TY - JOUR
T1 - A deep reinforcement learning algorithm for the power order optimization allocation of AGC in interconnected power grids
AU - Xi, Lei
AU - Zhou, Lipeng
AU - Liu, Lang
AU - Duan, Dongliang
AU - Xu, Yanchun
AU - Yang, Liuqing
AU - Wang, Shouxiang
N1 - Publisher Copyright:
© 2015 CSEE.
PY - 2020/9
Y1 - 2020/9
N2 - The integration of distributed generations (solar power, wind power), energy storage devices, and electric vehicles, causes unpredictable disturbances in power grids. It has become a top priority to coordinate the distributed generations, loads, and energy storages in order to better facilitate the utilization of new energy. Therefore, a novel algorithm based on deep reinforcement learning, namely the deep PDWoLF-PHC (policy dynamics based win or learn fast-policy hill climbing) network (DPDPN), is proposed to allocate power order among the various generators. The proposed algorithm combines the decision mechanism of reinforcement learning with the prediction mechanism of a deep neural network to obtain the optimal coordinated control for the source-grid-load. Consequently it solves the problem brought by stochastic disturbances and improves the utilization rate of new energy. Simulations are conducted with the case of the improved IEEE two-area and a case in the Guangdong power grid. Results show that the adaptability and control performance of the power system are improved using the proposed algorithm as compared with using other existing strategies.
AB - The integration of distributed generations (solar power, wind power), energy storage devices, and electric vehicles, causes unpredictable disturbances in power grids. It has become a top priority to coordinate the distributed generations, loads, and energy storages in order to better facilitate the utilization of new energy. Therefore, a novel algorithm based on deep reinforcement learning, namely the deep PDWoLF-PHC (policy dynamics based win or learn fast-policy hill climbing) network (DPDPN), is proposed to allocate power order among the various generators. The proposed algorithm combines the decision mechanism of reinforcement learning with the prediction mechanism of a deep neural network to obtain the optimal coordinated control for the source-grid-load. Consequently it solves the problem brought by stochastic disturbances and improves the utilization rate of new energy. Simulations are conducted with the case of the improved IEEE two-area and a case in the Guangdong power grid. Results show that the adaptability and control performance of the power system are improved using the proposed algorithm as compared with using other existing strategies.
KW - Automatic generation control
KW - DPDPN
KW - deep reinforcement learning
KW - power order allocation
UR - http://www.scopus.com/inward/record.url?scp=85091629273&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85091629273&partnerID=8YFLogxK
U2 - 10.17775/CSEEJPES.2019.01840
DO - 10.17775/CSEEJPES.2019.01840
M3 - Article
AN - SCOPUS:85091629273
SN - 2096-0042
VL - 6
SP - 712
EP - 723
JO - CSEE Journal of Power and Energy Systems
JF - CSEE Journal of Power and Energy Systems
IS - 3
M1 - 9056999
ER -