in density,
server-side topology management for IoT data streams is critical for
latency-sensitive control and analysis applications.

2.8 André Tavares ; António Cardoso ; Pedro Gonçalves”

Animal monitoring based on IoT technologies” 2021 IoT Vertical and

11
Topical Summit on Agriculture - Tuscany (IOT Tuscany) Tuscany,
Italy May2021

The placement of grazing animals in vineyards requires additional

support to the animal husbandry activities. Such support must include the
monitoring and the conditioning of animal's location and behavior,
specially their feeding posture. With such a system, it is possible to allow
sheep to graze in cultivated areas (e.g. vineyards, orchards) without
endangering them. This paper proposes an animal behavior monitoring
platform, based on IoT technologies. It includes an IoT local network to
gather data from animals and a cloud platform, with processing and storage
capabilities, to autonomously shepherd ovine within vineyard areas. The
cloud platform also incorporates machine learning features, allowing the
extraction of relevant information from the data gathered by the IoT
network. Thus, besides the platform description, some results are presented
regarding the machine learning platform. Namely, this platform was
evaluated for detecting and defining conditions respecting animal's posture,
with preliminary promising results. Since several algorithms were tested,
this paper includes a comparison of those algorithms.

2.9 Md. Jakaria Islam Mozumder and Surojit Ghosh “IoT Based
Automatic Electricity Monitoring and Remote Load Control System
Using PIC18F4550” 2018 9th International Conference on Computing,
Communication and Networking Technologies (ICCCNT)- 10-12 July
2018, Bangalore, India

With the development in modern communication technology, every

physical device is now connecting with the internet. IoT is getting
emerging technology for connecting physical devices with the user. In this
paper we combined existing energy meter with the IoT technology. By

12
implementation of IoT in the case of meter reading for electricity can give
customer relief in using electrical energy. In this work a digital energy
meter is connected with cloud server via IoT device. It sends the amount of
consumed energy of connected customer to webserver. There is a feature
for disconnection in the case of unauthorized and unpaid consumption and
also have option for renew the connection by paying bill online. We tried
to build up a consumer and business friendly system.

CHAPTER-III

13
 Application of Artificial Intelligence in EV Charging System

The high penetration of electric vehicles (EVs) will burden the

existing power delivery infrastructure if their charging and discharging are
not adequately coordinated. Dynamic pricing is a special form of demand
response that can encourage EV owners to participate in scheduling
programs. Therefore, EV charging and discharging scheduling and its
dynamic pricing model are important fields of study. Many researchers
have focused on artificial intelligence-based EV charging demand
forecasting and scheduling models and suggested that artificial intelligence
techniques perform better than conventional optimization methods such as
linear, exponential, and multinomial logit models. However, only a few
research studies focused on EV discharging scheduling (i.e., vehicle-to-
grid, V2G) because the concept of EV discharging electricity back to the
power grid is relatively new and evolving. Therefore, a review of existing
EV charging and discharging-related studies is needed to understand the
research gaps and to make some improvements in future studies. This
paper reviews EV charging and discharging-related studies and classifies
them into forecasting, scheduling, and pricing mechanisms. The paper
determines the linkage between forecasting, scheduling, and pricing
mechanism and identifies the research gaps in EV discharging scheduling
and dynamic pricing models.
In recent years, the rollout of electric vehicles (EVs) has been
accelerated in many countries to combat the energy crisis and
environmental concerns such as high CO2 emissions and climate change.
Around two million EVs were sold in the first quarter of 2022, an increase
of 75% from the same period in 2021.
The number of EVs will continue to grow with governments’ incentives
and policies around the globe. On the one hand, the increasing and

14
uncoordinated EV charging will burden the existing power grid. On the
other hand, EVs’ batteries are mobile energy storage systems that can be
used to provide ancillary services for power grids, such as peak-shaving
and valley-filling, voltage and frequency regulations. In addition, EVs’
batteries can be used as flexible load and supply to maximize renewable
energy utilization, if EVs charging and discharging are properly
coordinated to closely match renewable generation profiles

3.1 EV Charging/Discharging and Battery Degradation

3.1.1 EV Charging and Discharging Techniques
There are four charging/discharging techniques, namely,
uncontrolled charging-discharging, controlled charging-discharging, smart
charging, and indirectly controlled charging. Table 2.1 summarizes the
benefits and challenges faced by each charging/discharging technique. In
addition, the schema of each charging technique is illustrated in Figure 1.1
The uncontrolled charging-discharging approach allows EVs to charge or
discharge at rated power as soon as it is plugged in until the battery’s
storage level equals the maximum state of charge or unplugged . Thus, this
charging method is inflexible for demand-side management DSM. The
uncontrolled charging technique is convenient for EV owners to make
charging decisions freely. However, uncontrolled EV charging might cause
a negative impact on local distribution networks, such as power loss,
demand-supply unbalance, shorter transformer lifespan, and harmonic
distortion.

