Intelligent and Soft Computing Systems for Green Energy
Description
Written and edited by some of the world's top experts in the field, this exciting new volume provides state-of-the-art research and the latest technological breakthroughs in next-generation computing systems for the energy sector, striving to bring the science toward sustainability.
Real-world problems need intelligent solutions. Across many industries and fields, intelligent and soft computing systems, using such developing technologies as artificial intelligence and Internet of Things, are quickly becoming important tools for scientists, engineers, and other professionals for solving everyday problems in practical situations.
This book aims to bring together the research that has been carried out in the field of intelligent and soft computing systems. Intelligent and soft computing systems involves expertise from various domains of research, such as electrical engineering, computer engineering, and mechanical engineering. This book will serve as a point of convergence wherein all these domains come together.
The various chapters are configured to address the challenges faced in intelligent and soft computing systems from various fields and possible solutions. The outcome of this book can serve as a potential resource for industry professionals and researchers working in the domain of intelligent and soft computing systems.
To list a few soft computing techniques, neural-based load forecasting, IoT-enabled smart grids, and blockchain technology for energy trading. Whether for the veteran engineer or the student learning the latest breakthroughs, this exciting new volume is a must-have for any library.
More details
Other editions
Additional editions
Persons
A. Chitra is an associate professor in the School of Electrical Engineering, at Vellore Institute of Technology, Vellore, India. She has published many papers in reputed journals and conferences and is a Board of Studies member at Pondicherry Engineering College, where she received a Gold Medal while studying for her MTech and also where she earned her PhD.
V. Indragandhi, PhD, is an associate professor in the School of Electrical Engineering, VIT, Vellore, Tamilnadu. She received her PhD from Anna University in Chennai, India. She has over 12 years of experience in the area of power electronics and renewable energy systems and has authored over 100 research articles in leading peer-reviewed international journals. She has filed three patents and has one book to her credit. She has also received the best researcher award from NFED, Coimbatore and from VIT.
W. Razia Sultana, PhD, is an associate professor in the School of Electrical Engineering, at the Vellore Institute of Technology University, Vellore, Tamil Nadu, India, where she also received her PhD.
Content
Preface xvii
1 Placement and Sizing of Distributed Generator and Capacitor in a Radial Distribution System Considering Load Growth 1
G. Manikanta, N. Kirn Kumar, Ashish Mani and V. Indragandhi
1.1 Introduction 2
1.2 Problem Formulation 3
1.3 Algorithm 5
1.4 Results & Discussions 9
1.5 Discussion 20
1.6 Conclusions 21
References 21
2 Security Issues and Challenges for the IoT-Based Smart Grid 25
Prathiga, Kavya K., Nanthitha N., Nithishkumar K., Ritika T. and Vishal T.
2.1 Introduction 25
2.2 Usage of IoT in the Smart Grid Context 27
2.3 Advantages of IoT-Based Smart Grid 29
2.4 Cybersecurity Challenges 30
2.4.1 Review of Recent Attacks 32
2.4.1.1 Tram Hack Lodz, Poland 32
2.4.1.2 Texas Power Company Hack 32
2.4.1.3 Stuxnet Attack on Iranian Nuclear Power Facility 32
2.4.1.4 Houston, Texas, Water Distribution System Attack 33
2.4.1.5 Bowman Avenue Dam Cyberattack 33
2.5 Other Major Challenges Hindering Growth of IoT Network 33
2.5.1 Standardization Protocols 33
2.5.2 Cognitive Capability 34
2.5.3 Power 34
2.5.4 Consumer Illiteracy 35
2.5.5 Weak Regulations 35
2.5.6 Fear of Reputational Damage 36
2.6 Future Prospects 36
2.7 Conclusion 38
References 39
3 Electrical Load Forecasting Using Bayesian Regularization Algorithm in Matlab and Finding Optimal Solution via Renewable Source 41
Chinmay Singh, Yashwant Sawle, Navneet Kumar, Utkarsh Jha and Arunkumar L.
