IoT, Machine Learning and Blockchain Technologies for Renewable Energy and Modern Hybrid Power Systems / editors, C. Sharmeela [and three others].

Format:

Book

Contributor:

Sharmeela, C., editor.

Series:

River Publishers series in information science and technology.

Information Science and Technology Series

Language:

English

Subjects (All):

Blockchains (Databases).

Internet of things.

Renewable energy sources.

Physical Description:

1 online resource (306 pages)

Edition:

First edition.

Place of Publication:

Gistrup, Denmark : River Publishers, [2022]

Language Note:

In English.

Summary:

This edited book comprises chapters that describe the IoT, machine learning, and blockchain technologies for renewable energy and modern hybrid power systems with simulation examples and case studies. After reading this book, users will understand recent technologies such as IoT, machine learning techniques, and blockchain technologies and the application of these technologies to renewable energy resources and modern hybrid power systems through simulation examples and case studies.

Contents:

Front Cover

IoT, Machine Learning and Blockchain Technologies for Renewable Energy and Modern Hybrid Power Systems

Contents

Preface

Acknowledgments

List of Figures

List of Tables

List of Contributors

List of Abbreviations

1 Introduction to IoT

1.1 Introduction

1.2 History

1.3 Applications of IoT

1.3.1 Domestic Applications

1.3.2 Applications in Healthcare

1.3.3 Applications in E-commerce

1.3.4 Industrial Applications

1.3.5 Applications in Energy

1.4 Technical Details of IoT

1.4.1 Sensors

1.4.2 Actuators

1.4.3 Processing Topologies

1.4.4 Communication Technologies

1.5 Recent Developments

1.6 Challenges

1.7 Conclusion

References

2 IoT and its Requirements for Renewable Energy Resources

2.1 Introduction

2.1.1 IoT and its Necessity

2.1.2 Challenges in RES

2.1.3 Integration of IoT in RES and Benefits

2.2 Industrial IoT

2.2.1 Architecture of IoT

2.2.2 IoT Components

2.3 RES and IoT

2.3.1 IoT Controls for RES

2.3.2 Challenges in IoT Implementation

2.4 Challenges of IoT in EMS Post-implementation

2.4.1 Privacy Issues

2.4.2 Security Concerns

2.4.3 Data Storage Issues

2.4.3.1 Challenges in data management

2.4.3.2 Challenges in fetching data

2.4.3.3 Challenges in allocation

2.5 Solution to IoT Challenges

2.5.1 Blockchain Methodology

2.5.1.1 Blockchain technology infrastructure features

2.5.1.2 Application domains of blockchain technology

2.5.1.3 Challenges of blockchain technology

2.5.2 Cloud Computing

2.5.2.1 Reference architecture

2.5.2.2 Network communication and its challenge

2.5.2.3 Privacy and security

2.5.2.4 Background information

2.5.2.5 Big data analytics

2.5.2.6 Provision of program quality

2.5.2.7 IPv4 addressing limit

2.5.2.8 Legal aspects and social facts.

2.5.2.9 Service detection

2.6 Conclusion

3 Power Quality Monitoring of Low Voltage Distribution System Toward Smart Distribution Grid Through IoT

3.1 Introduction

3.2 Introduction to Various PQ Characteristics

3.3 Introduction to IoT

3.4 Smart Monitoring using IoT for the Low Voltage Distribution System

3.5 Power Quality Monitoring of Low Voltage Distribution System - Case Study

3.5.1 Undervoltage

3.5.2 Overvoltage

3.5.3 Interruption

3.5.4 Overload in Branch Circuit

3.6 Conclusion

4 Health Monitoring of a Transformer in a Smart Distribution System using IoT

4.1 Introduction

4.2 Introduction to the Transformer

4.3 Failure of the Distribution Transformer

4.4 Transformer Health Monitoring System through IoT

4.4.1 Winding and Oil Temperature Sensor

4.4.2 Oil Level Monitoring Sensor

4.4.3 Current Sensor and Voltage Sensor

4.4.4 Microcontroller

4.4.5 LCD or Monitor

4.4.6 Communication System

4.4.7 Central Monitoring and Control

4.5 Case Study

4.6 Conclusion

5 Introduction To Machine Learning Techniques

5.1 Why and What is Machine Learning?

5.1.1 Phrases in Machine Learning

5.1.2 Steps Involved in Machine Learning Practices

5.1.3 Properties of Data

5.1.4 Real-World Applications of Machine Learning

5.2 Classification of Machine Learning Techniques

5.2.1 Supervised Learning

5.2.1.1 Classification

5.2.1.2 Regression

5.2.2 Unsupervised Learning

5.2.2.1 Clustering

5.2.2.2 Association

5.2.3 Reinforcement Learning

5.2.3.1 Crucial terms in reinforcement learning

5.2.3.2 Salient features of reinforcement learning

5.2.3.3 Types of reinforcement learning