15
Figure 3.1. Schema of V2G development phases and corresponding EV
charging techniques, (a). smart charging, (b). controlled charging, (c).
smart charging, (d). indirectly controlled charging. The solid black arrow
indicates the power flow, the dash red arrow indicates the charging control,
and the blue dash arrow indicates the information flow.

Table 3.1 . Summary of different EV charging and discharging techniques.

16
 The controlled charging-discharging method, also known as
unidirectional V2G, gives system operators more freedom to decide when
EVs will be charged and discharged. However, EV owners have to cede
control to the system operators or aggregators immediately after the EV is
plugged in under the controlled charging-discharging strategy.
The smart charging technique manages EVs’ charging and discharging
based on real-time energy demand, grid requirements, and grid quality .
However, it is not easy to encourage EV owners with different preferences
to participate in smart charging programs without incentives. Smart
charging allows EV owners to charge or discharge their EVs at a certain
time and rate to achieve predefined goals such as minimizing charging
costs or balancing demand and supply. However, smart charging strategies
are usually designed by system operators to maximize their profit. In
addition, EV owners do not clearly understand how smart charging can
benefit them monetarily.
On the other hand, an indirectly controlled charging mechanism uses
more straightforward price signals to incentivize EV owners to provide

17
ancillary services to power grids. Wang and Wang suggested using macro-
incentive policies such as variable electricity tariffs to attract more EV
owners to participate in the V2G system. Dynamic pricing schemes , such
as Time of Use (ToU) and Real-Time Pricing (RTP), have been commonly
used as a special form of power load demand response, which encourages
EV owners to choose charging or discharging time according to financial
incentives. Two empirical studies in Germany to get the public’s opinions
about the dynamic electricity pricing determined by the Time of Use (ToU)
tariff and household load profile. The results indicate that consumers are
open to dynamic pricing but like more straightforward programs with a
smaller price fluctuation range Latinopoulos et al. investigated EV drivers’
responses to the dynamic pricing of parking and charging services. The
results suggest that younger individuals are more likely to exhibit forward-
looking behaviors. Therefore, indirectly controlled charging with dynamic
electricity pricing strategies will influence EV owners’ charging and
discharging behaviors.

3.1.2 Battery Degradation and Charging Efficiency

The degradation of lithium-ion batteries occurs throughout their lives

due to several chemicals and mechanical processes that reduce the cyclable
lithium and other active materials. Battery degradation depends on many
factors, such as the charging and discharging rates, depth of discharge
(DOD), temperature, voltage, cycle number, and storage stage of charge,
which are complex to quantify. The degradation of the battery can be
classified into two types: calendar aging and cycle aging. Calendar aging
occurs during storage, whereas cycle aging happens during charging and
discharging. Battery temperature and state of charge (SOC) are the key
factors that influence calendar aging, whereas cycle aging is affected by

18
cycle number, charging rate, and DOD. Therefore, additional cycle
numbers due to the V2G service will accelerate battery degradation. It is
important to quantify the degradation due to V2G service. Thus, adequate
battery monitoring systems are needed to monitor the batteries’ SOC and
state of health (SOH) during the charging and discharging process. Meng et
al. performed a Lithium-Ion battery monitoring and observability analysis
with an extended equivalent circuit model. As a result, the necessary
observability conditions for battery capacity are clearly indicated, which
can be used to aid battery charging control design. Meng et al. [86]
proposed a Kalman filter and Gaussian process regression-based battery
end-of-life (EOL) prediction model. The simulation results show that the
proposed model provides a better battery EOL prediction than the particle
filter, a popular method for battery EOL prediction. The effectiveness of
Gaussian process regression on battery SOH estimation. A recurrent neural
networks(RNNs)-based SOC and SOH estimation model which does not
require battery modeling or knowledge of batter parameters. The
simulation results indicate that the recurrent neural networks-based
estimation model can make good SOC and SOH estimations based on
measured voltage, current, and ambient temperature. The measured data’s
accuracy is vital for empirical models’ performance.
More charging/discharging cycles occur in the V2G service than when
there is no V2G service; thus, battery degradation due to V2G services
might be more severe than without it. Assessed the impact of V2G on two
types of Lithium-ion batteries, nickel cobalt aluminum oxides (NCA) and
lithium ferro-phosphate (LFP). The simulation results indicate that the
effects of V2G on different batteries are different. For example, NCA is
more sensitive to cycle aging compared to LEP cells. In addition, high
SOC can increase battery capacity loss during storage. Also indicated that
the calendar aging process occurs faster for the battery stored at high SOC.

