A New Generation Efficient Testing Method for Substation Protection Based on Cloud-based DDPG Optimization and Collaboration

doi:10.11930/j.issn.1004-9649.202408072

Abstract

Abstract:

Aiming at the new generation of substation, a protection efficiency testing method is proposed. Based on the new generation of substation system, the architecture of protection system based on cloud data optimization and coordination is designed, the self-adaptive test instrument is designed, and its information flow transmission relationship with cloud coordination is analyzed. Further the method of minimum unit decomposition based on sub-module test is proposed, the conversion time of switching process is analyzed, the sub-module test sequence optimization problem is characterized as a decision-making process, the mathematical model of protection test is established, and the optimal sub-module test sequence is solved based on deep deterministic policy gradient (DDPG) algorithm The proposed method helps to improve the intelligence level of relay protection test.

Key words: new generation substation, protection device, efficient testing

YE Yuanbo, WANG Jiwen, SUN Zhenxing, ZHOU Kun, MAO Yurong. A New Generation Efficient Testing Method for Substation Protection Based on Cloud-based DDPG Optimization and Collaboration[J]. Electric Power, 2025, 58(6): 90-96.

Add to citation manager EndNote|Ris|BibTeX

URL: https://www.electricpower.com.cn/EN/10.11930/j.issn.1004-9649.202408072

https://www.electricpower.com.cn/EN/Y2025/V58/I6/90

Figures/Tables 9

References 31

1	刘清泉, 杨鹏, 李铁成, 等. 应对继电保护多场景的数字仿真测试方法[J]. 中国电力, 2025, 58 (2): 118- 125. DOI
	LIU Qingquan, YANG Peng, LI Tiecheng, et al. Digital simulation test method for multiple scenarios relay protection[J]. Electric Power, 2025, 58 (2): 118- 125. DOI
2	计荣荣, 王梦芝, 周国伟, 等. 基于云端优化的智能变电站二次系统快速测试建模与系统设计[J]. 中国电力, 2025, 58 (5): 152- 157. DOI
	JI Rongrong, WANG Mengzhi, ZHOU Guowei, et al. Cloud-based optimized intelligent substation secondary system rapid test model and system design[J]. Electric Power, 2025, 58 (5): 152- 157. DOI
3	金国锋, 杨世峰, 刘玲玲, 等. 基于二维混沌映射正余弦算法的智能变电站虚回路自动连接技术[J]. 中国电力, 2024, 57 (8): 152- 158. DOI
	JIN Guofeng, YANG Shifeng, LIU Lingling, et al. Automatic connection of virtual circuits in smart substations based on chaotic two-dimensional mapping sine and cosine algorithm[J]. Electric Power, 2024, 57 (8): 152- 158. DOI
4	刘涛, 李伟华, 汤熠. 综合智慧能源系统典型构架网络安全防护研究[J]. 综合智慧能源, 2024, 46 (5): 81- 90. DOI
	LIU Tao, LI Weihua, TANG Yi. Security protection of typical networks for integrated smart energy systems[J]. Integrated Intelligent Energy, 2024, 46 (5): 81- 90. DOI
5	杨超, 伏晓燕. 智能变电站继电保护设备全防误状态监测技术研究[J]. 电网与清洁能源, 2023, 39 (7): 73- 79. DOI
	YANG Chao, FU Xiaoyan. Research on the full error prevention state monitoring technology of relay protection equipment in intelligent substations[J]. Power System and Clean Energy, 2023, 39 (7): 73- 79. DOI
6	计荣荣, 张淦锋, 王梦芝, 等. 基于数据驱动的智能变电站信息高效校验技术[J]. 中国电力, 2025, 58 (1): 100- 106. DOI
	JI Rongrong, ZHANG Ganfeng, WANG Mengzhi, et al. Data-driven efficient verification technique for smart substations messages[J]. Electric Power, 2025, 58 (1): 100- 106. DOI
7	耿治, 张建忠, 陈昊. 智能变电站保护装置自动测试系统分析与设计[J]. 电力系统保护与控制, 2017, 45 (11): 121- 125. DOI
