基于TD3算法的含分布式光伏综合负荷模型参数在线辨识

尹雁和; 钟毅; 贺怡; 李国号; 李卓环; 潘世贤

doi:10.19912/j.0254-0096.tynxb.2024-0464

PDF(2340 KB)

太阳能学报 ›› 2025, Vol. 46 ›› Issue (7) : 710-719. DOI: 10.19912/j.0254-0096.tynxb.2024-0464

第二十七届中国科协年会学术论文

基于TD3算法的含分布式光伏综合负荷模型参数在线辨识

尹雁和¹, 钟毅¹, 贺怡¹, 李国号¹, 李卓环², 潘世贤²

作者信息 +

ON-LINE PARAMETER IDENTIFICATION OF COMPOSITE LOAD MODEL WITH DISTRIBUTED PHOTOVOLTAIC BASED ON TD3 ALGORITHM

Yin Yanhe¹, Zhong Yi¹, He Yi¹, Li Guohao¹, Li Zhuohuan², Pan Shixian²

Author information +

文章历史 +

摘要

针对当前辨识方法依赖于系统大扰动下的暂态数据、无法满足新型电力系统在线分析需求的问题,提出一种基于深度强化学习TD3算法的含分布式光伏综合负荷模型参数在线辨识方法。从机理层面对模型简化,并在随机小干扰下计算参数的全局灵敏度,筛选出对模型动态特性影响较大的可辨参数;利用模型不同参数在系统小干扰下的动态响应差异,采用深度强化学习TD3算法辨识模型参数,构造算法与仿真系统之间的接口函数,并设计能使算法满足多场景辨识需求的训练方案;最后,在PSASP中EPRI-36节点算例的多种随机小干扰场景下验证所提方法的可行性。

Abstract

Focusing on the problem that the current identification methods rely on the transient data under the large disturbance of the system, which cannot meet the online analysis requirements of the new power system, an online parameter estimation method for distributed photovoltaic composite load model based on deep reinforcement learning algorithm TD3 is proposed in this paper. The model is simplified based on the mechanism, and the global sensitivity of the parameters is calculated under random small disturbance, based on which the discernible parameters that have great influence on the dynamic characteristics of load model are selected. Using the difference between dynamic response with different parameters under small disturbance, the TD3 algorithm is used to identify the model parameters, the interface function between the algorithm and the simulation system is constructed, and the training scheme that can make the algorithm meet the needs of multi-scene identification is designed. Finally, the feasibility of the proposed method is verified in various random small disturbance scenarios based on EPRI-36 node system in PSASP.

导出引用

尹雁和, 钟毅, 贺怡, 李国号, 李卓环, 潘世贤. 基于TD3算法的含分布式光伏综合负荷模型参数在线辨识[J]. 太阳能学报. 2025, 46(7): 710-719 https://doi.org/10.19912/j.0254-0096.tynxb.2024-0464

Yin Yanhe, Zhong Yi, He Yi, Li Guohao, Li Zhuohuan, Pan Shixian. ON-LINE PARAMETER IDENTIFICATION OF COMPOSITE LOAD MODEL WITH DISTRIBUTED PHOTOVOLTAIC BASED ON TD3 ALGORITHM[J]. Acta Energiae Solaris Sinica. 2025, 46(7): 710-719 https://doi.org/10.19912/j.0254-0096.tynxb.2024-0464