19
The authors found that battery overcharging and over-discharging
degradation happen when the battery operates outside its specified voltage
range. Although battery degradation is inevitable at the moment, it is
possible to minimize the process by avoiding overcharging/over-
discharging and encouraging charging/discharging batteries at an optimal
rate, under the optimal temperature range, and storing the battery at an
optimal SOC. Therefore, battery degradation estimation and modeling need
to be more accurate to support battery charging and discharging control
design.
Charging and discharging efficiency is also one of the primary
concerns of the V2G program. Apostolaki-Iosifidou et al. conducted
experimental measurements to determine power loss during EV charging
and discharging. The measurement results indicate that most power losses
occur in the power electronics used for AC-DC conversion. Usually, the
highest efficiency of the power electronics occurs at the top region of their
rated power . In addition, the efficiency of the power electronics is higher
during charging than discharging. This is due to the higher voltage during
charging than discharging at a given power. The higher charging voltage
results in a lower charging current, thus lowering internal resistance
losses . Therefore, the trade-off between inevitable battery degradation and
power loss during battery discharging and the benefit of V2G needs to be
farther investigated. More research on battery design and management is
required to minimize battery degradation during charging/discharging.

3. 2 Artificial Intelligence-Based Forecasting Model

The relationship between forecasting, scheduling, and dynamic
pricing is shown in Figure 3.2. As can be seen, there are three critical
components of EV charging/discharging that are interlinked. These

20
components are EV charging/discharging-related forecasting, scheduling,
and dynamic pricing. Accurate forecasting results provide insightful
information on system conditions to scheduling models, which provide
optimal charging/discharging control and pricing signals which are then
used to update the forecasting model to enhance prediction accuracy. Thus,
accurate forecasting results are crucial for making optimal EV
charging/discharging strategies. Commonly used artificial intelligence-
based forecasting models related to EV charging/discharging are discussed
in this section.

Figure 3.2. Relationship between EV charging and discharging scheduling,

forecasting, and dynamic pricing.

21
3.3. Supervised Learning Methods

EV charging-related forecasting results are generally used as inputs to

the optimization models to enhance EV charging scheduling performance.
Many different types of machine learning methods can be used for both
regression and classification problems. Commonly used machine learning
methods for forecasting tasks are linear regression (LR), decision tree (DT)
, random forest (RF) , support vector machine (SVM) , k-nearest neighbor
(KNN), artificial neural networks (ANNs) , convolutional neural
network(CNN), deep convolutional neural network (DCNN), recurrent
neural network (RNN) and its two gating mechanisms, gated recurrent
units (GRUs) and long short-term memory (LSTM). LR is suitable for
linear models. Although LR is easy to implement, the performance of LR is
largely affected by overfitting issues and outliers . EV charging-related
forecasting tasks are nonlinear. Therefore, LR has barely been used to
handle EV charging-related problems. In contrast, DT is able to separate a
complex decision into multiple straightforward decisions. However, a
single DT cannot always guarantee a good prediction. Moreover, DT is
often prone to overfitting issues. RF is an ensemble of DTs; thus, it is more
accurate than DT and can overcome overfitting by aggregating multiple
DTs . RF is proposed in to forecast EV charging load. The results of the
simulations indicate the effectiveness of RF on EV charging load
prediction. Although SVM and KNN are suitable for solving regression
problems, they are generally used for classification tasks. Erol-Kantarci
and Mouftah used KNN to predict electricity prices to reduce PHEVs’
charging costs and CO2 emissions. The simulation results show that the
prediction-based charging scheme reduces the PHEVs’ operating costs and
CO2 emissions. SVM is used in to forecast EV charging demand with a

22
3.69% mean absolute percentage error (MAPE), which is lower than the
8.99% MAPE of the Monte Carlo technique.

3.4. Gated Recurrent Units (GRUs)

Deep neural networks, such as RNN, GRU, LSTM, and CNN, are very
efficient and popular nowadays due to the availability of a large number of
datasets and strong computational power. It has been proven that RNN
with gating units (GRU and LSTM) performs better than without them .
The Gated recurrent units (GRUs) gating mechanism of recurrent neural
networks was first introduced. GRUs is similar to LSTM, which can also
be used to solve the vanishing and exploding gradient problems. In
addition, the structure of GRU is simpler than LSTM. Moreover, GRU
usually performs better than LSTM in solving problems with a low sample
size. Therefore, GRU usually requires less processing power and training
time than LSTM. As a result, GRU is also popular for solving problems
with long sequence samples, such as spot electricity price prediction, load
demand, and PV power production. A GRU to forecast spot electricity
prices used to plan travel routes and charging schemes. The results of
simulations indicate that the route planning algorithm can effectively and
accurately provide optimal charging routes for EVs users. The prediction
of the future trend of load demand and PV power production is made by
GRU in to reduce the operating costs of EV charging stations. Compared
the EV charging load forecasting performance of four popular deep
learning models: ANN, GRU, LTSM, and RNN. The simulation results
indicate that GRU has the best performance, followed by RNN, LTSM, and
ANN. However, their results should only be used as guidance when
selecting a model for forecasting tasks because the generalization of these
models was not tested.

