Coordinated load frequency control of multi-area integrated energy system using multi-agent deep reinforcement learning

•A novel coordinated automatic generation control algorithm framework is proposed.•A deep reinforcement learning algorithm is introduced to obtains better performance.•Controllers can realize the coordinated control of multiple areas.•The proposed method can maximize control performance and minimize...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Applied energy Jg. 306; S. 117900
Hauptverfasser: Li, Jiawen, Yu, Tao, Zhang, Xiaoshun
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 15.01.2022
Schlagworte:
algorithms
China
curriculum
Distributed intelligent coordinated automatic generation control (DIC-AGC)
energy
Evolutionary imitation curriculum multi-agent double delayed deep deterministic policy gradient algorithm (EIC-MADDPG)
issues and policy
markets
Performance-based frequency regulation market
China
Performance-based frequency regulation market
Evolutionary imitation curriculum multi-agent double delayed deep deterministic policy gradient algorithm (EIC-MADDPG)
Distributed intelligent coordinated automatic generation control (DIC-AGC)
ISSN:0306-2619, 1872-9118
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:•A novel coordinated automatic generation control algorithm framework is proposed.•A deep reinforcement learning algorithm is introduced to obtains better performance.•Controllers can realize the coordinated control of multiple areas.•The proposed method can maximize control performance and minimize payment. To dynamically balance multiple energy fluctuations in a multi-area integrated energy system (IES), a coordinated power control framework, named distributed intelligent coordinated automatic generation control (DIC-AGC), is constructed among different areas during load frequency control (LFC). Furthermore, an evolutionary imitation curriculum multi-agent deep deterministic policy gradient (EIC-MADDPG) algorithm is proposed as a novel deep reinforcement learning algorithm to realize coordinated control and improve the performance of DIC-AGC in the performance-based frequency regulation market. EIC-MADDPG, which combines imitation learning and curriculum learning, can adaptively derive the optimal coordinated control strategies for multiple areas of LFC controllers through centralized learning and decentralized implementation. The simulation of a four-area LFC-IES model on the China Southern Grid (CSG) demonstrates the effectiveness of the proposed method in maximizing control performance while minimizing regulation mileage payment in every area against stochastic load and renewable power fluctuations.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0306-2619
1872-9118
DOI:10.1016/j.apenergy.2021.117900