3.1 Introduction 42
3.2 Algorithm 43
3.2.1 Levenberg-Marquardt Algorithm 43
3.2.2 Bayesian Regularization 45
3.2.2.1 Comparison of Bayesian Models 46
3.2.2.2 Bayesian Ways to Neural Network Modeling 46
3.2.3 Scaled Conjugate Gradient Algorithm 47
3.2.3.1 Steps of Algorithm 47
3.2.4 Gradient Descent 48
3.2.5 Conjugate Gradient 48
3.3 Methodology and Modelling 49
3.4 Results and Discussion 52
3.5 Conclusion 55
References 55
4 Theft Detection Sensing by IoT in Smart Grid 59
N. Siva Mallikarjuna Rao, M. Ramu and Lekha Varisa
4.1 Introduction 60
4.1.1 Power Theft Identification 60
4.1.2 Basic Structure of Smart Grid 60
4.2 Problem Identification 62
4.2.1 Power Theft Methods 62
4.3 Methodology for Implementation of IoT to Different Theft Mechanisms in Smart Grid 64
4.4 Conclusion 66
4.5 Future Work 67
References 67
5 Energy Metering and Billing Systems Using Arduino 69
M. Ramu, Lekha Varisa and N. Siva Mallikarjuna Rao
5.1 Introduction 69
5.2 Smart Meters and Billing Systems 72
5.2.1 Arduino Mega 72
5.2.2 Lcd 72
5.2.3 Proteus Software 73
5.3 Working 73
5.4 Applications 74
5.5 Time of Use 74
5.6 Observations 74
5.7 Equations 75
5.8 Results 75
5.9 Adoption in India 76
5.10 Excess Generation of Electricity 76
5.11 Commercial Use & Home Energy Monitoring 76
5.12 Conclusion 77
References 77
6 Smart Meter Vulnerability Assessment Under Cyberattack Events - An Attempt to Safeguard 79
Kunal Kumar and R. Raja Singh
6.1 Introduction 80
6.2 Advanced Metering Infrastructure Architecture 82
6.2.1 Smart Meter Architecture and Design 83
6.2.2 AMI Communication Network 83
6.2.3 Home Area Network 84
6.2.4 Data Concentrator 84
6.3 Possible Attacks on AMI 84
6.3.1 Manual Attacks 84
6.3.2 Cyberattacks 84
6.3.3 Threats and Countermeasures of Attacks on Smart Meter 87
6.4 RSA Attack Detection Model 87
6.4.1 RSA Keys Creation 89
6.5 Hash Code for Data Integrity 89
6.6 Results and Discussion 90
6.6.1 Attack Detection System 90
6.6.2 Python Implementation 91
6.7 Conclusion 93
References 94
7 Power Quality Improvement for Grid-Connected Hybrid Wind-Solar Energy System Using a Three-Phase Three-Wire Grid-Interfacing Compensator 97
Boopathi R. and Dr. Indragandhi V.
7.1 Introduction 98
7.2 Proposed Current Control System 100
7.3 Simulation Analysis and Discussion 103
7.4 Conclusion 107
References 108
8 Energy Trading in Virtual Power Plant Enabled Communities Using Double Auction Technique and Blockchain Technology 111
Radhika Yadav, Balla Manoj Kumar, Saurav Baid and Padma Priya R.