23
3.5. Long Short-Term Memory (LSTM)
Long short-term memory (LSTM) is another popular gating
mechanism of RNN. It was first introduced. GRU and LSTM can solve
complex, long-sequence problems better than recurrent neural networks
(RNNs). Additionally, LSTM usually performs better for solving high-
complexity sequences than GRU. Therefore, LSTM has been generally
used to solve problems with long and high-complexity sequence samples.
Kriekinge et al., proposed an LSTM model to predict load demand and
one day ahead of EV charging demand. Schedulers then use the forecasted
load demand to plan EVs’ charging and discharging. LSTM to predict
future charging prices based on the historical charging price. LSTM
networks and deep LSTM have been applied to predict V2G capacity by
compared the V2G capacity forecasting performance of LSTM with the
Nonlinear Autoregressive Neural Network (NAR). The simulation results
indicate that NAR performs slightly better than LSTM. However, both
models can use historical knowledge to correct learned aggregated
available capacity deviations for V2G service.

3.6. Hybrid and Ensemble

Different forecasting mechanisms have various advantages and
disadvantages. The forecasting performances should be able to improve if
the advantages of different mechanisms are combined to form hybrid
models. A hybrid of CNN and LSTM-based models to predict the next 24 h
of aggregated available SOC of 48 vehicles for V2G services based on the
previous 24 h of data. Further enhanced by continually refining the
prediction model based on the latest observed behavior . A load demand
and renewable energy output prediction model that combines CNN with a
deep belief network (DBN) to form the CNN-DBN prediction model. The
forecasted results are then used to schedule EVs’ charging to minimize the

24
operating cost of the distribution network. Artificial Intelligence-based
hybrid model that consists of K-means clustering, KNN classification, and
LSTM prediction to predict EV driver charging behavior. A CNN-based
ensemble model to forecast traffic flow and EV load demand. The
forecasted load demand can be used to make electricity trading decisions.
Artificial intelligence-based forecasting models are usually supervised
learning-based models which use labeled data to train the models for
predictions. The forecasting models are used to predict electricity price, EV
load demand, driving pattern, and availability of state of charge, which can
then provide EV charging and discharging schedules and pricing.
However, the performance of these charging scheduling models is highly
dependent on the accuracy of the prediction models. Uncertainty is an
inherent property of forecasting models. The stochastic and unpredictable
EV charging, discharging, and driving behaviors make forecasting harder.
Therefore, forecasting results alone will not result in optimal charging
scheduling strategies. Other than the suggested hybrid and ensemble
techniques, online-based prediction models that take the latest available
information to update the prediction models might reduce the forecasting
uncertainty.
Moreover, probabilistic learning algorithms, such as Gaussian
processes (GP) can provide prediction with an uncertainty interval that
could also be applied to EV charging/discharging-related studies.

3.7 Artificial Intelligence-Based Scheduling

Conventional numerical optimization methods, such as convex
optimization and linear programming, need to make some physically
unknown assumptions. The investigation results of indicate that most
researchers prefer artificial intelligence models to probabilistic models
because artificial intelligence is suitable for complex nonlinear problems

25
like forecasting EV charging demand and optimizing charging schedules.
Moreover, artificial intelligence models such as neural networks and
reinforcement learning approaches can obtain nonlinear relationships from
historical data and learn via interacting with the environment, respectively.
Therefore, they usually do not require expert knowledge of a complex
system to build a model from system developers due to the ability of
artificial intelligence to learn from the existing dataset. Furthermore,
complex problems like demand forecasting and charging scheduling
optimization are stochastic, requiring the models to be continuously
updated. The online setup of artificial intelligence allows models to learn
the latest available dataset to improve model performance. The following
are some of the artificial intelligence-based scheduling algorithms.

3.8 Heuristic Algorithms

Heuristic algorithms such as Genetic Algorithm (GA) , Particle Swarm
Optimization (PSO), Differential Evaluation (DE) [, Artificial Bee Colony
(ABC) , to name only a few, are very popular for solving optimization
problems due to their easy implementation and fast training speed. Among
all the heuristic algorithms, GA and PSO are the most commonly used ones
for EV charging and discharging scheduling problems. A GA was
employed by to optimize the battery charging and discharging schedule.
The simulation results show that the proposed model can provide a demand
response to adjust the main transformer load. Farahani proposed a PSO-
based EV charging/discharging scheduling to minimize the voltage
unbalance factor of low-voltage distribution networks. The simulation
results indicate that the proposed model is able to reduce the voltage
unbalance factor. PSO-based EV charging scheduling model is also
proposed in to reduce power loss and peak valley difference. Although GA
and PSO-based optimization models mentioned in perform well, the

