Dynamic energy management and control of networked microgrids based on load to grid services and incentive-based demand response programs: A multi-agent deep reinforcement learning approach

•Increase the speed of operational processing.•Creation of a competitive and encouraging platform based on L2 G services.•Increase the accuracy of data assessment.•Configuration of the IBDR structure to improve the load profile. This study has presented the energy management paradigm in a networked...

Full description

Saved in:
Bibliographic Details
Published in:Sustainable cities and society Vol. 117; p. 105957
Main Authors: Seylab, Masoumeh Rezazadeh, Naderi, Mehdi S., Gharehpetian, Gevork B.
Format: Journal Article
Language:English
Published: Elsevier Ltd 15.12.2024
Subjects:
L2G services
Multi-agent deep reinforcement learning algorithm
Multi-task learning algorithm
Networked microgrid
Optimal operation
Voltage and frequency control
Multi-agent deep reinforcement learning algorithm
L2G services
Networked microgrid
Optimal operation
Voltage and frequency control
Multi-task learning algorithm
ISSN:2210-6707
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•Increase the speed of operational processing.•Creation of a competitive and encouraging platform based on L2 G services.•Increase the accuracy of data assessment.•Configuration of the IBDR structure to improve the load profile. This study has presented the energy management paradigm in a networked microgrid structure based on L2G services and considering incentive-based load response (IBDR) programs and energy market requirements to reduce operating costs, control and restore voltage and frequency index, providing the benefits of subscribers and distribution system operators. In this study, multi-objective functions such as optimal operation based on IBDR structure and energy market requirements, risk assessment, and L2G service approach are configured in the framework of central and local controllers. Optimal operation and risk assessment are analyzed by a multi-task learning algorithm based on multi-objective function and L2G service policies are evaluated based on multi-agent deep reinforcement learning. Control policies are sent by the communication system to the components affecting the optimal power distribution as well as the voltage and frequency controllers. L2G services have been evaluated in different scenarios such as plug-and-play operating conditions, load fluctuations, and operating in island mode. The results of optimal operation based on L2G services show that the IBDR program implementation reduces the total operation cost by 21%. Also, the total operating cost of the proposed framework is 13.97% less than the RL method and 27.8% less than the ANN method.
ISSN:2210-6707
DOI:10.1016/j.scs.2024.105957