This book provides a relatively whole view of data-driven decision-making methods for energy service innovation and energy system optimization. Through personalized energy services provision and energy efficiency improvement, the book can contribute to the green transformation of energy system and the sustainable development of the society. The book gives a new way to achieve smart energy management, based on various data mining and machine learning methods, including fuzzy clustering, shape-based clustering, ensemble clustering, deep learning, and reinforcement learning. The applications of these data-driven methods in improving energy efficiency and supporting energy service innovation are presented. Moreover, this book also investigates the role of blockchain in supporting peer-to-peer (P2P) electricity trading innovation, thus supporting smart energy management. The general scope of this book mainly includes load clustering, load forecasting, price-based demand response, incentive-based demand response, and energy blockchain-based electricity trading. The intended readership of the book includes researchers and engineers in related areas, graduate and undergraduate students in university, and some other general interested audience. The important features of the book are: (1) it introduces various data-driven methods for achieving different smart energy management tasks; (2) it investigates the role of data-driven methods in supporting various energy service innovation; and (3) it explores energy blockchain in P2P electricity trading, and thus supporting smart energy management.
Author(s): Kaile Zhou, Lulu Wen
Publisher: Springer
Year: 2022
Language: English
Pages: 325
City: Singapore
Preface
Acknowledgements
About This Book
Contents
1 Introduction
1.1 Background
1.2 Data-Driven Smart Energy Management
1.2.1 Framework of Smart Energy Management
1.2.2 Energy Big Data Driven Applications
1.2.3 Business and Service Model Innovation
1.3 Literature Review
1.3.1 Smart Energy System Management
1.3.2 Load Characteristic Recognition
1.3.3 Demand Response
1.4 Scope of the Book
References
2 Residential Electricity Consumption Pattern Mining Based on Fuzzy Clustering
2.1 Introduction
2.2 Methodology
2.2.1 Clustering
2.2.2 FCM Clustering
2.3 Model
2.3.1 Fuzzifier Selection
2.3.2 Cluster Validation
2.3.3 Searching Capability Optimization
2.4 Results and Discussion
2.4.1 Data
2.4.2 Discussion
2.4.3 Results Validation
2.5 Conclusion
References
3 Load Profiling Considering Shape Similarity Using Shape-Based Clustering
3.1 Introduction
3.2 Literature Review
3.3 Data
3.3.1 Dataset A
3.3.2 Dataset B
3.4 Framework and Methodology
3.4.1 Principal Component Analysis
3.4.2 K-means Clustering
3.4.3 Dynamic Time Warping
3.4.4 Shape-Based Clustering
3.5 Results and Discussion
3.5.1 Clustering with the Improved K-means Algorithm
3.5.2 Shape-Based Pattern Recognition
3.6 Conclusion
References
4 Load Classification and Driven Factors Identification Based on Ensemble Clustering
4.1 Introduction
4.2 Methodology
4.2.1 K-means Clustering
4.2.2 Spectral Clustering
4.2.3 Concurrent K-means and Spectral Clustering
4.2.4 Multi-Nominal Logistic Regression
4.3 Data
4.4 Results and Discussion
4.4.1 Load Classification Result
4.4.2 Different Load Patterns in Weekdays and Weekends
4.4.3 Influence Factors
4.5 Conclusion
References
5 Power Demand and Probability Density Forecasting Based on Deep Learning
5.1 Introduction
5.2 Deep Learning Model
5.2.1 Power Demand Forecasting
5.2.2 Power Demand Probability Density Forecasting
5.3 Case Study
5.3.1 Data
5.3.2 Feature Engineering
5.3.3 Case Study 1
5.3.4 Case Study 2
5.3.5 Case Study 3