26
performance comparison of these models is lacking. Tested the
performance of four different heuristic algorithms on EV
charging/discharging scheduling. The simulation results show that GA can
provide the lowest EV station operating cost and the most convenience for
EV owners, followed by PSO, DE, and ABC. Although heuristic
algorithms are easy to implement and can provide a fast solution, they do
not always provide optimal solutions because they might be trapped in
local optimal and provide unstable performances. In addition, the
parameters of these algorithms can largely impact their performance. Thus,
the ranking of these algorithms should only be used as guidance.

3.9 Fuzzy Logic

A fuzzy logic-based controller has been implemented in to manage and
schedule EVs’ charging/discharging intelligently. Authors in used fuzzy
logic-based controllers to maintain a balance between system operators and
EV owners. The simulation results indicate that the fuzzy logic controller is
able to improve the power system efficiency and increase profit for
aggregators. The control action of is based on EVs’ initial and target state
of charge and available charging duration. The simulation results indicate
that the controller can consider EV owners’ and power providers’
preferences and provide economic benefits for both EV owners and power
providers.

3.10 Q-Learning and Deep Reinforcement Learning (DRL)

Many authors have applied reinforcement learning (RL) algorithms to
schedule EVs’ charging and discharging. RL-based EV charging
scheduling is usually present in the Markov decision process (MDP) A
finite MDP can be solved by dynamic programming (DP), which assumes
perfect knowledge of the environment and requires high computation

27
expense. A DP-based model to optimally control PHEVs’ charging time
and power rate based on the forecasted electricity prices in deregulated
electricity markets. The simulation results indicate that the model can
reduce daily electricity costs substantially. Markov chain model to predict
the probability of EVs’ driving patterns. Then a stochastic DP model is
applied to the EVs’ driving pattern and electricity price to provide the
optimal charging policy. The simulation results show that the optimal
charging policy can reduce daily energy costs. However, the environment
of EV charging scheduling tasks is not usually known. DP optimizes its
policy based on a known environment, whereas Q-learning, a model-free
RL, optimizes its policy via interacting with its environment. Watkins
introduced Q-learning in 1989 , which is popular for scheduling problems
with a limited number of state and action spaces.
Artificial neural networks (ANN) forecasting model to predict the next
day’s electricity price. The forecasted results are then used to train the Q-
learning-based charging scheduling model. A Q-learning-based energy
management system that considers the ToU tariff, home appliances, and
energy storage system with charging/discharging functionality. The
simulation results show that the proposed model provides a 14% electricity
bill reduction compared to MILP.
The charging/discharging functionality of the energy storage systems
is similar to that of EVs’ charging and discharging. Therefore, the results
should be similar if the proposed model in is applied for EV charging and
discharging. A Q-learning model to give EVs real-time charging and
discharging schedules. The simulation results indicate that the proposed
model can achieve a cost saving of approximately 68% compared to the
uncontrolled one. However, one of the limitations of Q-learning algorithms
is the curse of dimensionality. Thus, deep reinforcement learning which

28
combines deep neural networks with reinforcement learning, has been
widely used to overcome the issue of the curse of dimensionality.
Deep-Q networks (DQN) combine deep neural networks with Q-
learning to make RL more suitable for high-dimensional and complex
environments DQN has been used in to reduce charging costs and increase
power grid reliability. A DQN-based battery-swapping scheduling strategy
to provide fast frequency regulation services. The simulation results
indicate that the proposed model can maximize the battery swapping
station operators’ revenue by autonomously scheduling the hourly
regulation capacity in real-time. DQN and Dyna Q learning to allow the
model to learn from both real-time experiences and simulated experiences,
which speeds up training. The proposed algorithm can reduce the long-
term charging cost while avoiding battery depletion during trips. Double-
DQN was introduced in to reduce the overestimation of action values of
DQN, and it is applied in to control EVs’ charging/discharging based on
the hourly electricity price. The simulation results indicate that the Double-
DQN algorithm reduces the correlation of the action values with the target
and provides better profit for EV owners than other state-of-the-art models
such as RNN, CDNN, and LSTM. However, the training time of DQN for
problems with complex and large state spaces is usually long due to its
value iteration nature. Asynchronous Advantage Actor Critic (A3C), which
requires less training time than DQN, was introduced in 2016. Although
A3C has not been applied to EV charging and discharging-related studies
in the reviewed literature, it is a good algorithm for a complex problem
with many states like EV charging and discharging and should be used in
the future.
In addition, both Q-learning and DQN are only suitable for discrete
action spaces, significantly reducing the effectiveness of the EV charging
control algorithm due to the limitation of the action space exploration. The