	GENG Zhi, ZHANG Jianzhong, CHEN Hao. Research and design of automatic test system for protection device in intelligent substation[J]. Power System Protection and Control, 2017, 45 (11): 121- 125. DOI
8	加依达尔·金格斯, 谭金龙, 南东亮, 等. 数字化智能变电站继电保护装置自动测试系统研究[J]. 电工技术, 2021, (22): 116- 119, 122.
	JAYDAR·Jingus, TAN Jinlong, NAN Dongliang, et al. Research on automatic test system of relay protection device in digital intelligent substation[J]. Electric Engineering, 2021, (22): 116- 119, 122.
9	姜涵, 毛新飞. 智能变电站继电保护装置的自动测试系统设计[J]. 电子技术, 2023, 52 (7): 278- 279.
	JIANG Han, MAO Xinfei. Design of automatic testing system for relay protection devices in intelligent substation[J]. Electronic Technology, 2023, 52 (7): 278- 279.
10	陈飞建, 吕元双, 樊国盛, 等. 基于信息融合的智能变电站继电保护设备自动测试系统[J]. 电力系统保护与控制, 2020, 48 (5): 158- 163.
	CHEN Feijian, LÜ Yuanshuang, FAN Guosheng, et al. Automatic test system of relay protection device for smart substation based on information fusion technology[J]. Power System Protection and Control, 2020, 48 (5): 158- 163.
11	李涵, 宋宇, 楚皓翔. 基于故障录波回放的智能变电站保护测试技术研究[J]. 电气技术, 2021, 22 (12): 78- 83, 89. DOI
	LI Han, SONG Yu, CHU Haoxiang. Research on intelligent substation protection test technology based on fault recording and playback[J]. Electrical Engineering, 2021, 22 (12): 78- 83, 89. DOI
12	陈桂芳, 董秀成, 郑永康, 等. 基于长短期记忆网络的继电保护测试故障诊断研究[J]. 电力系统保护与控制, 2022, 50 (5): 65- 73.
	CHEN Guifang, DONG Xiucheng, ZHENG Yongkang, et al. Fault diagnosis of a relay protection test based on a long short-term memory network[J]. Power System Protection and Control, 2022, 50 (5): 65- 73.
13	刘亮, 王刘伟, 亢瑞瑞. 智能变电站继电保护装置自动测试系统研究和应用[J]. 电工材料, 2024, (3): 41- 44.
	LIU Liang, WANG Liuwei, KANG Ruirui. Research and application of automatic test system of relay protection device in intelligent substation[J]. Electrical Engineering Materials, 2024, (3): 41- 44.
14	冉一丁, 孙晓雷, 李智诚, 等. 基于继电保护装置定值校验仪的定值校核研究[J]. 电气技术与经济, 2024, (3): 32- 35. DOI
15	余洋, 陆文韬, 刘霡, 等. 考虑复杂出行链基于双链马尔科夫的电动汽车负荷建模方法[J]. 电网与清洁能源, 2024, 40 (1): 109- 118. DOI
	YU Yang, LU Wentao, LIU Mai, et al. A load modeling method for electric vehicles based on double chain Markov considering complex travel chains[J]. Power System and Clean Energy, 2024, 40 (1): 109- 118. DOI
16	肖白, 李梦雪, 尉博旭. 基于AP聚类-跳转持续MC的风电出力时间序列模拟生成方法研究[J]. 东北电力大学学报, 2023, 43 (1): 35- 44.
	XIAO Bai;LI Mengxue;WEI Boxu. Research on simulation method to generate wind power output time series based on AP clustering-transition and persistence Markov chain[J]. Journal of Northeast Electric Power University, 2023, 43 (1): 35- 44.
17	陈潇潇, 周云海, 张泰源, 等. 基于深度强化学习的有源配电网实时电压控制策略[J]. 三峡大学学报(自然科学版), 2024, 46 (1): 76- 84.
	CHEN Xiaoxiao, ZHOU Yunhai, ZHANG Taiyuan, et al. Strategy of real-time voltage control in active distribution network based on deep reinforcement learning[J]. Journal of China Three Gorges University (Natural Sciences), 2024, 46 (1): 76- 84.
18	YOUNES S, IDI M, ROBBANA R. Discrete-time Markov decision process for performance analysis of virtual machine allocation schemes in C-RAN[J]. Journal of Network and Computer Applications, 2024, 225, 103859. DOI
19	ZHANG L Y, PENG Y, YANG W H, et al. Semi-infinitely constrained Markov decision processes and provably efficient reinforcement learning[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46 (5): 3722- 3735. DOI
