Q-Learning-Based Method for Distribution Layer Partitioning and Grid Planning in Hybrid Centralized-Distributed Networks

doi:10.12096/j.2096-4528.pgt.24005

Abstract

Abstract:

Objectives To improve the research on distribution layer partitioning and grid planning in hybrid centralized-distributed networks, this study fully considers various factors such as the requirements of hybrid centralized-distributed networks and proposes a method for distribution layer partitioning and network planning based on Q-learning. Methods The method addresses issues such as directed and undirected transitions, grid connectivity, and multi-factor classification during the training process. The Reward and Agent are improved based on the different requirements of the two stages: distribution layer partitioning and grid planning. This makes the model more comprehensive by incorporating more elements and is verified through simulations using actual power grid data. Results Compared to traditional grid planning methods, the hybrid centralized-distributed planning scheme using this method provides better economic efficiency while ensuring a certain level of reliability. Conclusions The proposed method demonstrates significant application value in distribution networks with high renewable energy penetration, providing a novel idea and technical approach for the planning and design of hybrid centralized-distributed networks.

Key words: distribution network, hybrid centralized-distributed form, distribution layer partitioning, grid planning, reinforcement learning, agent, machine learning

CLC Number:

TK 01

Wei WANG, Yun XIONG, Pengzhen ZHAO, Ning XIE, Xiang JIN, Zhengyang WANG. Q-Learning-Based Method for Distribution Layer Partitioning and Grid Planning in Hybrid Centralized-Distributed Networks[J]. Power Generation Technology, 2025, 46(5): 977-985.