8.1 Introduction 112
8.2 Related Work 113
8.3 Proposed Methodology 114
8.3.1 System Model 115
8.3.2 Problem Formulation 116
8.3.2.1 Objective 1 (Optimum Reimbursements for both the Traders) 116
8.3.2.2 Objective 2 (Shortest Line Routing System) 116
8.3.2.3 Utility Function (Maximum Social Welfare) 116
8.3.3 Our Approach 117
8.3.3.1 Double Auction 117
8.3.3.2 Shortest Line Route Detection 119
8.3.3.3 Blockchain 119
8.3.3.4 ElGamal Cryptography 120
8.4 Performance Evaluation 121
8.4.1 Evaluation Methodology 121
8.4.2 Evaluation Results 122
8.5 Conclusion 123
References 124
9 Sales Demand Forecasting for Retail Marketing Using XGBoost Algorithm 127
M. Kavitha, R. Srinivasan, R. Kavitha and M. Suganthy
9.1 Introduction 128
9.2 Related Work 129
9.3 Methodology 130
9.3.1 XGBoost Algorithm 130
9.3.2 Architecture 131
9.4 Experimental Results 131
9.4.1 Exploratory Data Analysis 132
9.4.1.1 Empirical Cumulative Distribution Function (ECDF) 132
9.4.1.2 Exploring the Dataset and Making Visualizations between Months and Sales 133
9.4.1.3 Correlation between each Feature or Attribute 134
9.4.1.4 Time Series Analysis 134
9.4.2 Model Prediction 137
9.5 Conclusion 138
References 139
10 Region-Based Convolutional Neural Networks for Selective Search 141
R. Kavitha, Srinivasan R, P. Subha and M. Kavitha
10.1 Introduction 142
10.2 Literature Review 143
10.3 Existing Method 145
10.4 Proposed Methodology 145
10.5 Implementation and Results 147
10.6 Conclusion 149
References 150
11 Design and Development of Mobility System for Double Amputees 151
Dr. Saravanan T S, Dr. Sagayaraj R, Dr. Sivaraman P R, Sivamani D, Jaiganesh R and Ragupathy P
11.1 Introduction 152
11.2 Block Diagram 152
11.3 Working Methodology 153
11.4 Design Calculation 154
11.5 Hardware Implementation 156
11.6 Conclusion 159
References 159
12 A Review: Precision Vehicle Control Using Internet of Things 163
R. Srinivasan, Kavitha R, Kavitha M and Sridhar K
12.1 Introduction 163
12.2 Related Works 164
12.3 Proposed Work 166
12.4 Existing System 167
12.4.1 Advantages 167
12.4.2 Disadvantages 168
12.4.3 Applications 168
12.5 Proposed System 169
12.6 Conclusion and Future Enhancement 170
References 171
13 A Process of Analyzing Soil Moisture with the Integration of Internet of Things and Wireless Sensor Network 173
R. Srinivasan, Kavitha R, V. Murugananthan and T. Mylsami
13.1 Introduction 174
13.1.1 Wsn 174
13.1.2 IoT 174
13.2 Literature Study 175
13.3 Proposed Work 176
13.3.1 Sensing and Transmitter Module 176
13.3.2 Receiver Unit 178
13.3.3 IoT Activation 178
13.3.4 Event Recognition Algorithm 179
13.4 Result and Discussion 180
13.5 Conclusion 182
References 183
14 Automatic Angular Position Stabilization of Ambulance Stretcher in Real Time 185
Vedant Joshi, Maheshwari S. and Kathirvelan J.
14.1 Introduction 185
14.2 Materials and Methods 187
14.2.1 Interior and Flaws 187
14.2.2 Proposed Position of the Stretcher 188
14.2.3 Hardware and Software 188
14.2.4 Methodology 189
14.3 Results and Discussion 192
14.3.1 Results 192
14.4 Discussion 194
14.5 Conclusion 195
References 195
15 Automated Ploughing Seeding with Water Management System 199
Anto Sheeba J., Shyam D., Sivamani D., Sangari A., Jayashree K. and Nazar Ali A.
15.1 Introduction 199
15.2 Block Diagram 200
15.3 Working Methodology 201
15.4 Design Calculation 202
15.5 Simulation 203
15.6 Hardware Implementation 205
15.7 Conclusion 208
References 208
16 Detecting Fraudulent Data Using Stacked Auto-Encoding: A Three-Layer Approach 211
P. Saravanan, V. Indragandhi and V. Subramaniyaswamy
16.1 Introduction 211
16.1.1 Deep Learning 212
16.1.2 Auto-Encoders 212
16.2 Related Work 214
16.3 Proposed Methodology 215
16.4 Results and Discussion 218
16.5 Conclusion 221
Acknowledgment 221
References 221
17 Artificial Intelligence-Based Ambulance 223
Dr. R. Sumathi, R.M. Gokul, M. Gokulakrishnan, K. Ganesh Babu and S. Pavithra
17.1 Introduction 224
17.1.1 Problem Statement 224
17.1.2 Field of the Project 224
17.1.3 Objectives 225
17.2 Proposed System 225
17.2.1 Block Diagram of Traffic Signal Control System 225
17.2.2 Block Diagram of Biometric-Based Medical Records 226
17.3 Implementation of Traffic Signal Control System 226
17.3.1 Flowchart of Traffic Signal Control System 226
17.3.2 Algorithm of Biometric-Based Medical Records System 228
17.3.3 Methodology of Traffic Signal Control System 228
17.3.3.1 Normal Mode 229
17.3.3.2 Emergency Mode 230
17.3.4 Methodology of Biometric-Based Medical Records System 230
17.3.4.1 Smpt 230
17.4 Result and Discussion 231
17.4.1 Comparison of Results 231
17.4.2 Hardware Result 231
17.5 Conclusion 234
17.6 Future Scope 234
References 235
18 LoRa-Based Flaw Location Detection in HT Line Using GSM 237
Dr. M. Senthilkumar, Abisheck D., Gnana Prakash K., Hari Babu S. and Hariharan R.