29
deep deterministic policy gradient (DDPG) is suitable for tasks with
continuous state and action spaces. It has been proposed to maximize
system operators’ financial benefit or reduce the charging cost of EV
owners. The simulation results show that the higher pricing frequency can
better reflect power system demand and supply situations and shift EV
charging load. The simulation results is suggest that a DDPG-based EV
charging strategy can strictly guarantee voltage security by scheduling EV
charging and discharging at suitable time periods.DDPG to solve the
voltage control strategy problem to mitigate voltage fluctuation caused by
stochastic EV and load demand. A prioritized deep deterministic policy
gradient (PDDPG), a combination of DDPG and prioritized experience
replay, to optimize EV owners’ and aggregators’ profits. PDDPG can solve
the problem in multi-dimensional continuous state and action spaces,
which is preferable for practical application and requires lower
computational resources than DDPG with uniform sampling. The
simulation results of show that PDDOG can provide 31%, 13%, and 5%
higher profit than Q-learning, DQN, and DDPG, respectively. Another off-
policy algorithm, soft-actor-critic (SAC) is used to balance charging costs
and drivers’ anxiety. The maximum entropy framework of SAC makes the
proposed model more sample efficient and robust. SAC model to provide
dynamic EV charging and discharging pricing to maximize the profits of
multiple EVCSs.

30
 CHAPTER 4

SENSORS AND INTERFACING CIRCUITS WITH ARDUINO UNO

4.1 INTRODUCTION
Sensors are mainly used to detect the status of the physical quantity.
Here we are using sensors for measuring irrigation area temperature,
Humidity, Soil moisture and flow of water.DHT11 temperature cum
humidity sensor is used to measure irrigation field temperature and
humidity,Soil moisture sensors are used to measure soil moisture and
Water flow sensor is used to measure water flow in motor output.
Electromagnetic relays are used to interface Motor and solenoid valves.

4.2 DHT11 Sensor Interface with Arduino

DHT11 is a Humidity and Temperature Sensor, which generates
calibrated digital output. DHT11 can be interface with any microcontroller
like Arduino, Raspberry Pi, etc. and get instantaneous results. DHT11 is a
low cost humidity and temperature sensor which provides high reliability
and long term stability.
In this project, we will build a small circuit to interface Arduino with
DHT11 Temperature and Humidity Sensor. One of the main applications
of connecting DTH11 sensor with Arduino is weather monitoring in
agriculture field

31
 Fig 4.1 Photo Image and Pin Configuration of DHT11.

Fig 4.2 Photo Image DHT11 interface with Arduino.

4.3 LCD INTERFACE

A Liquid Crystal Display commonly abbreviated as LCD is basically

a display unit built using Liquid Crystal technology. When we build real
life/real world electronics based projects, we need a medium/device to
display output values and messages. The most basic form of electronic
display available is 7 Segment display – which has its own limitations. The
next best available option is Liquid Crystal Displays which comes in
different size specifications. Out of all available LCD modules in market,
the most commonly used one is 16×2 LCD Module which can display 32
ASCII characters in 2 lines (16 characters in 1 line). Other commonly used
LCD displays are 20×4 Character LCD, Nokia 5110 LCD module, 128×64
Graphical LCD Display and 2.4 inch TFT Touch screen LCD display.

In this article, we are going to learn how to interface lcd to arduino with 2
examples – one being interfacing a 16×2 LCD module to Arduino and the
other being interfacing a 20×4 LCD module to Arduino.

32
4.4 Interfacing 16×2 LCD to Arduino uno

LCD modules form a very important part in many arduino based

embedded system designs. So the knowledge on interfacing LCD module
to arduino is very essential in designing embedded systems. This section of
the article is about interfacing an Arduino to 16×2 LCD. JHD162A is the
LCD module used here. JHD162A is a 16×2 LCD module based on the
HD44780 driver from Hitachi. The JHD162A has 16 pins and can be
operated in 4-bit mode (using only 4 data lines) or 8-bit mode (using all 8
data lines). Here we are using the LCD module in 4-bit mode. First, I will
show you how to display a plain text messages on the LCD module using
arduino and then I have designed a useful project using LCD and arduino
– a digital thermometer. Before going in to the details of the project, let’s
have a look at the JHD162A LCD module.

16×2 LCD Module Pin Out Diagram

The JHD162A lcd module has 16 pins and can be operated in 4-bit
mode or 8-bit mode. Here we are using the LCD module in 4-bit mode.
Before going in to the details of the project, let’s have a look at the
JHD162A LCD module.The schematic of a JHD162A LCD pin diagram is
given below.

Fig 4.3 16×2 LCD Module Pin Out Diagram

The name and functions of each pin of the 16×2 LCD module is
given below.