20	刘航, 申皓, 杨勇, 等. 基于高阶马尔可夫链的纯电重卡集群负荷预测[J]. 中国电力, 2024, 57 (5): 61- 69. DOI
	LIU Hang, SHEN Hao, YANG Yong, et al. Load forecast of electric trucks aggregation based on higher-order Markov chains[J]. Electric Power, 2024, 57 (5): 61- 69. DOI
21	李付强, 张文朝, 潘艳, 等. 基于改进深度确定性策略梯度算法的电压无功优化策略[J]. 智慧电力, 2024, 52 (5): 1- 7, 30. DOI
	LI Fuqiang, ZHANG Wenchao, PAN Yan, et al. Reactive voltage optimization strategy based on improved depth deterministic strategy gradient algorithm[J]. Smart Power, 2024, 52 (5): 1- 7, 30. DOI
22	李宏浩, 张沛, 刘曌. 基于深度强化学习的暂态稳定紧急控制决策方法[J]. 电力系统自动化, 2023, 47 (5): 144- 152. DOI
	LI Honghao, ZHANG Pei, LIU Zhao. Decision-making method for transient stability emergency control based on deep reinforcement learning[J]. Automation of Electric Power Systems, 2023, 47 (5): 144- 152. DOI
23	杜婉琳, 王玲, 罗威, 等. 基于深度强化学习的有源配电网电压分层控制策略[J]. 发电技术, 2024, 45 (4): 734- 743. DOI
	DU Wanlin, WANG Ling, LUO Wei, et al. Voltage hierarchical control strategy of active distribution network based on deep reinforcement learning[J]. Power Generation Technology, 2024, 45 (4): 734- 743. DOI
24	李建标, 陈建福, 高滢, 等. 基于RG-DDPG的直流微网能量管理策略[J]. 中国电力, 2023, 56 (7): 85- 94. DOI
	LI Jianbiao, CHEN Jianfu, GAO Ying, et al. Strategy for DC microgrid energy management based on RG-DDPG[J]. Electric Power, 2023, 56 (7): 85- 94. DOI
25	黄堃, 付明, 梁加本. 基于融合专家知识DDPG的孤岛微电网频率调节策略[J]. 中国电力, 2024, 57 (2): 194- 201. DOI
	HUANG Kun, FU Ming, LIANG Jiaben. Frequency regulation strategy of isolated island microgrid based on fusion expert knowledge DDPG[J]. Electric Power, 2024, 57 (2): 194- 201. DOI
26	TANG X L, YANG Y Y, LIU T, et al. Path planning and tracking control for parking via soft actor-critic under non-ideal scenarios[J]. IEEE/CAA Journal of Automatica Sinica, 2024, 11 (1): 181- 195. DOI
27	DENG T B, HUANG H, FANG Y W, et al. Reinforcement learning-based missile terminal guidance of maneuvering targets with decoys[J]. Chinese Journal of Aeronautics, 2023, 36 (12): 309- 324. DOI
28	陈池瑶, 苗世洪, 姚福星, 等. 基于多智能体算法的多微电网-配电网分层协同调度策略[J]. 电力系统自动化, 2023, 47 (10): 57- 65. DOI
	CHEN Chiyao, MIAO Shihong, YAO Fuxing, et al. Hierarchical cooperative dispatching strategy of multi-microgrid and distribution networks based on multi-agent algorithm[J]. Automation of Electric Power Systems, 2023, 47 (10): 57- 65. DOI
29	周雪松, 张心茹, 赵浛宇, 等. 基于DDPG算法的微网负载端接口变换器自抗扰控制[J]. 电力系统保护与控制, 2023, 51 (21): 66- 75.
	ZHOU Xuesong, ZHANG Xinru, ZHAO Hanyu, et al. Active disturbance rejection control of a microgrid load-side interface converter based on a DDPG algorithm[J]. Power System Protection and Control, 2023, 51 (21): 66- 75.
30	刘建行, 刘方. 基于深度强化学习的梯级水蓄风光互补系统优化调度策略研究[J]. 广东电力, 2024, 37 (5): 10- 22. DOI
	LIU Jianhang, LIU Fang. Research on optimized dispatching strategy of cascade hydropower-pumping-storage-wind-photovoltaic multi-energy complementary system based on deep reinforcement learning[J]. Guangdong Electric Power, 2024, 37 (5): 10- 22. DOI
31	苏向敬, 邓超, 栗风永, 等. 基于MGAT-TCN模型的可解释电网虚假数据注入攻击检测方法[J]. 电力系统自动化, 2024, 48 (2): 118- 127. DOI
	SU Xiangjing, DENG Chao, LI Fengyong, et al. Interpretable detection method for false data injection attack on power grid based on multi-head graph attention network and time convolution network model[J]. Automation of Electric Power Systems, 2024, 48 (2): 118- 127. DOI