18.1 Introduction 238
18.1.1 Different Types of Transmission Line Fault 238
18.1.1.1 Single Line-to-Ground Fault 238
18.1.1.2 Line-to-Line Fault 238
18.1.1.3 Double Line-to-Ground Fault 239
18.1.1.4 Balance Three-Phase Fault 239
18.2 Objective 240
18.3 Literature Survey 240
18.4 Proposed System 241
18.5 Flow Chart 244
18.6 Result and Discussion 244
18.7 Novelty of Work 248
18.8 Conclusion 250
18.9 Future Enhancement 251
References 252
19 Classification Models for Breast Cancer Detection 255
Varsha B., Sneka P., Tanuja A. and Shana J.
19.1 Introduction 255
19.2 Related Work 256
19.3 Research Objective 257
19.4 Methodology 257
19.4.1 Dataset Description 258
19.4.2 Data Preprocessing 258
19.4.3 Exploratory Data Analysis 258
19.5 Model Selection 260
19.5.1 Logistic Regression 260
19.5.2 Decision Tree Classifier 261
19.5.3 Random Forest Classifier 261
19.6 Results and Discussion 261
19.6.1 Confusion Matrix 261
19.6.2 Model Evaluation and Prediction 262
19.7 Conclusion 263
References 263
20 T-Count Optimized Quantum Comparator Circuit 265
Gayathri S. S., R. Kumar and Samiappan Dhanalakshmi
20.1 Introduction 265
20.2 Related Works 268
20.3 Proposed Quantum Comparator 268
20.3.1 Multi-Qubit Magnitude Comparator 268
20.4 Conclusion 270
References 270
21 IoT-Based Heart Rate Monitoring System for Smart Healthcare Applications 273
Jaba Deva Krupa Abel, Samiappan Dhanalakshmi, Sanjana N.L. and R. Kumar
21.1 Introduction 274
21.2 Related Work 275
21.3 Methodology 276
21.3.1 Fractional Fourier Transform 278
21.3.2 Amazon Web Services 280
21.4 Results and Discussion 281
21.5 Conclusion 283
References 284
22 Neural Collaborative Filtering-Based Hybrid Recommender System for Online Movies Recommendation 287
S. Priyanka, P. Saravanan, V. Indragandhi and V. Subramaniyaswamy
22.1 Introduction 288
22.2 Related Works 289
22.3 Proposed Methodology 290
22.3.1 Dataset Used for the Proposed System 291
22.3.2 Architecture Diagram 291
22.3.3 Sentiment Analysis 292
22.3.4 Hybrid Recommendation 293
22.3.4.1 Filtering Based on Content 293
22.3.4.2 Collaborative Filtering 293
22.3.5 Neural Collaborative Filtering (NCF) 294
22.3.6 User-Based Recurrent Neural Networks (RNN) 296
22.4 Results and Discussion 297
22.5 Conclusion and Future Work 299
References 300
23 Farmer's Eye Using CNN 303
Elam Cheren S., Yuvan Raj Kumar M., Vivek G., Udhayakumar N. and Saravanakumar M. V.
