Internet of Energy for Smart Cities: Machine Learning Models and Techniques

ISBN-13: 9780367497750 / Angielski / Twarda / 2021 / 302 str.

Anish Jindal; Neeraj Kumar; Gagangeet Singh Aujla

Opis

The focus of this book is on using the machine learning approaches to present various solutions for IoE network in smart cities to solve various research gaps such as demand response management, resource management and effective utilization of the underlying ICT network. It helps build the technical understanding for the reader.

Spis treści

SECTION I Overview
Chapter 1 Smart City: The Verticals of Energy Demand and Challenges
Sumedha Sharma, Ashu Verma, and B.K. Panigrahi
1.1 Introduction
1.2 Smart Energy Distribution
1.2.1 Demand Response
1.2.2 Demand Side Management
1.3 Real-Time Grid Analytics and Data Management
1.3.1 Energy System Operations
1.3.2 Energy Management Systems
1.3.3 Design and Formulation of Optimizer Model
1.3.4 Real-Time Optimization
1.3.4.1 Robust Optimization
1.3.4.2 Stochastic Programming with Recourse
1.3.4.3 Chance-Constrained Optimization
1.3.5 Big Data Analytics
1.3.6 Energy Blockchain
1.4 Intelligent Cloud based Grid Applications
1.4.1 Centralized Control
1.4.2 Decentralized Control
1.4.3 Distributed Control
1.4.4 Multi-Agent Systems
1.5 Conclusion

SECTION II Smart Grids
Chapter 2 Conventional Power Grid to Smart Grid
Dristi Datta and Nurul I Sarkar
2.1 Introduction
2.2 Evolution: From Power Grid to Smart Grid
2.3 Benefits of Smart Grid System
2.3.1 Technological Benefits
2.3.2 Benefits to Customers
2.3.3 Benefits to Stakeholders
2.4 Smart Grid: Standards and Technologies
2.4.1 Standards
2.4.1.1 Revenue Metering Information Model
2.4.1.2 Building Automation
2.4.1.3 Substation Automation
2.4.1.4 Powerline Networking
2.4.1.5 Home Area Network Device Communication
Measurement and Control
2.4.1.6 Application-Level Energy Management
Systems
2.4.1.7 Inter-Control and Interoperability Center
Communications
2.4.1.8 Cyber Security
2.4.1.9 Electric Vehicles
2.4.2 Technologies
2.4.2.1 Storage Systems
2.4.2.2 Telecommunication Systems
2.4.2.3 ICT Infrastructure
2.5 Implementation Aspects
2.6 Challenges of Implementing Smart grid
2.6.1 Technical Challenges
2.6.2 Socio-economic Challenges
2.6.3 Miscellaneous
2.7 Open Research Questions
2.8 Concluding Remarks

Chapter 3 Smart Grids: An Integrated Perspective
Rafael S. Salles, B. Isa´ıas Lima Fuly, and Paulo F. Ribeiro
3.1 Introduction
3.2 Design challenges and philosophical considerations
3.2.1 Challenges and Technical Barriers
3.2.1.1 Renewable Generation Sources
3.2.1.2 Management and Market Complexity
3.2.1.3 Power Quality Issues
3.2.1.4 Cybersecurity
3.2.2 Holistic Normative Engineering Design for
Smart Grids
3.3 Smart grid architectures and technologies
3.3.1 The Communication Structure and Technologies
3.3.2 Smart Metering, Measurements, Control and
Automation
3.3.3 Microgrids and Key Technologies
3.4 Interoperability and scalability
3.4.1 Moving for Interoperability in Smart Grids
3.4.2 Scalability Aspects for the Modern Grid Model
3.5 Applications
3.5.1 Distributed Energy Resources Management
3.5.2 Energy Storage
3.5.3 Metering and Automation

SECTION III Internet of Energy (IoE)
Chapter 4 Internet of Energy: Solution for Smart Cities
Ash Mohammad Abbas
4.1 Introduction
4.2 Constituents of Smart Cities
4.2.1 Participation of Citizen
4.2.2 Residential Buildings
4.2.3 Street Lights
4.3 Need of IoE in Smart Cities
4.4 Problems to be Solved Using IoE
4.5 Operation of IoE
4.6 Integration of Electrical Vehicles to IoE
4.7 Infrastructure Required for IoE
4.8 IoE Tools
4.9 Conclusion

Chapter 5 IoE Applications for Smart Cities
Manju Lata and Vikas Kumar
5.1 Introduction
5.2 Energy Challenges in IoE
5.2.1 Reliability and Scalability
5.2.2 Security and Privacy intended for Data Access
5.2.3 Cost and Expenditure
5.2.4 Climate Conditions
5.2.5 Legislation
5.2.6 Education and Engagement of Citizens
5.2.7 Infrastructure and Capacity Building
5.3 Resolutions to IoE Energy Challenges
5.4 Smart Applications of IoE
5.5 Conclusion