33
Pin1(Vss):Ground pin of the LCD module.

Pin2(Vcc): Power to LCD module (+5V supply is given to this pin)

Pin3(VEE):Contrast adjustment pin. This is done by connecting the ends of

a 10K potentimeter to +5V and ground and then connecting the slider pin
to the VEE pin. The voltage at the VEE pin defines the contrast. The
normal setting is between 0.4 and 0.9V.

Pin4(RS):Register select pin.The JHD162A has two registers namely

command register and data register. Logic HIGH at RS pin selects data
register and logic LOW at RS pin selects command register. If we make the
RS pin HIGH and feed an input to the data lines (DB0 to DB7), this input
will be treated as data to display on LCD screen. If we make the RS pin
LOW and feed an input to the data lines, then this will be treated as a
command ( a command to be written to LCD controller – like positioning
cursor or clear screen or scroll).

Pin5(R/W): Read/Write modes. This pin is used for selecting between read
and write modes. Logic HIGH at this pin activates read mode and logic
LOW at this pin activates write mode.

Pin6(E): This pin is meant for enabling the LCD module. A HIGH to LOW
signal at this pin will enable the module.

Pin7(DB0) to Pin14(DB7): These are data pins. The commands and data
are fed to the LCD module though these pins.

Pin15(LED+): Anode of the back light LED. When operated on 5V, a 560
ohm resistor should be connected in series to this pin. In arduino based
projects the back light LED can be powered from the 3.3V source on the
arduino board.

34
Pin16(LED-): Cathode of the back light LED.

For knowing more about LCD module JHD162A and its pin functions,
read this article: Interfacing 16×2 LCD and 8051 microcontroller. The
circuit diagram of interfacing LCD to arduino for displaying a text message
is shown below.

Fig 4.4 Circuit diagram – Arduino to 16×2 LCD Module

RS pin of the LCD module is connected to digital pin 12 of the

arduino. R/W pin of the LCD is grounded. Enable pin of the LCD module
is connected to digital pin 11 of the arduino. In this project, the LCD
module and arduino are interfaced in the 4-bit mode. This means only four
of the digital input lines( DB4 to DB7) of the LCD are used. This method
is very simple, requires less connections and you can almost utilize the full
potential of the LCD module. Digital lines DB4, DB5, DB6 and DB7 are
interfaced to digital pins 5, 4, 3 and 2 of the Arduino. The 10K
potentiometer is used for adjusting the contrast of the display. 560 ohm
resistor R1 limits the current through the back light LED. The arduino can
be powered through the external power jack provided on the board. +5V
required in some other parts of the circuit can be tapped from the 5V

35
source on the arduino board. The arduino can be also powered from the PC
through the USB port. The full program for interfacing LCD to arduino is
shown below.

4.5 RELAY AND BUZZER INTERFACE CIRCUIT

A relay is an electromagnetic switch used to switch High Voltage or

Current using low power circuits. For example, we can use it for
controlling home appliances with a normal low voltage electronic circuit.
Electromagnetic relays uses an electromagnet to operate a switching
mechanism mechanically. It also provides isolation between low power
circuit and high power circuits.

Fig 4.5 Internal Architecture of Electromagnetic Relay

The construction and working of a relay can be understood from the

above diagram. The main part of a relay is the electromagnet. The
electromagnet is made by a coil of wire wrapped around a soft iron core
which provides low reluctance path for magnetic flux. It also consists of a
movable iron armature and one or more set of contacts. These are held in a
position by a spring as shown in the above diagram.
Normally a SPDT relay has 5 terminals. Two them are used
to energies the electromagnet and other three are COM, NO, NC. COM

36
stands for Common, NO stands for Normally Open and NC stands for
Normally Closed. When the electromagnet is not energized, the armature
will be connected to NC contact. Thus COM and NC will be connected.
When the electromagnet is energized, the electromagnet attracts the iron
armature and it will be connected to NO contact. Thus COM and NO will
be connected.