23.1 Introduction 303
23.2 Related Works 304
23.3 PV Module 305
23.4 Hardware Description 306
23.5 Software Implementation 309
23.6 Hardware Implementation 311
23.7 Conclusion 313
References 313
24 Solar Powered Density and Emergency-Based Traffic Control System Using NI LabVIEW 315
M. Devika Rani, G. Bhavani, K. Kartheek, A. Sindhura and D. Nikhila
24.1 Introduction 315
24.2 Literature Review 316
24.3 Methodology 317
24.3.1 Block Diagram 317
24.3.2 LabVIEW 319
24.4 Components 322
24.4.1 Main Components 322
24.4.1.1 Solar Panel 322
24.4.1.2 Battery 323
24.4.1.3 Buck Converter 323
24.4.1.4 IR Sensor 323
24.4.1.5 NI my RIO 324
24.4.1.6 NPN Transistor 324
24.4.1.7 Glue Sticks 324
24.4.1.8 Heat Sink Slive Tubes 325
24.4.1.9 Toggle Switch 325
24.4.2 Supporting Components 326
24.4.2.1 Connecting Pins 326
24.4.2.2 Leds 326
24.5 Result 328
24.5.1 SIM View 328
24.6 Implementation of Hardware Components 330
24.7 Conclusion 332
Applications 332
References 332
25 Observation of TCSU: Travel Cold Storage Unit Operated by SPV Technology 335
Devesh Umesh Sarkar, Tapan Prakash, Madhur Zadegaonkar, Ritu Bhimgade, Abhijeeta Gupta and Nidhi Ambekar
25.1 Introduction 335
25.2 Working Methodology 336
25.3 Tools & Platform 338
25.4 Design & Implementation 338
25.5 Advantages & Application 341
25.6 Conclusion 341
References 342
Index 345
1
Placement and Sizing of Distributed Generator and Capacitor in a Radial Distribution System Considering Load Growth
By Robert X. Perez
G. Manikanta1, N. Kirn Kumar2*, Ashish Mani1 and V. Indragandhi3
1Electrical & Electronics Engineering Department, A.S.E.T, Amity University Uttar Pradesh, Noida, UP, India
2Department of Electrical & Electronics Engineering, M S Ramaiah Institute of Technology, Bangalore, India
3School of Electrical Engineering, Vellore Institute of Technology, Vellore, Tamil Nadu, India
Abstract
Annual load growth in a distribution system is expanding consistently, which results in underprivileged voltage-regulation and increment in power losses. Independent implementation of Distributed generation (DGs) along with capacitors is chosen as alternative techniques to decrease the power loss in the network. Optimal location and capacity of Capacitors along with DGs not only maximize the percentage power loss reduction but also increase the voltage profile, if optimal location and capacity is appropriate. Inappropriate placement and competence of capacitors and DGs leads the system to an increase in power loss. The best location and competence of capacitors and DGs is a difficult nondifferentiable combinatorial optimization problem, which has been applied to solve various engineering optimization problems like improvement in reliability, loadabilty, loss minimization, etc., using various analytical and evolutionary algorithms. In this study economic load growth is modelled with a predetermined yearly load expansion for the base year and next five years. In this work the main contributions are made with placing and sizing the DGs and Capacitors to minimize the power losses for every year. Tabulated results demonstrate that simultaneous implementation of Capacitor and DGs has high reduction in power loss for every year including base year in comparison with independent implementation of DGs and Capacitors. For obtaining the best location and competence of capacitors and DGs an Adaptive Quantum inspired evolutionary Algorithm (AQiEA) is applied successfully. AQiEA uses probabilistic representation with Q-bit and does not require any additional operators. The effectiveness of AQiEA is verified on a standard test bus system, i.e., 85 bus system. Simulated results exhibit that the proposed algorithm has superior performance in comparison to the algorithms in the available literature.
Keywords: Distributed generators, capacitor, load growth, power losses, 85 bus system, AQiEA
1.1 Introduction
The power demand at distribution network keeps on increasing day to day and in some scenarios the generated power is unable to meet the required load demand. Load demand at distributed network is exponentially increasing from day to day, due to industrial, domestic, commercial, municipal, residential and irrigation needs. Load growth in distribution network is a natural phenomenon which results in increased power losses (both active and reactive) and increased voltage drop. Many methods and techniques have been executed in distributed networks in order to decrease the losses. Over the last few decades, DGs and Capacitors in the distributed network are used to reduce the losses. Implementation of DG in the network will reduce losses and also improve the system voltage. DGs are defined as small power generating sources, located nearer to the load centers and size varies from kW to few MW [1]. DGs are used in distribution system due to its ease of implementation, environmental friendly technologies and low maintenance [2]. Different types of DG are available with respect to their modular structure and size. Therefore, their impact on the distribution system varies depending on location and capacity [3]. Compensation of reactive power in the distribution network is generally provided by the capacitors. Installation of Capacitors nearer to load centres reduces the power losses and maintains the voltage profile within permissible limits [4].
