Journal
IEEE INTERNET OF THINGS JOURNAL
Volume 10, Issue 14, Pages 12923-12937Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JIOT.2023.3253693
Keywords
Active control; distributed optimization; evolutionary multiagent deep meta actor critic (EMA-DMAC); isolated multiarea microgrid; load frequency control
Ask authors/readers for more resources
This article proposes a swarm intelligence load frequency control (SI-LFC) method for coordinating the interests of multiple operators in an isolated multiarea microgrid. The method treats the units in each area as independent agents and adopts swarm intelligence centralized offline learning policy to achieve a balance of interests. Online, each unit only needs to collect the frequency locally to achieve global optimal control, reducing network communication burden. The article also introduces an evolutionary multiagent deep meta-actor-critic (EMA-DMAC) algorithm, which enhances collaborative learning of swarm agents, improving the robustness and quality of SI-LFC strategies. The proposed method's effectiveness is demonstrated in a simulation of a four-area LFC model for Sansha island in the China Southern Grid (CSG).
In an isolated multiarea microgrid, a conventional centralized active control policy relies on excessive communication and therefore is incapable of coordinating the interests of multiple operators. For this reason, this article proposes a swarm intelligence load frequency control (SI-LFC) method. Based on the swarm intelligence method, the proposed method equates the units in each area as independent agents and adopts the swarm intelligence centralized offline learning policy to achieve the balance of interests of different operators. In an online application, each unit only needs to collect the frequency locally to achieve global optimal control, thereby reducing the communication burden across the network. In addition, this article proposes an evolutionary multiagent deep meta-actor-critic (EMA-DMAC) algorithm, which introduces meta-reinforcement learning and evolutionary learning to achieve fast collaborative learning of swarm agents, thereby improving the robustness and quality of the obtained SI-LFC strategies. The effectiveness of the proposed method is demonstrated in a simulation of the four-area LFC model for Sansha island in the China Southern Grid (CSG).
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available