AUTHOR=Gao Zhiping , Kang Wenwen , Chen Xinghua , Gong Siru , Liu Zongxiong , He Degang , Shi Shen , Shangguan Xing-Chen 

TITLE=Optimal economic dispatch of a virtual power plant based on gated recurrent unit proximal policy optimization

JOURNAL=Frontiers in Energy Research

VOLUME=Volume 12 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2024.1357406

DOI=10.3389/fenrg.2024.1357406

ISSN=2296-598X

ABSTRACT=The intermittent renewable energy in virtual power plant (VPP) brings generation uncertainties, which prevents the VPP from providing a reliable and friendly power supply. This paper proposes a gated recurrent unit proximal policy optimization (GRUPPO) based optimal VPP economic dispatch. Firstly, electrical generation, storage, and consumption are established to form a VPP framework by considering the accessibility of VPP state information. The optimal VPP economic dispatch can then be expressed as a partially observable Markov decision process (POMDP) problem. A novel deep reinforcement learning method, called GRUPPO is further developed based on VPP time series characteristics. Finally, cased studies are conducted with 24-hour based on the actual historical data. The tested results illustrate that the proposed economic dispatch can achieve at most 6.5% operation cost reduction and effectively smooth the uncertain supply-demand