Analytical-based methods are easy to implement; their major drawback is implementation of single DG or Capacitor with large size in order to reduce the losses [5-7]. In most of the works, minimization of power loss in distribution system with DG integration, population-based meta-heuristics are used as solution strategies. Symbiotic Organism Search [8], Particle Swarm Optimization [9], Simulated Annealing [10], Big-Bang Big-crunch optimization [11] and Fire Work Algorithm [12] are some of the well-known optimization techniques used to reduce the losses. However, Simulated Annealing [13], Firefly Algorithm [14], Plant Growth Simulation Algorithm [15], Teaching Learning-Based Optimization [16] and Particle Swarm Optimization [17] are some population-based meta-heuristic techniques used for optimal location and capacity of Capacitors to reduce the losses. Some methods have considered only injection of real power (DG) and some other methods considered only injecting the reactive power (Capacitor) into the system, and other methods have considered simultaneous implementation of capacitors and DG [18, 19].
In this study, AQiEA was implemented to find the optimal placement and capacity of Capacitors and DGs in distribution network without violating the limits. The objective of reducing losses was considered by implementing DGs and Capacitor placements both at the same time. The yearly load increment was calculated in advance for continuous successive five years. Effect of load increase was calculated based on with and without inclusion of Capacitors and DGs. In recent times, AQiEA was applied on DG network for optimal location of capacitor was successfully applied [20], optimal DG problem [21-23], DG operation along with the network re arrangement [24], simultaneous implementation of both DG and Capacitor [25], ceramic grinding [26] and constraint handling technique [27].
The rest of the chapter was prepared as follows. The problem formulation section describes the objective to minimize the power loss by implementation of both Capacitor and DGs with predetermined annual load growth. Placement and sizing of Capacitors and DGs is a tough task and also a non-differentiable combinational optimization problem. The problem of optimization of placing and sizing of capacitors was solved by using AQiEA, which is described in the section Algorithm. The efficiency of AQiEA was compared with some other algorithms in the Results and Discussions section. In the final section of the chapter a conclusion is provided.
1.2 Problem Formulation
A load forecast for five years was precalculated based on the past and present load growth, which was used as an objective function for minimization of power losses. This was assumed based on yearly load growth in the DG network and determined by using growth rate plus the initial load in the network [28].
(1.1) (1.2)Where PLk(y) & QLk(y) are the real and reactive load in y year, PLk(0) & QLk(0) are the real and reactive load at base year, g is the annual load growth which is assumed as 7.5% and represents number of year (maximum number of years considered for this study is 5).
The primary goal of this research is to reduce power loss for every year by simultaneous implementation of Capacitor and DG. The generalized objective function is given as follows:
(1.3)Where, Pm & Qm are real and reactive power injections at mth bus. Vm indicates voltage at mth bus, Rm & Xm indicates magnitude of resistance and inductance.
Inequality Constraint:
Operation of DG and Capacitor:
(1.4) (1.5)The power injected by DG into the network should be within the limits. PDG(m) & QDG(m) are injected real and reactive powers.
Voltage limit:
(1.6)The voltage produced at each individual bus in the network has to be in acceptable limits.
Equality Constraint:
Power injection:
(1.7)The total power injected by DGs and Capacitor in addition to the substation must be equal or less than its total load demand and losses of the system. Where Psub, Ploss and Pload represents substation power, power loss and demand in the system.
1.3 Algorithm
Quantum-inspired evolutionary algorithms:
QiEA uses probabilistic representation with Q-bit and it has good characteristic representation of population diversity compared with other representations. It is defined as the smallest unit of information in a quantum computer [29]. It could be represented in two states as state 'a', and state 'b' or the sum of both states. It can be shown in the following equation as
(1.8)Here probability amplitudes Y1 and Y2 are connected to its corresponding states. Y1 2 and Y2 2 will provides probability of Q-bits which are to be found in state 'a' or 'b' respectively. A Q-bit individual 'q' with m-bits is given as follows
(1.9)Here, |Y1i|2 + |Y2i|2 = 1, i = 1,2,..m
In QiEA, qubit probabilistic nature is widely used for maintaining diversity. Quantum gate operators are used...