Figures/Tables 10

References 23

[1]	IPCC ．Special report on global warming of 1.5 ℃[M]．UK：Cambridge University Press，2018：1-32．
[2]	金红洋，申永山，滕云，等．考虑碳减排的多能源系统网格化优化调度方法[J]．可再生能源，2023，41(2)：261-267．
	JIN H Y， SHEN Y S， TENG Y，et al ．Grid-based optimal scheduling method for multi-energy system considering carbon emission reduction[J]．Renewable Energy Resources，2023，41(2)：261-267．
[3]	姚琪，苏川，杨玉静，等．低碳背景下智能电网减排双目标调度规划方法[J]．电网与清洁能源，2024，40(8)：134-140．
	YAO Q， SU C， YANG Y J，et al ．A dual-objective scheduling planning method for smart grid emission reduction under low-carbon background[J]．Power System and Clean Energy，2024，40(8)：134-140．
[4]	刘洪波，刘珅诚，盖雪扬，等．高比例新能源接入的主动配电网规划综述[J]．发电技术，2024，45(1)：151-161． doi:10.12096/j.2096-4528.pgt.22106
	LIU H B， LIU S C， GAI X Y，et al ．Overview of active distribution network planning with high proportion of new energy access[J]．Power Generation Technology，2024，45(1)：151-161． doi:10.12096/j.2096-4528.pgt.22106
[5]	朱建昆，高红均，贺帅佳，等．考虑VSC与光-储-充协同配置的交直流混合配电网规划[J]．智慧电力，2023，51(11)：7-14．
	ZHU J K， GAO H J， HE S J，et al ．AC-DC hybrid distribution network planning considering VSC and photovoltaic-storage-charging coordinated configuration[J]．Smart Power，2023，51(11)：7-14．
[6]	张军达，卢姬，常俊晓，等．考虑可靠性成本的配电网多阶段扩展规划方法[J]．电测与仪表，2023，60(11)：113-122．
	ZHANG J D， LU J， CHANG J X，et al ．Multi-stage expansion planning method for distribution network considering reliability cost[J]．Electrical Measurement & Instrumentation，2023，60(11)：113-122．
[7]	张玉莹，曾博，周吟雨，等．碳减排驱动下的数据中心与配电网交互式集成规划研究[J]．电工技术学报，2023，38(23)：6433-6450．
	ZHANG Y Y， ZENG B， ZHOU Y Y，et al ．Research on interactive integration planning of data centers and distribution network driven by carbon emission reduction[J]．Transactions of China Electrotechnical Society，2023，38(23)：6433-6450．
[8]	巨云涛，周伟鹏，于宗民．考虑移动储能车提升系统供电可靠性的配电网规划方法[J]．电力系统保护与控制，2024，52(17)：128-138．
	JU Y T， ZHOU W P， YU Z M ．A distribution network planning approach considering mobile energy storage vehicles to enhance system power supply reliability[J]．Power System Protection and Control，2024，52(17)：128-138．
[9]	赵鹏臻，徐谦，谢宁，等．基于自主式元胞电网模式的电源及耦合点规划方法[J]．电力自动化设备，2021，41(8)：194-200．
	ZHAO P Z， XU Q， XIE N，et al ．Planning method of power sources and coupling points based on autonomous web-of-cell mode[J]．Electric Power Automation Equipment，2021，41(8)：194-200．
[10]	谢光龙，王旭斌，朱琳，等．蜂巢配电网的构建过程及优势分析[J]．电力系统及其自动化学报，2024，36(2)：11-18．
	XIE G L， WANG X B， ZHU L，et al ．Construction process and advantages of honeycomb distribution network[J]．Proceedings of the CSU-EPSA，2024，36(2)：11-18．
[11]	徐谦，邹波，王蕾，等．呈现集中-分布式形态的耦合协同型配电网架构研究[J]．电力自动化设备，2021，41(6)：81-90．
	XU Q， ZOU B， WANG L，et al ．Research on architecture of coupled collaborative distribution network presenting centralized-distributed pattern[J]．Electric Power Automation Equipment，2021，41(6)：81-90．
[12]	赵鹏臻，谢宁，殷佳敏，等．适应新型电力系统发展趋势的配电网集中-分布式形态及其分层分区方法[J]．智慧电力，2023，51(1)：94-100．
	ZHAO P Z， XIE N， YIN J M，et al ．Centralized-distributed pattern of distribution network and its hierarchical partition method adapting to development trend of new power system[J]．Smart Power，2023，51(1)：94-100．
[13]	金国彬，刘玉龙，李国庆，等．考虑可靠性的交直流混合配电网网架与分布式电源协同优化规划[J]．电力系统保护与控制，2022，50(22)：59-70．
	JIN G B， LIU Y L， LI G Q，et al ．Collaborative optimization planning of an AC/DC hybrid distribution network frame and distributed power generation considering reliability[J]．Power System Protection and Control，2022，50(22)：59-70．
[14]	SU Y， CHAO H， WANG Y，et al ．Planning optimization for the photovoltaic/storage/network system considering photovoltaic consumption level and grid supporting capacity[C]//2022 4th International Conference on Electrical Engineering and Control Technologies．Shanghai，China：CEECT，2022：1059-1063． doi:10.1109/ceect55960.2022.10030354
[15]	ZHANG X， WU J， LI S，et al ．Research on active distribution network structure planning for multi distributed generation access[C]//2020 IEEE 4th Conference on Energy Internet and Energy System Integration (EI2)．Wuhan，China：IEEE，2020：2197-2202． doi:10.1109/ei250167.2020.9347220
[16]	赵辰宇，俞永春，刘明林，等．考虑不确定性风险及结构脆弱性的配电网网架规划[J]．应用科技，2023，50(2)：86-92．
	ZHAO C Y， YU Y C， LIU M L，et al ．A distribution network frame optimization planning considering uncertain risk and structural vulnerability[J]．Applied Science and Technology，2023，50(2)：86-92．
[17]	张鑫，李媛媛，吉平．含高比例可再生能源的交直流混联电网规划方法[J]．全球能源互联网，2021，4(4)：372-381．
	ZHANG X， LI Y Y， JI P ．A planning approach for AC/DC hybrid power grid with high proportion of renewable energy[J]．Journal of Global Energy Interconnection，2021，4(4)：372-381．
[18]	刘洪，滑雪娇，韩柳，等．配电网网架规划与多模块智能终端配置联合优化方法[J]．电力自动化设备，2023，43(1)：41-47．
	LIU H， HUA X J， HAN L，et al ．Joint optimization method of distribution network grid planning and multi-module intelligent terminal configuration[J]．Electric Power Automation Equipment，2023，43(1)：41-47．
[19]	聂文海，方逸航，周毅，等．基于状态变量x0+Δx分解的配电自动化规划研究[J]．供用电，2022，39(3)：25-31．
	NIE W H， FANG Y H， ZHOU Y，et al ．Research on distribution automation planning based on state variables x0+Δx decomposition[J]．Distribution & Utilization，2022，39(3)：25-31．
[20]	杨轩．基于改进遗传算法的配电网网架规划[J]．科技创新与应用，2022，12(15)：64-67．
	YANG X ．Distribution network planning based on improved genetic algorithm[J]．Technology Innovation and Application，2022，12(15)：64-67．
[21]	FENG L， CUI C， MA R，et al ．Deep learning algorithm for preliminary siting of substations considering various features in distribution network planning[J]．IOP Conference Series Earth and Environmental Science，2018，192(1)：012032． doi:10.1088/1755-1315/192/1/012032
[22]	AHMADIAN A， ELKAMEL A， MAZOUZ A ．An improved hybrid particle swarm optimization and tabu search algorithm for expansion planning of large dimension electric distribution network[J]．Energies，2019，12(16)：3052-3061． doi:10.3390/en12163052
[23]	WU K， LI K， LIANG R，et al ．A joint planning method for substations and lines in distribution systems based on the parallel bird swarm algorithm[J]．Energies，2018(10)：2669-2696． doi:10.3390/en11102669

