Artificial Intelligence-Based Energy Management Systems for Smart Microgrids

Baseem Khan, Sanjeevikumar Padmanaban, Hassan Haes Alhelou, Om Prakash Mahela, S. Rajkumar, Baseem Khan, Sanjeevikumar Padmanaban, Hassan Haes Alhelou, Om Prakash Mahela, S. Rajkumar

• Publisher: CRC Press
• Year: 2022
• Print ISBN: 9780367754341
• eBook ISBN: 9781000589252
• Topic: Technology & Engineering
• Subtopic: Electrical Engineering & Telecommunications
• Index: Technology & Engineering

Modeling and optimization of energy management systems for micro- and mini-grids play an important role in the fields of energy generation dispatch, system operation, protection coordination, power quality issues, and peak demand conflict with grid security. This comprehensive reference text provides an in-depth insight into these topics. This text discusses the use of meta-heuristic and artificial intelligence algorithms for developing energy management systems with energy use prediction for mini- and microgrid systems. It covers important concepts including modeling of microgrid and energy management systems, optimal protection coordination-based microgrid energy management, optimal energy dispatch with energy management systems, and peak demand management with energy management systems.

Key Features:

• Presents a comprehensive discussion of mini- and microgrid concepts
• Discusses AC and DC microgrid modeling in detail
• Covers optimization of mini- and microgrid systems using AI and meta-heuristic techniques
• Provides MATLAB®-based simulations on a mini- and microgrid

Comprehensively discussing concepts of microgrids with the help of software-based simulations, this text will be useful as a reference text for graduate students and professionals in the fields of electrical engineering, electronics and communication engineering, renewable energy, and clean technology.

1 Flexibility of Microgrids with Energy Management Systems

Hooman Firoozi, Hosna Khajeh, and Hannu Laaksonen

Flexible Energy Resource, School of Technology and Innovations, University of Vaasa, Vaasa, Finland

DOI: 10.1201/b22884-1

CONTENTS

1. 1.1 Introduction
2. 1.2 Flexible Energy Resources in Microgrids
3. 1.2.1 Storage-Based Flexible Resources
4. 1.2.2 Electric Vehicles (EVs)
5. 1.2.2.1 Battery Energy Storage (BES)
6. 1.2.2.2 Thermal Energy Storage (TES)
7. 1.2.2.3 Flywheel
8. 1.2.2.4 Fuel Cell (FC)
9. 1.2.3 Demand-Based Flexible Resources
10. 1.2.3.1 Thermostatically Controllable Load (TCL)
11. 1.2.3.2 Shiftable Load
12. 1.2.3.3 Curtailable Load
13. 1.2.4 Fuel-Based Flexible Resources
14. 1.2.4.1 Combined Heat and Power (CHP)
15. 1.2.4.2 Diesel Generator (DiGen)
16. 1.3 Modeling the Microgrid Energy Management
17. 1.3.1 Microgrid Energy Management Methods
18. 1.3.2 Microgrid Energy Management Objectives
19. 1.3.2.1 Cost Reduction/Profit Maximization
20. 1.3.2.2 Self-Sufficiency
21. 1.3.2.3 Flexibility Provision
22. 1.3.2.4 TSO-Level Flexibility Services
23. 1.3.2.5 DSO-Level Flexibility Services
24. 1.3.3 Microgrid Energy Management Tools and Techniques
25. 1.3.3.1 Optimization Methods
26. 1.3.3.2 Deterministic Optimization
27. 1.3.3.3 Stochastic Optimization
28. 1.3.3.4 Robust Optimization
29. 1.3.3.5 Uncertainty Characterization
30. 1.4 Conclusion
31. References

1.1 Introduction

In recent years, approaches towards energy transition and sustainable development have been ever-increasing due to the need for mitigating climate change issues and the efficient utilization of existed energy resources. With this regard, state-of-the-art technologies and infrastructures along with active operation and control of different energy resources would become crucial. Amongst all energy resources, microgrids (MGs) are believed to be one of the highly potent resources to deal with the issues of electrical systems. In other words, active operation and control of MGs in which there exist different kinds of demands and energy resources (e.g., energy storages, micro-generation units, etc.) would be beneficial not only for MG stakeholders in terms of cost-benefit efficiency but also for power system operators in terms of MGs’ contribution to grid's flexibility [1, 2, 3, 4, 5].