中图分类号： TM71

参考文献

[1] 王国春, 许洪强, 冯长有, 等. 新一代在线安全分析技术架构及未来展望[J]. 电力系统自动化, 2023, 47(24): 110-120.
WANG G C, XU H Q, FENG C Y, et al.Technical architecture and future prospect for new generation of online security analysis[J]. Automation of electric power systems, 2023, 47(24): 110-120.
[2] 舒印彪, 张智刚, 郭剑波, 等. 新能源消纳关键因素分析及解决措施研究[J]. 中国电机工程学报, 2017, 37(1): 1-9.
SHU Y B, ZHANG Z G, GUO J B, et al.Study on key factors and solution of renewable energy accommodation[J]. Proceedings of the CSEE, 2017, 37(1): 1-9.
[3] 李亚楼, 张星, 胡善华, 等. 含高比例电力电子装备电力系统安全稳定分析建模仿真技术[J]. 电力系统自动化, 2022, 46(10): 33-42.
LI Y L, ZHANG X, HU S H, et al.Modeling and simulation technology for stability analysis of power system with high proportion of power electronics[J]. Automation of electric power systems, 2022, 46(10): 33-42.
[4] 陈国平, 李明节, 许涛, 等. 关于新能源发展的技术瓶颈研究[J]. 中国电机工程学报, 2017, 37(1): 20-27.
CHEN G P, LI M J, XU T, et al.Study on technical bottleneck of new energy development[J]. Proceedings of the CSEE, 2017, 37(1): 20-27.
[5] 马亚辉, 李欣然, 曹一家, 等. 含逆变型分布式电源的综合负荷建模[J]. 太阳能学报, 2015, 36(8): 1869-1875.
MA Y H, LI X R, CAO Y J, et al.Composite load modeling of distribution network with inverter-based distributed generation[J]. Acta energiae solaris sinica, 2015, 36(8): 1869-1875.
[6] 屈星, 李欣然. 考虑配电网结构的电力系统综合负荷建模[J]. 电力系统自动化, 2020, 44(12): 117-123.
QU X, LI X R.Synthesis load modeling of power system considering distribution network structure[J]. Automation of electric power systems, 2020, 44(12): 117-123.
[7] 鞠平, 郭德正, 曹路, 等. 含主动负荷的综合电力负荷建模研究综述与展望[J]. 河海大学学报(自然科学版), 2020, 48(4): 367-376.
JU P, GUO D Z, CAO L, et al.Review and prospect of modeling on generalized synthesis electric load containing active loads[J]. Journal of Hohai University(natural sciences), 2020, 48(4): 367-376.
[8] 董坤, 赵剑锋, 孙睿晨, 等. 含新型负荷元件的电力负荷建模方法研究现状与展望[J]. 电力系统自动化, 2023, 47(23): 70-83.
DONG K, ZHAO J F, SUN R C, et al.Research status and prospects of modeling methods for power loads with new load elements[J]. Automation of electric power systems, 2023, 47(23): 70-83.
[9] ARIF A, WANG Z Y, WANG J H, et al.Load modeling: a review[J]. IEEE transactions on smart grid, 2018, 9(6): 5986-5999.
[10] LIU Q S, CHEN Y P, DUAN D F.The load modeling and parameters identification for voltage stability analysis[C]//Proceedings of International Conference on Power System Technology. Kunming, China, 2002: 2030-2033.
[11] 徐岩, 靳伟佳, 朱晓荣. 基于遗传粒子群算法的光伏并网逆变器参数辨识[J]. 太阳能学报, 2021, 42(7): 103-109.
XU Y, JIN W J, ZHU X R.Parameter identification of photovoltaic grid-connected inverter based on GAPSO[J]. Acta energiae solaris sinica, 2021, 42(7): 103-109.
[12] 盛四清, 关皓闻, 雷业涛, 等. 基于混沌海鸥优化算法的含光伏发电系统负荷模型参数辨识[J]. 太阳能学报, 2022, 43(7): 64-72.
SHENG S Q, GUAN H W, LEI Y T, et al.Parameter identification of load model of photovoltaic power generation system based on chaotic seagull optimization algorithm[J]. Acta energiae solaris sinica, 2022, 43(7): 64-72.
[13] MA J, DONG Z Y, ZHANG P.Using a support vector machine (SVM) to improve generalization ability of load model parameters[C]//2009 IEEE/PES Power Systems Conference and Exposition, Seattle, WA, USA, 2009: 1-8.
[14] LEE S H, SON S E, LEE S M, et al.Kalman-filter based static load modeling of real power system using K-EMS data[J]. Journal of electrical engineering and technology, 2012, 7(3): 304-311.
[15] HU J X, WANG Q, YE Y J, et al.Toward online power system model identification: a deep reinforcement learning approach[J]. IEEE transactions on power systems, 2023, 38(3): 2580-2593.
[16] BU F, MA Z, YUAN Y, et al.WECC composite load model parameter identification using evolutionary deep reinforcement learning[J]. IEEE transactions on smart grid, 2020, 11(6): 5407-5417.
[17] 朱亮亮. 基于负荷模型在线修正的交直流电网频率控制技术[D]. 南京: 东南大学, 2018.
ZHU L L.Frequency control technology of AC/DC power system based on online load modeling[D]. Nanjing: Southeast University, 2018.
[18] ZHANG K Q, ZHU H, GUO S M.Dependency analysis and improved parameter estimation for dynamic composite load modeling[J]. IEEE transactions on power systems, 2017, 32(4): 3287-3297.
[19] 马亚辉. 含分布式电源的综合负荷建模方法研究[D]. 长沙: 湖南大学, 2013.
MA Y H.Studies on composite load modeling of distribution network considering distributed generation[D]. Changsha: Hunan University, 2013.