协调层	分布层	负责供电单元	净负荷/MW
协调层1	分布层1-1	A、B、D、E	113.48
	分布层1-2	C、K、L、Q	102.19
	分布层1-3	I、J、M、O、N	95.06
协调层2	分布层2-1	F、G、H	120.94
	分布层2-2	P、X	108.31
	分布层2-3	R、S、T、U、V、W	116.61

协调层	分布层	负责供电单元	净负荷/MW
协调层1	分布层1-1	A、B、D、E	113.48
	分布层1-2	C、K、L、Q	102.19
	分布层1-3	I、J、M、O、N	95.06
协调层2	分布层2-1	F、G、H	120.94
	分布层2-2	P、X	108.31
	分布层2-3	R、S、T、U、V、W	116.61

规划指标	规划结果
可再生能源渗透率/%	70
分布层1-1光伏装机/MW	47.04
分布层1-1风电装机/MW	3.00
分布层1-1燃气轮机装机/MW	4.80
分布层1-2光伏装机/MW	137.20
分布层1-2风电装机/MW	3.00
分布层1-2燃气轮机装机/MW	14.00
分布层1-3光伏装机/MW	125.26
分布层1-3风电装机/MW	3.00
分布层1-3燃气轮机装机/MW	8.00
分布层2-1光伏装机/MW	50.96
分布层2-1风电装机/MW	3.00
分布层2-1燃气轮机装机/MW	5.20
分布层2-2光伏装机/MW	60.76
分布层2-2风电装机/MW	3.00
分布层2-2燃气轮机装机/MW	6.20
分布层2-3光伏装机/MW	124.28
分布层2-3风电装机/MW	3.00
分布层2-3燃气轮机装机/MW	8.60
协调层1储能容量/(MW∙h)	175
协调层2储能容量/(MW∙h)	112.5
可再生能源装机占比/%	92.33
可再生能源发电占比/%	70.04
经济性/亿元	257.31
源荷匹配率(满载)/%	97.16

规划指标	规划结果
可再生能源渗透率/%	70
分布层1-1光伏装机/MW	47.04
分布层1-1风电装机/MW	3.00
分布层1-1燃气轮机装机/MW	4.80
分布层1-2光伏装机/MW	137.20
分布层1-2风电装机/MW	3.00
分布层1-2燃气轮机装机/MW	14.00
分布层1-3光伏装机/MW	125.26
分布层1-3风电装机/MW	3.00
分布层1-3燃气轮机装机/MW	8.00
分布层2-1光伏装机/MW	50.96
分布层2-1风电装机/MW	3.00
分布层2-1燃气轮机装机/MW	5.20
分布层2-2光伏装机/MW	60.76
分布层2-2风电装机/MW	3.00
分布层2-2燃气轮机装机/MW	6.20
分布层2-3光伏装机/MW	124.28
分布层2-3风电装机/MW	3.00
分布层2-3燃气轮机装机/MW	8.60
协调层1储能容量/(MW∙h)	175
协调层2储能容量/(MW∙h)	112.5
可再生能源装机占比/%	92.33
可再生能源发电占比/%	70.04
经济性/亿元	257.31
源荷匹配率(满载)/%	97.16

参数	集中—分布式形态方案	传统方案
可再生能源渗透率/%	70	0
源荷匹配率(满载)/%	97.16	100.00
源荷匹配率(半载)/%	100.00	100.00
变电站平均负载率/%	60.79	59.01
经济性/亿元	257.31	303.76