In order to unlock the active utilization of MGs, cutting-edge technologies along with efficient infrastructure are a necessity. These technologies together in communication with the MGs’ energy resources are known as energy management systems (EMSs). EMSs are intelligent automated systems that contribute to, for instance, lowering/shifting energy consumption in critical moments along with a reduction in the MGs’ costs. Although the utilization of EMS might consider other objectives such as CO₂ emission reduction or self-sufficiency, they mostly employ optimization techniques either as single-objective or multi-objective approaches. EMSs can also enable either the bidirectional energy exchange with the network in grid-connected mode, or stand-alone operation of MGs in islanded-mode [6, 7, 8, 9, 10].

In this chapter, the focus of the study is on the MGs equipped with an EMS. There have been introduced several approaches to the energy management of MGs. However, in most of them, economic aspects, i.e., cost reduction, are the top priority desire of the problem from the MG stakeholders’ point of view. This could be done in different ways. On the one hand, reducing the total costs of the MGs by maximum utilization of self-production facilities (PV panels, wind turbines, etc.) as well as changing the energy consumption over time from peak hours to off-peak hours during the day. On the other hand, exploiting MGs’ flexibility so as to help the upstream grid in critical moments for monetary profits in return. Accordingly, the authors first present an introduction to flexible energy resources (FERs) in MG along with their characteristics in Section 1.2. Afterward, the MGEM modeling approaches are widely presented in Section 1.3. In this section, first, the different kinds of management method deployed in the MGs are illustrated. Then, various objectives for energy management in MGs will be introduced. Regarding this section, we introduce a number of approaches based on well-known optimization algorithms considering different MG-related as well as grid-related constraints. Microgrids’ constraints are related to the physics and limitations of the MG's resources whilst the constraints of the grid are related to the limitation of energy exchange with the upstream grid (e.g., congestion management, emission reduction, and/or energy loss reduction). Moreover, the application of the MGEM system in MGs with FERs such as energy storages, electric vehicles (EVs), and thermostatically controllable loads (TCLs) which exchange energy and flexibility with the grid will be discussed as well which is followed by the flexibility services that MGs could provide to the different levels of power system. Finally, this chapter will be summarized and con...

Table of contents

• Cover
• Half Title
• Title Page
• Copyright Page
• Contents
• Acknowledgments
• Editors
• Chapter 1: Flexibility of Microgrids with Energy Management Systems
• Chapter 2: Hybrid Particle Swarm Optimization – Artificial Neural Network Algorithm for Energy Management
• Chapter 3: Community Microgrid Energy Scheduling Based on the Grey Wolf Optimization Algorithm
• Chapter 4: Different Optimization Algorithms for Optimal Coordination of Directional Overcurrent Relays
• Chapter 5: Microgrids—A Future Perspective
• Chapter 6: Control Techniques for the Operation and Power Management of Smart DC Microgrids
• Chapter 7: Analysis and Optimization of a PV-Integrated Rural Distribution Network
• Chapter 8: Fuzzy C-Means Clustering and K-NN Regression-Based Protection Scheme for Transmission Lines
• Chapter 9: Estimation of Solar Insolation Along with Worldwide Airports Situated on Different Latitude Locations: A Case Study of Rajasthan State, India
• Chapter 10: An Algorithm for Identification of Multiple Power Quality Disturbances
• Chapter 11: Recognition of Simple Power Quality Disturbances Using Wavelet Packet-Based Fast Kurtogram and Ruled Decision Tree Algorithm
• Chapter 12: Identification of Transmission Line Faults Using Voltage-Based Stockwell Transform Features and Decision Rules Supported Fault Classification
• Chapter 13: Algorithm Based on Harmonic Wavelet Transform and Rule-Based Decision Tree for Detection and Classification of Transmission Line Faults
• Chapter 14: A Voltage-Based Algorithm Using the Gabor Wigner Distribution and Rule-Based Decision Tree for the Detection of Transmission Line Faults
• Chapter 15: Power Quality Estimation and Event Detection in a Distribution System in the Presence of Renewable Energy
• Chapter 16: Recognition and Categorization of PQ Disturbances Using a Power Quality Index and Mesh Plots
• Index