Fig4.6 Photo Image of Electromagnetic Relay

37
 CHAPTER V

HARDWARE DESCRIPTION

5.1 MAIN CIRCUIT DIAGRAM

Fig 5.1 Main circuit diagram

38
 CHAPTER-VI

CONCLUSION

Today, EV is still a huge market. However, as old barriers to

adoption and new challenges for EVs emerge, companies are turning to
autonomous solutions for business and strategic imperatives. From an
economic point of view, autonomous fleets can reduce the total cost of
ownership by 53 %. As autonomy becomes more mature, cars will not only
be able to drive themselves better but also predict the probability of things
going wrong in the future allowing fleet operators to inspect cars
proactively before they go out on their next shift. In short, companies and
industries around the world are already working on ways to help EV
technology meet its full potential.Overall, the combination of IoT and AI
technology holds great promise for electric vehicle adoption. It can
accelerate EV deployments and enhance the customer experience.
This projects reviews three crucial aspects of EV charging and
discharging: forecasting, scheduling, and dynamic pricing. The
interconnected relationship between forecasting, scheduling, and dynamic
pricing is identified. Scheduling models’ performance mainly depends on
the accuracy of forecasting results and pricing strategies. On the other
hand, forecasting accuracy and scheduling performance largely influence
the effectiveness of dynamic pricing strategies in reflecting real-time
power system conditions.
Most forecasting models mentioned in this paper are supervised,
learning-based models. Among them, LSTM and GRU are the most
popular methods due to their ability to handle nonlinear and long-term
dependency. However, uncertainty is one of the inherent properties of
forecasting models. Therefore, the performance of forecasting models
needs to continue improving. Besides hybrid and ensemble techniques,

39
using the latest available data to update forecasting models and adding
uncertainty intervals are other options to assist decision-making.
Reinforcement learning-based optimization models that can take many
variables as state spaces have been applied by many researchers to make
optimal EV charging and discharging decisions based on the forecasted
results, including charging and discharging prices. DQN, DDPG, and SAC
are some of the most popular reinforcement learning models. Each of them
has its advantages and disadvantages. DQN can overcome the curse of
dimensionality faced by conventional Q-learning. However, overestimation
of action values and long training time requirements are common issues
faced by these methods. Double-DQN and A3C can solve action value
overestimation and reduce training time, respectively. Improving
reinforcement learning performance is also a key field of research.
Scheduling models cannot make effective charging/discharging decisions
to optimize power grids if the information they use to make decisions
cannot accurately reflect the power grid’s real-time conditions. Therefore,
both forecasting results and dynamic pricing signals that can reflect the
real-time conditions of the power grid are important.

40
 REFERENCES
1. H. Khayyam, B. Javadi, M. Jalili and R.N Jazar, "Artificial Intelligence
and Internet of Things for Autonomous Vehicles", Nonlinear Approaches
in Engineering Applications, 2019.
2. Z. Wang, M. Ogbodo, H. Huang, C. Qiu, M. Hisada and A. B. Abdallah,
"AEBIS: AI-Enabled Blockchain-Based Electric Vehicle Integration
System for Power Management in Smart Grid Platform", IEEE Access,
vol. 8, pp. 226409-226421, 2020.
3. Shabana Urooj, Fadwa Alrowais, Yuvaraja Teekaraman, Hariprasath
Manoharan and Ramya Kuppusamy, "IoT Based Electric Vehicle
Application Using Boosting Algorithm for Smart Cities", Energies, vol.
1072, pp. 14, 2021.
4. Chitra, P. Sanjeevikumar, Jens Bo Holm-Nielsen and S. Himavathi, "IoT-
Based Battery Management System for Hybrid Electric
Vehicle", Artificial Intelligent Techniques for Electric and Hybrid
Electric Vehicles, 2020.
5. Surendar and P. Pradeepa, "An IOT-based Battery Surveillance System
For E-Vehicles", 2021 Fifth International Conference on I-SMAC, pp.
119-124, 2021.
6. Heba Yahia Youssef, Latifa Alkhaja, Hajar Almazrouei, Ali Bou Nassif,
Chaouki Ghenai and Mohammad Al-Shabi, "A machine learning
approach for state-of-charge estimation of Li-ion batteries", Artificial
Intelligence and Machine Learning for MultiDomain Operations
Applications IV, pp. 1211329, 2022.
7. Moin Ahmed, Yun Zheng, Anna Amine, Hamed Fathiannasab and
Zhongwei Chen, "The role of artificial intelligence in the mass adoption
of electric vehicles", Joule, vol. 5.9, pp. 2296-2322, 2021.

41
8. Phillip Kollmeyer, Carlos Vidal, Mina Naguib and Michael Skells, "LG
18650HG2 Li-ion Battery Data and Example Deep Neural Network xEV
SOC Estimator Script", Mendeley Data V2, 2020.
9. Muhammad Nizam, Hari Maghfiroh, Rizal Abdulrozaq Rosadi and
Kirana DU Kusumaputri, "Battery management system design (BMS) for
lithium-ion batteries", AIP Conference Proceedings, vol. 2217.1, pp.
030157, 2020.
10.Yong Feng, Zhenwei Cao, Weixiang Shen, Xinghuo Yu, Han Fengling,
Rita Chen, et al., "Intelligent battery management for electric and hybrid
electric vehicles: A survey", pp. 1436-1441, 2013.
11.R Ananthraj and Arnab Ghosh, "Battery Management System in Electric
Vehicle", 4th Biennial International Conference on Nascent
Technologies in Engineering (ICNTE), pp. 1-6, 2021.

42