求解方法	求解时间/ms
求解方法	中位数	均值	方差
PSO	814.6	826.7	7.19×10^–3
TD3	5.6	5.8	5.34×10^–5
DE	783.2	793.4	4.38×10^–4
DDPG	4.1	4.9	4.12×10^–5

求解方法	求解时间/ms
求解方法	中位数	均值	方差
PSO	814.6	826.7	7.19×10^–3
TD3	5.6	5.8	5.34×10^–5
DE	783.2	793.4	4.38×10^–4
DDPG	4.1	4.9	4.12×10^–5

训练参数		数值
价值网络学习率		0.001
策略网络学习率		0.0001
折扣因子		0.98
经验数据集大小		1000000
噪声方差		0.3
软更新率		0.01

训练参数		数值
价值网络学习率		0.001
策略网络学习率		0.0001
折扣因子		0.98
经验数据集大小		1000000
噪声方差		0.3
软更新率		0.01

方法	改进优点	仍存在的不足	测试效率
文献[7-8]	不需要模拟式继电保护检测仪，可自动实现保护二次系统的检测，硬件要求低	无法适用于电磁式电流互感器构成的模拟式测量回路	较低
文献[9]	测试流程采用模板技术根据模板生成测试报告，测试流程得到优化	测试模版不全面，同时导入测试仪的过程较为复杂，且难以及时更正测试过程中改变的施加信息	一般
文献[10]	引入信息融合技术自动更改测试参数，自动化程度提高	针对不同保护装置、不同保护原理需要测试时仍需要辅助大量的人力去完成检测	一般
文献[11]	采用故障录波文件回放的检测方式代替较常规动/静模检测实验，且验证性平台需求低	现场录波文件很难覆盖不同工况的综合性验证，推广应用程度较低	较高
文献[12]	利用长短期记忆网络数据驱动方法实现继电保护测试与故障诊断，有效提高测试效率和测试准确度	没有考虑到测试顺序的进一步优化，整套测试效率仍存在较大提升空间	较高
本文所提方法	基于云端数据优化能力与协同工作机制，应用深度确定性策略梯度算法求解最优测试序列，大幅度提升测试效率	尚未推广	高