5.4 Conclusion
References
6 Load Forecasting of Residential Buildings Based on Deep Learning
6.1 Introduction
6.2 Methodology
6.2.1 Artificial Neural Network
6.2.2 Recurrent Neural Network
6.2.3 Long Short-Term Memory
6.2.4 Gated Recurrent Unit
6.3 Model
6.3.1 Model Inputs and Formulation
6.3.2 Model Structure
6.3.3 Model Setup
6.4 Data and Evaluation Metrics
6.4.1 Data
6.4.2 Evaluation Metrics
6.5 Results and Discussion
6.5.1 Aggregated Load Forecasting
6.5.2 Discussion
6.6 Conclusion
References
7 Incentive-Based Demand Response with Deep Learning and Reinforcement Learning
7.1 Introduction
7.2 Demand Response Model
7.2.1 Energy Service Provider’s Profits
7.2.2 End Users’ Profits
7.3 Modified Deep Learning Model for Forecasting
7.3.1 Recurrent Neural Network
7.3.2 Modified Deep Learning Model Based on RNN
7.4 Reinforcement Learning for Incentive Rates Optimization
7.5 Results and Discussion
7.5.1 Data
7.5.2 Forecasting Results
7.5.3 Incentive Rate Optimization Based on Reinforcement Learning
7.6 Conclusion
References
8 Residential Electricity Pricing Based on Multi-Agent Simulation
8.1 Introduction
8.2 Multi-Agent Simulation Based Model
8.2.1 Power Market Analysis
8.2.2 Multi-Agent Simulation Framework
8.3 Residential Decision Model Based on User Satisfaction
8.3.1 Electricity Pricing Schemes
8.3.2 User Response Analysis Based on Demand Elasticity
8.3.3 Satisfaction Function and Decision Process
8.4 Case Study
8.5 Conclusion
References
9 Integrated Energy Services Based on Integrated Demand Response
9.1 Introduction
9.2 Modeling the Integrated Energy System
9.3 IDR Model
9.3.1 Objective Function
9.3.2 Constraint Conditions
9.3.3 Model Solution
9.4 Experimental Results and Discussion
9.4.1 Experimental Data and Setup
9.4.2 Results of Implementing IDR
9.4.3 Results Without Implementation of IDR
9.4.4 Influence of Load Reduction and Shifting
9.5 Conclusion
References
10 Electric Vehicle Charging Scheduling Considering Different Charging Demands
10.1 Introduction
10.2 Model
10.2.1 General Description
10.2.2 Charging and Discharging Time
10.2.3 Time Slot Division
10.2.4 Charging Urgency Indicator
10.2.5 Charging Mode Selection
10.2.6 Optimization Model
10.2.7 Total Load of Microgrid
10.3 Results and Discussion
10.3.1 Input Data and Simulation Setup
10.3.2 Dispatch Results and Comparative Analysis
10.3.3 Impact of Charging Pattern
10.3.4 Validation of the Simulation Results
10.4 Conclusion
References
11 P2P Electricity Trading Pricing in Energy Blockchain Environment
11.1 Introduction
11.2 P2P Trading in Energy Blockchain
11.2.1 PBFT Based Consortium Blockchain
11.2.2 P2P Trading Process
11.2.3 Security Analysis
11.2.4 Comparisons with Traditional Centralized Trading
11.3 Pricing of P2P Trading
11.3.1 Roles Identification
11.3.2 Stackelberg Game Among Prosumers
11.3.3 Non-cooperative Static Game Among Prosumers
11.4 Case Study
11.4.1 Comparison Results
11.4.2 Data
11.4.3 Results and Discussion
11.5 Conclusion
Appendix A. Simplification of KKT Conditions in Buyers’ Optimization Model
Appendix B. Existence of Nash Equilibrium Condition (2) and (3) Proof
Appendix C. Nomenclature
References
12 Credit-Based P2P Electricity Trading in Energy Blockchain Environment
12.1 Introduction
12.2 Credit-Based P2P Electricity Trading Model
12.2.1 Participants
12.2.2 Trading Rules
12.2.3 Consensus Mechanism
12.3 Credit-Based P2P Electricity Trading Process
12.3.1 Order Generation
12.3.2 Default Query
12.3.3 Order Picking
12.3.4 Trading Execution
12.3.5 Trading Check
12.3.6 Payment
12.4 Experimental Results
12.4.1 Experimental Platform and Parameter Setting
12.4.2 Results and Analysis
12.5 Conclusion
References
