AGC Power Generation Command Allocation Method Based on Improved Deep Deterministic Policy Gradient Algorithm

被引：0
|
作者：
Li J. [1 ]
Yu T. [1 ]
Zhang X. [2 ]
Zhu H. [1 ]
机构：
[1] College of Electric Power, South China University of Technology, Guangzhou
[2] School of Engineering, Shantou University, Shantou
来源：
Zhongguo Dianji Gongcheng Xuebao/Proceedings of the Chinese Society of Electrical Engineering | 2021年 / 41卷 / 21期
基金：
中国国家自然科学基金;
关键词：
AGC; Deep reinforcement learning; Dynamic allocation of generation power command; Frequency regulation market; Regulation mileage;
D O I：
10.13334/j.0258-8013.pcsee.201253
中图分类号：
学科分类号：
摘要：
An optimization model for an AGC generation power command allocation algorithm of the comprehensive energy system was built in the environment of a frequency regulation ancillary services market in this paper. AGC generation power command allocation was dynamically optimized to reduce area control deviation and regulation mileage payments. The experience pools in the twin delayed deep deterministic policy gradient were categorized by using the multiple experience pool probability experience replay twin delayed deep deterministic policy gradient (ME-TD3) algorithm. Samples from different experience pools were used for training by using different probabilities, and training efficiency as well as the optimum-seeking correctness rate for intelligent agents was improved, and therefore the quality of the optimal solution was improved. Finally, the two-area load frequency control model and the power grid model of a certain province were used to verify the performance of the proposed algorithm. © 2021 Chin. Soc. for Elec. Eng.
引用
收藏
页码：7198 / 7211
页数：13
相关论文
共 21 条
  • [1] XI Lei, CHEN Jianfeng, HUANG Yuehua, Et al., Smart generation control based on multi-agent reinforcement learning with the idea of the time tunnel, Energy, 153, pp. 977-987, (2018)
  • [2] ZHANG Xiaoshun, YU Tao, YANG Bo, Et al., Virtual generation tribe based robust collaborative consensus algorithm for dynamic generation command dispatch optimization of smart grid, Energy, 101, pp. 34-51, (2016)
  • [3] LAKSHMANAN V, MARINELLI M, HU Junjie, Et al., Provision of secondary frequency control via demand response activation on thermostatically controlled loads: Solutions and experiences from Denmark, Applied Energy, 173, pp. 470-480, (2016)
  • [4] DOHERTY R, MULLANE A, NOLAN G, Et al., An assessment of the impact of wind generation on system frequency control, IEEE Transactions on Power Systems, 25, 1, pp. 452-460, (2010)
  • [5] ZHANG Xiaoshun, XU Zhao, YU Tao, Et al., Optimal mileage based AGC dispatch of a Genco, IEEE Transactions on Power Systems, 35, 4, pp. 2516-2526, (2020)
  • [6] PAPALEXOPOULOS A D, ANDRIANESIS P E., Performance-based pricing of frequency regulation in electricity markets, IEEE Transactions on Power Systems, 29, 1, pp. 441-449, (2014)
  • [7] XU Bolun, SHI Yuanyuan, KIRSCHEN D S, Et al., Optimal battery participation in frequency regulation markets, IEEE Transactions on Power Systems, 33, 6, pp. 6715-6725, (2018)
  • [8] YU Xichang, ZHOU Quanren, Practical implementation of the SCADA+AGC/EDC system of the Hunan power pool in the central China power network, IEEE Transactions on Energy Conversion, 9, 2, pp. 250-255, (1994)
  • [9] SADEGHI-MOBARAKEH A, MOHSENIAN-RAD H., Optimal bidding in performance-based regulation markets: an MPEC analysis with system dynamics, IEEE Transactions on Power Systems, 32, 2, pp. 1282-1292, (2017)
  • [10] WANG Zhongwei, ZHONG Jin, LI Jianhui, Design of performance-based frequency regulation market and its implementations in real-time operation, International Journal of Electrical Power & Energy Systems, 87, pp. 187-197, (2017)
123