5.2.3.4 Reinforcement learning algorithms

5.3 Some Crucial Algorithmic Mathematical Models in Machine Learning

5.3.1 Logistic Regression.

5.3.2 Decision Trees

5.3.3 Linear Regression

5.3.4 K-Nearest Neighbors

5.3.5 K-Means Clustering

5.4 Pre-Eminent Python Libraries Intended for Machine Learning

5.4.1 Human Detection (OpenCV, HoG, SVM with Multi-Threading)

5.4.2 Instagram Filters - (OpenCV, Matplotlib, NumPy)

5.5 Machine Learning Techniques in State of Affairs of Power Systems

5.6 Conclusion

6 Machine Learning Techniques for Renewable Energy Resources

6.1 Introduction

6.2 Overview of Machine Learning

6.3 Deep Learning Architecture

6.4 LSTM Network Based Prediction

6.5 Concepts of Solar PV and its MPPT Techniques

6.6 Simulation Results and Discussion

6.6.1 Modeling and Performance Analysis

6.6.2 Prediction or Forecasting Methodology

6.6.3 Utilizing Predicted Value in MPPT Technique

6.7 Conclusion and Future Directions

7 Application of Optimization Technique in Modern Hybrid Power Systems

7.1 Introduction

7.2 Modern Power System

7.2.1 Deregulated Power System

7.2.2 Components of Deregulation

7.2.3 Types of Transactions

7.2.3.1 Bilateral transactions

7.2.3.2 DPM and APF

7.2.4 Renewable Energy Sources

7.2.4.1 Doubly fed induction generator

7.2.4.2 DFIG in deregulated power system

7.3 Optimization Techniques and Proposed Technique

7.3.1 Controllers

7.3.2 PI Controller

7.3.3 Artificial Optimization Algorithm for Tuning PI

7.3.3.1 Differential evolution

7.3.3.2 Flower pollination algorithm

7.3.3.3 Hybrid algorithm

7.3.3.4 Design of a hybrid DE-FPA algorithm for LFC

7.4 Simulation Results and Discussion

7.5 Conclusion

8 Application of Machine Learning Techniques in Modern Hybrid Power Systems - A Case Study

8.1 Introduction

8.2 Technical Issues in Modern Hybrid Power Systems

8.2.1 Power Quality.

8.2.2 Demand-Supply Management

8.2.3 Synchronization and Islanding

8.2.4 Protective Devices, Safety, and Environment

8.2.5 Human Factor

8.3 Application of ML and Optimization Techniques in MHPS

8.4 A Prediction Case Study of ML in MHPS

8.4.1 Forecasting Irradiance of SPP

8.4.2 Metrics for Understanding the Performance of Predictions using ML Methods

8.4.3 Model-Based and Model-Free Regression Techniques

8.4.4 Prediction Block

8.4.5 Forecasting of Solar Irradiance with a Model-Based Regression Approach

8.4.6 Forecasting of Solar Irradiance with a Model-Free Regression Approach (ANNs)

8.4.7 Normalization, Training, and Testing for Model-Free Regression

8.5 Optimization Block in MHPS

8.5.1 Optimization-Assisted ML of MHPS

8.5.2 Experimental Setup

8.5.3 Validation Block

8.5.3.1 Thorough comparisons in voltage-magnitudes for the actual test day for model-based and model-free approaches

8.6 Conclusion

9 Establishing a Realistic Shunt Capacitor Bank with a Power System using PSO/ACCS

9.1 Introduction

9.2 Problem Statement

9.2.1 Power Flow Equations

9.2.2 Mathematical Representation

9.2.3 Sensitivity Calculations

9.3 Capacitor Bank Operation Strategies

9.4 Particle Swarm Optimization

9.5 Limitation Treatment

9.6 PSO Implementation for Offline Capacitor Study

9.7 Simulation System for Optimal Capacitor Allocation

9.7.1 Modified System Data

9.7.2 Simulation Study

9.8 Automatic Capacitor Control Scheme

9.8.1 ACCS IED Scope

9.8.2 ACCS Operation Logic Steps

9.8.3 ACCS Operation Sample

9.9 Conclusion

10 Introduction to Blockchain Technologies

10.1 Introduction and Classification

10.2 Blockchain Technology Characteristics

10.2.1 Multi-Centralization

10.2.2 Tamper-Proof, Traceable, and Transparent.

10.2.3 High Reliability

10.3 Blockchain Technology Graph

10.3.1 Core Technology Overview

10.3.2 Expansion Technology Overview

10.3.3 Supporting Technology Overview

10.4 Conclusion

11 Blockchain Technologies for Renewable Energy Resources with Case Study: SHA-256, 384, and 512

11.1 Introduction

11.2 Local Energy Trading and Consensus Algorithms

11.3 Simulation

11.3.1 Energy Trading Model and Case Study

11.3.2 Performance Result and Evaluation of the Models at Different Hash Algorithms

11.4 Conclusion and Recommendations

Index

About the Editors

Back Cover.

Notes:

Includes bibliographical references and index.

Description based on print version record.

ISBN:

9781523156283

1523156287

9781003360780

1003360785

9781000824407

1000824403

9781000824445

1000824446

9788770227117

877022711X

OCLC:

1355218743