| Title |
Multilevel Energy Management And Optimal Control System In Smart Cities Based On Deep Machine Learning |
| ID_Doc |
38545 |
| Authors |
Reza S.; Atefeh H.; Javid G.; Ahmed A.D. |
| Year |
2024 |
| Published |
Applications of Deep Machine Learning in Future Energy Systems |
| DOI |
http://dx.doi.org/10.1016/B978-0-443-21432-5.00011-5 |
| Abstract |
This chapter presents the multilevel structure of intelligent energy management and optimal control system (IEMOCS) in smart cities and intelligent networked microgrid (INMG) to minimize the operating cost, reduce the calculation time, minimize the processing operations, increase the calculation accuracy, and minimize the false data injection risks and cyber attacks as well as improvement dynamic response based on primary, secondary, and tertiary control levels. The IEMOCS based on the Hybrid Takagi-Sugeno-Kang Fuzzy System and Multiagent Deep Reinforcement Learning (Hybrid TSKFS&MADRL) model has been developed. The decision-making variables of the IEMOCS model are modeled using the two-level Markov-Decision process (MDP) and Deep Q network (DQN) methods. The MADRL structure is programmed based on offline training and online operation. The deep deterministic policy gradient (DDPG) method based on the alternating direction method of multipliers (ADMM) algorithm has been developed to improve the critic and actor network learning structure. © 2024 Elsevier Inc. All rights reserved. |
| Author Keywords |
demand response programs; intelligent energy management and optimal control system; Intelligent networked microgrid; multiagent reinforcement learning; smart cities |