Chapter 6 IoE Design Principles and Architecture
Rania Salih Abdalla, Sara A. Mahbub, Rania A. Mokhtar, Elmustafa
Sayed Ali, and Rashid A. Saeed
6.1 Introduction
6.2 IoE Architecture Models
6.2.1 An EMS-Based Architecture
6.2.2 A Fog Based Architecture
6.3 Embedding Intelligence in IoE Design
6.3.1 Cloud Computing
6.3.2 Fog Computing
6.3.3 Blockchain
6.4 IoE Standards8
6.4.1 IEEE 2030 Standard
6.4.2 IEEE 802.15.4g
6.4.3 IEEE 21450 and IEEE 21451
6.4.4 The 4th G -Based Low Power Wide Area (LPWA)
6.5 IoE Interoperability
6.6 IoE Privacy and Security
6.6.1 IoE Cyber Security
6.6.2 IoE Hardware Security
6.7 Conclusion

SECTION IV Machine Learning Models
Chapter 7 Machine Learning Models for Smart Cities
Dristi Datta and Nurul I Sarkar
7.1 Introduction
7.2 Machine Learning Frameworks
7.2.1 Machine Learning Approaches
7.2.2 Machine Learning Models
7.2.2.1 Supervised Learning Models
7.2.2.2 Unsupervised Learning Models
7.2.2.3 Semi-supervised Learning Models
7.2.2.4 Reinforcement Learning Model
7.3 Problem-solving using Machine Learning Techniques
7.4 Smart City Design Infrastructure
7.5 Smart City Design Challenges
7.5.1 Technical Challenges
7.5.2 Social Challenges
7.5.3 Economic Challenges
7.5.4 Miscellaneous Challenges
7.6 Implications of ML Models in the Design of Smart Cities
7.7 Concluding Remarks

Chapter 8 Machine Learning Models in Smart Cities - Data-Driven Perspective
Seyed Mahdi Miraftabzadeh, Michela Longo, and Federica Foiadelli
8.1 Introduction
8.2 Artificial Intelligence and the smart cities
8.3 Machine Learning
8.3.1 Categories of machine learning techniques
8.3.2 Big Data and Machine learning
8.4 Data terminology
8.4.1 Data definitions
8.4.2 Data type
8.4.3 Dataset in machine learning
8.5 Machine learning model
8.5.1 Model performance analysis (Error)
8.5.2 Validation Set
8.5.3 Model performance’s evaluation metrics
8.5.3.1 Classification metrics
8.5.3.2 Regression metrics
8.5.4 Machine learning algorithms
8.5.4.1 Classification algorithms
8.5.4.2 Regression algorithms

SECTION V Case Studies and Future Directions
Chapter 9 Case Study - 1: Machine Learning Techniques for Monitoring of PV Panel
Haba Cristian-Gyozo
9.1 Introduction
9.2 Solar panel monitoring
9.3 Photovoltaic operation degradation
9.4 Preventing measures
9.5 Real time data acquisition and analytics
9.5.1 Data sources
9.5.1.1 Local data acquisition systems
9.5.1.2 Meteorological mini stations
9.5.1.3 Astronomical data
9.5.1.4 Cloud services
9.5.1.5 Alerting systems
9.6 Machine learning techniques in PV panel operation
monitoring
9.7 Case study of system for PV panel monitoring
9.7.1 Photovoltaic systems in Romania
9.7.2 Description of the photovoltaic system
9.7.3 Weather station prototype
9.7.4 Data sources
9.7.4.1 Data from PV system
9.7.4.2 Weather ministations
9.7.4.3 Cloud services
9.7.5 ML Methodology
9.7.5.1 Data collection
9.7.5.2 Data Preprocessing
9.7.5.3 Model selection
9.7.5.4 Feature selection
9.7.5.5 Training and Validation
9.8 Conclusions

Chapter 10 Case Study - 2: Intelligent Control System for Smart Environment
Chintan Bhatt, Riya Patel, Siddharth Patel, Hussain Sadikot,
Akrit Khanna, and Esha Shah
10.1 Introduction
10.2 Related Work
10.3 Methodology
10.3.1 Privileged Access
10.3.2 Manual control of Electrical Appliances
10.3.3 Automatic control of electrical appliances
10.4 Experimental Set-up and Results
10.5 Discussion and Conclusion
10.6 Limitations
10.7 Future Enhancements

Chapter 11 Pathway and Future of the IoE in Smart Cities
Sharda Tripathi and Swades De
11.1 Introduction
11.2 IoE Application case studies
11.2.1 Smart monitoring of civic infrastructure and
amenities
11.2.2 Smart wireless services
11.2.3 Advanced power metering
11.2.4 Smart grid monitoring
11.3 Roles of big data and context-specific learning in future
IoE
11.3.1 Roles and challenges of big data
11.3.2 Node- and network-level data-driven optimization
11.4 Role and challenges of smart grid in IoE energy sustainability
11.4.1 Energy sustainability
11.4.2 Stability and controllability of power grid
11.5 Concluding remarks