Artificial Intelligence-Based Energy Management Systems for Smart Microgrids

Cover
Half Title
Title Page
Copyright Page
Contents
Acknowledgments
Editors
1. Flexibility of Microgrids with Energy Management Systems
1.1 Introduction
1.2 Flexible Energy Resources in Microgrids
1.2.1 Storage-Based Flexible Resources
1.2.2 Electric Vehicles (EVs)
1.2.2.1 Battery Energy Storage (BES)
1.2.2.2 Thermal Energy Storage (TES)
1.2.2.3 Flywheel
1.2.2.4 Fuel Cell (FC)
1.2.3 Demand-Based Flexible Resources
1.2.3.1 Thermostatically Controllable Load (TCL)
1.2.3.2 Shiftable Load
1.2.3.3 Curtailable Load
1.2.4 Fuel-Based Flexible Resources
1.2.4.1 Combined Heat and Power (CHP)
1.2.4.2 Diesel Generator (DiGen)
1.3 Modeling the Microgrid Energy Management
1.3.1 Microgrid Energy Management Methods
1.3.2 Microgrid Energy Management Objectives
1.3.2.1 Cost Reduction/Profit Maximization
1.3.2.2 Self-Sufficiency
1.3.2.3 Flexibility Provision
1.3.2.4 TSO-Level Flexibility Services
1.3.2.5 DSO-Level Flexibility Services
1.3.3 Microgrid Energy Management Tools and Techniques
1.3.3.1 Optimization Methods
1.3.3.2 Deterministic Optimization
1.3.3.3 Stochastic Optimization
1.3.3.4 Robust Optimization
1.3.3.5 Uncertainty Characterization
1.3.3.5.1 Uncertainty of Wind Units
1.3.3.5.2 Uncertainty of PV Units
1.3.3.5.3 Uncertainty of EV Owners' Behavior
1.3.3.5.4 Uncertainty of Flexibility Needs
1.3.3.5.5 Model Predictive Control
1.3.3.5.6 Game Theory
1.4 Conclusion
References
2. Hybrid Particle Swarm Optimization - Artificial Neural Network Algorithm for Energy Management
2.1 Introduction
2.1.1 Energy Management (EM)
2.1.2 Fuel Switch
2.1.3 DERs
2.1.4 Demand Response (DR)
2.2 Energy Management Systems (EMS)
2.3 Artificial Neural Network (ANN)
2.3.1 Biological and Artificial Neural Network
2.3.2 Comparison between ANN and BNN
2.3.3 Model of ANN
2.3.3.1 Network Architecture
2.3.3.2 One-Layer Feed Forward N/W
2.3.3.3 Many-Layer Feed Forward N/W
2.3.3.4 Recurrent Network
2.3.3.5 Adjustment of Weights (or) Learning
2.3.3.6 Supervised Learning
2.3.3.7 Unsupervised Learning
2.3.3.8 Reinforcement Learning
2.3.3.9 Activation Function
2.4 Particle Swarm Optimization
2.4.1 Flow Chart
2.5 ANN-PSO-EMS
2.6 Conclusion
References
3. Community Microgrid Energy Scheduling Based on the Grey Wolf Optimization Algorithm
3.1 Introduction
3.2 CMG Energy Scheduling Problem Formulation
3.2.1 Community Microgrid System Model
3.2.2 Problem Formulation
3.2.3 Constraints
3.3 Grey Wolf Optimization Algorithm
3.3.1 GW Hierarchy
3.3.2 Prey Encircling
3.3.3 Hunting
3.3.4 Prey Attacking (Exploitation)
3.3.5 Prey Searching (Exploration)
3.3.6 GWO Application for CMG Energy Scheduling
3.4 Results and Discussions
3.5 Conclusions
Acknowledgments
References
4. Different Optimization Algorithms for Optimal Coordination of Directional Overcurrent Relays
4.1 Introduction
4.1.1 Literature Review
4.1.2 Main Goals of this Chapter
4.2 DOCRs' Coordination Problem
4.2.1 Boundaries of the Coordination Problem
4.2.1.1 Limits on Relay Characteristics
4.2.1.1.1 Limits on Pickup Current Setting
4.2.1.1.2 Limits on TDS
4.2.1.1.3 Boundaries on DOCRs' Coordination
4.3 Optimization Techniques
4.3.1 GWO and EGWO
4.3.1.1 Conventional GWO
4.3.1.2 EGWO Algorithm
4.3.2 WOA and HWGO
4.3.2.1 WOA Technique
4.3.2.2 HWGO Algorithm
4.4 Results and Discussion
4.4.1 Description of Test System
4.4.1.1 The Eight-Bus Network
4.4.1.2 IEEE 30-Bus Test System
4.4.2 Using the EGWO for Solving the Coordination Problem
4.4.3 Using the HWGO for Solving the Coordination Problem
4.5 Conclusions
References
5. Microgrids—A Future Perspective
5.1 Introduction
5.2 A Note from NREL
5.3 Workings of a Microgrid
5.3.1 Grid-Connected Mode
5.3.2 Island Mode
5.4 Microgrid Control
5.4.1 Centralized Microgrid Control
5.4.2 Decentralized Microgrid Control
5.4.3 Primary Control Strategy
5.4.4 Secondary Control Strategy
5.4.5 Tertiary Control Strategy
5.5 Need for Microgrids
5.6 Issues Related to Microgrid Installations
5.7 Faults and Their Classification
5.8 FACTS Devices
5.8.1 STATCOM
5.8.2 SVC
5.8.3 SSSC
5.8.4 UPFC
5.8.5 IPFC
5.9 Conclusion
References
6. Control Techniques for the Operation and Power Management of Smart DC Microgrids
6.1 Introduction
6.1.1 Architecture of DC Microgrids
6.1.2 Power Control Algorithm for Smart DCMG
6.1.3 Dynamic Modeling of Single-Phase VSI with LC Filter
6.1.4 Determination of Transfer Functions of Single-Phase VSI
6.2 Developed Control Technique of Single-Phase VSI
6.3 Operational Analysis with Simulation Results
6.3.1 Performance Analysis of Smart DCMG for Power Control Technique
6.3.1.1 Performance Analysis for Developed Control Technique of Single-Phase VSI
6.4 Conclusions
References
7. Analysis and Optimization of a PV-Integrated Rural Distribution Network
7.1 Introduction
7.2 Modeling of a Rural Distribution Network
7.3 Formulation of Optimal Power Flow Problem
7.3.1 Formulation of Objective Functions
7.3.2 Formulation Constraints Functions
7.3.2.1 Equality Constraints
7.3.2.2 Inequality Constraints
7.4 Solution Methodology
7.5 Results and Discussion
7.6 Conclusion
References
8. Fuzzy C-Means Clustering and K-NN Regression-Based Protection Scheme for Transmission Lines
8.1 Introduction
8.2 Machine Learning Algorithm Used in the Proposed Algorithm
8.2.1 Fuzzy C-Means Clustering (FCM)
8.2.2 K-Nearest Neighbor (K-NN)
8.3 Proposed Algorithm
8.3.1 Detection and Classification Method
8.3.2 Fault Location Detection
8.4 Simulation and Results
8.4.1 Various Case Studies of Fault Identification and Classification
8.4.2 Simulation of Fault Location Estimation
8.5 Conclusion
References
9. Estimation of Solar Insolation Along with Worldwide Airports Situated on Different Latitude Locations: A Case Study of Rajasthan State, India
9.1 Introduction
9.1.1 Solar Energy
9.1.2 Solar Radiation
9.1.3 Solar Irradiance
9.1.4 Solar Constant
9.1.5 Effect of Atmosphere on Solar Radiation
9.1.6 Insolation
9.1.7 The Sun-Earth Relationship
9.1.8 Solar Array Orientation
9.1.9 Solar Radiation Measurement Device
9.2 Calculation for Cumulative Inclined Radiation by Using Instant Radiation with Classical Approach (Average Method)
9.3 Relative Study of Global Solar Insolation in Bikaner, Rajasthan Desert
9.3.1 Selection of PV Module Direction (Azimuth Angle) to Get Maximum Solar Insolation
9.3.2 Selection of Tilt Angle of a Solar PV Module at a Particular Location
9.4 Relative Study of Cumulative Inclined Radiation on Different Latitudes Using METEONORM Software
9.5 Conclusion
References
10. An Algorithm for Identification of Multiple Power Quality Disturbances
10.1 Introduction
10.2 Formulation of PQ Issues and Methodology
10.2.1 Formulation of PQ Disturbances
10.2.2 Algorithm Adopted to Identify and Categorize the PQ Disturbances
10.3 Results and Discussion
10.3.1 Voltage Signal with Sag and Harmonics
10.3.2 Voltage Signal with Swell and Harmonics
10.3.3 Voltage Signal with Momentary Interruption and Harmonics
10.3.4 Voltage Signal with Oscillatory Transient and Voltage Sag
10.3.5 Voltage Signal with Oscillatory Transient and Voltage Swell
10.3.6 Voltage Signal with Impulsive Transient and Voltage Sag
10.3.7 Voltage Signal with Impulsive Transient and Voltage Swell
10.3.8 Voltage Signal with Simultaneou Occurrence of Voltage Swell, Oscillatory Transient, and Harmonics
10.3.9 Voltage Signal with Simultaneous Occurrence of Voltage Sag, Oscillatory Transient, and Harmonics
10.3.10 Voltage Signal with Simultaneous Occurrence of Oscillatory Transient, Impulsive Transient, Voltage Sag, and Harmonics
10.4 Feature Estimation and Classification of PQ Events
10.4.1 Feature Extraction
10.4.2 Classification of Complex PQ Disturbances
10.5 Performance Validation
10.6 Conclusion
References
11. Recognition of Simple Power Quality Disturbances Using Wavelet Packet-Based Fast Kurtogram and Ruled Decision Tree Algorithm
11.1 Introduction
11.1.1 Related Work
11.1.2 Contribution of the Proposed Work
11.1.3 Organization of this Chapter
11.2 Methodology
11.2.1 Formulation of Problem
11.2.2 Formulation and Generation of Simple Nature PQ Disturbances
11.2.3 Wavelet Packet Supported Fast Kurtogram and Decision Rules-Based Algorithm for Identification and Classification of Simple Nature PQ Disturbances
11.3 Results and Discussion
11.3.1 Voltage Signal Without PQ Disturbance
11.3.2 Voltage Signal with Sag Disturbance
11.3.3 Voltage Signal with Swell Disturbance
11.3.4 Voltage Signal with Momentary Interruption Disturbance
11.3.5 Voltage Signal with Harmonic Disturbance
11.3.6 Voltage Signal with Oscillatory Transient Disturbance
11.3.7 Voltage Signal with Impuslive Transient Disturbance
11.3.8 Voltage Signal with Notches Disturbance
11.3.9 Voltage Signal with Spikes Disturbance
11.3.10 Classification of Power Quality Disturbances
11.3.11 Performance of Proposed Algorithm
11.3.12 Comparison of Performance of Proposed Algorithm with Reported Techniques
11.4 Conclusion
References
12. Identification of Transmission Line Faults Using Voltage-Based Stockwell Transform Features and Decision Rules Supported Fault Classification
12.1 Introduction
12.1.1 Related Work
12.1.2 Contribution of the Work
12.1.3 Organization of this Chapter
12.2 Methodology and Test System
12.2.1 Problem Formulation
12.2.2 Test System Used for the Study
12.2.3 Voltage Supported Algorithm Used for the Estimation of Fault Conditions
12.3 Results and Discussion
12.3.1 Fault on Phase-A and Involvement of Ground
12.3.2 Fault on Phases-A and B without Involvement of Ground
12.3.3 Fault on Phases-A and B with Involvement of Ground
12.3.4 Fault on All the Phases without Involvement of Ground
12.3.5 Fault on All the Phases with Involvement of Ground
12.3.6 Impact of Variations in Fault Incidence Angle
12.3.7 Impact of Variations in Fault Impedance
12.3.8 Impact of Variations in Fault Location
12.3.9 Classification of the Faults Using Voltage-Based Features
12.4 Conclusion
References
13. Algorithm Based on Harmonic Wavelet Transform and Rule-Based Decision Tree for Detection and Classification of Transmission Line Faults
13.1 Introduction
13.2 Proposed Test System
13.3 Simulation Results and Discussion
13.3.1 Line to Ground Fault
13.3.2 Double Line Fault
13.3.3 Double Line to Ground Fault
13.3.4 Three-Phase Fault with the Involvement of Ground
13.3.5 Classification of Transmission Line Faults
13.4 Conclusion
References
14. A Voltage-Based Algorithm Using the Gabor Wigner Distribution and Rule-Based Decision Tree for the Detection of Transmission Line Faults
14.1 Introduction
14.2 Proposed Test System
14.3 Proposed Methodology
14.4 Simulation Results with Their Discussion
14.4.1 Line to Ground Fault
14.4.2 Double Line Fault
14.4.3 Double Line to Ground Fault
14.4.4 Three-Phase Fault Involving Ground
14.5 Performance Comparison
14.6 Conclusion
References
15. Power Quality Estimation and Event Detection in a Distribution System in the Presence of Renewable Energy
15.1 Introduction
15.2 Test Distribution Grid with RE Generators
15.3 Proposed PQ Estimation and Event Detection Algorithm
15.4 Discussion of Simulation Results
15.4.1 Feeder Opening Event
15.4.2 Feeder Closing Event
15.4.3 Load Switching ON Event
15.4.4 Load Switching OFF Event
15.4.5 Capacitor Switching ON Event
15.4.6 Capacitor Outage Event
15.4.7 Solar Power Plant Outage Event
15.4.8 Solar Power Plant Grid Synchronization Event
15.4.9 Wind Power Plant Outage Event
15.4.10 Wind Power Plant Grid Synchronization Event
15.5 Classification of Events
15.6 Performance Comparison
15.7 Conclusion
References
16. Recognition and Categorization of PQ Disturbances Using a Power Quality Index and Mesh Plots
16.1 Introduction
16.2 Research Method
16.2.1 Formulation of Single-Stage PQ Disturbances
16.2.2 Algorithm Adopted to Identify and Categorize the PQ Disturbances
16.3 Results and Analysis
16.3.1 Voltage Signal without PQ Disturbance
16.3.2 Sag Associated with the Voltage Signal
16.3.3 Swell Associated with the Voltage Signal
16.3.4 Momentary Interruption Associated with the Voltage Signal
16.3.5 Harmonics Associated with the Voltage Signal
16.3.6 Oscillatory Transient Associated with the Voltage Signal
16.3.7 Impulsive Transient Associated with the Voltage Signal
16.3.8 Notch Associated with the Voltage Signal
16.3.9 Spike Associated with the Voltage Signal
16.4 Extraction of Features from the PQI and PQTLI for the Classification of PQ Events
16.5 Classification of PQ Disturbances
16.6 Performance Validation
16.7 Conclusion
References
Index