电工电气杂志社

基于SSA-DELM配电网光伏发电接纳能力研究

来源：电工电气发布时间：2025-01-07 15:07 浏览次数：13

基于SSA-DELM配电网光伏发电接纳能力研究

杨群力¹，苏乐²，顾晨²，周鹏²，潘学萍²

(1 江苏省战略与发展研究中心，江苏南京 210036；

2 河海大学能源与电气学院，江苏南京 211100)

摘要：针对配电网拓扑以及参数难以获取，数学建模方法无法应用于实际分析的困难，提出基于深度极限学习机(DELM)网络的配电网光伏发电接纳能力数据驱动分析方法。对配电网潮流分析数学模型与 DELM 网络计算流程的相似性进行了对比，阐述了采用 DELM 网络进行配电网数据建模的可行性；提出采用麻雀搜索算法(SSA)对 DELM 网络进行优化，来提升 DELM 网络的建模精度；给出了节点功率-节点电压的非机理建模策略，并据此外推配电网对单点或多点接入下的光伏发电接纳能力。基于系统仿真及某实际低压配电网，研究了电压安全约束下配电网对光伏发电的接纳能力，验证了所提算法的有效性和优越性。

关键词： 配电网；电压安全；光伏发电接纳能力；麻雀搜索算法；深度极限学习机；电压灵敏度

中图分类号：TM615 ；TM711 文献标识码：A 文章编号：1007-3175(2024)12-0034-08

Research on Photovoltaic Power Generation Acceptance Capacity of

Distribution Network Based on SSA-DELM

YANG Qun-li¹, SU Le², GU Chen², ZHOU Peng², PAN Xue-ping²

（1 Jiangsu Strategy and Development Research Center, Nanjing 210036, China;

2 College of Energy and Electrical Engineering, Hohai University, Nanjing 211100, China）

Abstract: With the difficulty of attaining topology and parameters of distribution network, mathematical modeling methods can not be applied to practical analysis difficulties. Therefore, a data-driven analysis method for analyzing the acceptance capacity of the distribution network for photovoltaic (PV) power is proposed based on deep extreme learning machine(DELM) network. Firstly, the similarity between the mathematical model of power flow analysis of distribution network and the calculation process of DELM network is compared, and the feasibility of using DELM network for distribution network data modeling is expounded. Then the sparrow search algorithm (SSA) is proposed to optimize the DELM network to improve the data modeling accuracy by the DELM network. A non-mechanistic modeling strategy of node power-node voltage is given and based on this, the acceptance capacity of the distribution grid for PV power generation under single-point or multi-point access is deduced. Based on the system simulation and an actual low-voltage distribution network, the acceptance capacity of the distribution network for photovoltaic power generation under the constraint of voltage safety is studied, and the effectiveness and superiority of the proposed algorithm are verified.

Key words: distribution network; voltage safety; photovoltaic power acceptance capacity; sparrow search algorithm; deep extreme learning machine; voltage sensitivity

参考文献

[1] 高志远，张晶，庄卫金，等. 关于新型电力系统部分特点的思考[J]. 电力自动化设备，2023，43(6) ：137-143.

[2] 杜晓东，赵建利，刘科研，等. 基于数字孪生的光伏高比例配电网过载风险预警方法[J]. 电力系统保护与控制，2022，50(9) ：136-144.

[3] HOKE A, BUTLER R, HAMBRICK J, et al.Steady-state analysis of maximum photovoltaic penetration levels on typical distribution feeders[J].IEEE Transactions on Sustainable Energy，2013，4(2) ：350-357.

[4] AYRES H M, FREITAS W, DE ALMEIDA M C, et al.Method for determining the maximum allowable penetration level of distributed generation without steady-state voltage violations[J].IET Generation, Transmission & Distribution，2010，4(4) ：495-508.

[5] AL-SAADI H , ZIVANOVIC R , AL-SARAWI S F.Probabilistic hosting capacity for active distribution networks[J].IEEE Transactions on Industrial Informatics，2017，13(5) ：2519-2532.

[6] MOHAMMAD S S A , MA J , ZHANG D , et al .Probabilistic assessment of hosting capacity in radial distribution systems[J].IEEE Transactions on Sustainable Energy，2018，9(4) ：1935-1947.

[7] 薛禹胜，赖业宁. 大能源思维与大数据思维的融合：(一) 大数据与电力大数据[J] . 电力系统自动化，2016，40(1) ：1-8.

[8] 黄蔓云，卫志农，孙国强，等. 数据挖掘在配电网态势感知中的应用：模型、算法和挑战[J]. 中国电机工程学报，2022，42(18) ：6588-6598.

[9] 巨云涛，杨明友，吴文传. 适用于配电网三相优化潮流的数据物理融合驱动线性化方法[J]. 电力系统自动化，2022，46(13) ：43-52.

[10] WENG Y, LIAO Y, RAJAGOPAL R.Distributed energy resources topology identification via graphical modeling[J].IEEE Transactions on Power Systems，2017，32(4) ：2682-2694.

[11] United States Energy Information Administration.How many smart meters are installed in the United States, and who has them?[EB/OL].(2023-10-20)[2024-10-28].https://www.eia.gov/tools/faqs/faq.php?id=108&t=3.

[12] European Commission.Smart Metering Deployment in the European Union[EB/OL].(2023-10-24)[2024-10-28].http://ses.jrc.ec.europa.eu/smart-meteringdeployment-european-union.

[13] YU J, WENG Y, RAJAGOPAL R.Robust mapping rule estimation for power flow analysis in distribution grids[C]//North American Power Symposium(NAPS)，2017.

[14] PERTL M, HEUSSEN K, GEHRKE O, et al.Voltage estimation in active distribution grids using neural networks[C]//IEEE Power and Energy Society General Meeting(PESGM)，2016.

[15] MICHAEL P, PHILIP J D, KAI H, et al.Validation of a robust neural real-time voltage estimator for active distribution grids on field data[J].Electric Power Systems Research，2018，154(8)：182-192.

[16] IMEN L, DJAMEL L.Power flow variation based on extreme learning machine algorithm in power system[J].International Journal of Power Electronics and Drive Systems，2019，10(3) ：1244.

[17] BAGHAEE H R, MIRSALIM M, GHAREHPETIAN G B.Power calculation using RBF neural networks to improve power sharing of hierarchical control scheme in multi-DER microgrids[J].IEEE Journal of Emerging and Selected Topics in Power Electronics，2016，4(4) ：1217-1225.

[18] YANG Y, YANG Z F, YU J, et al.Fast calculation of probabilistic power flow: A model-based deep learning approach[J].IEEE Transactions on Smart Grid，2020，11(3) ：2235-2244.

[19] 张天策，王剑晓，李庚银，等. 面向高比例新能源接入的配电网电压时空分布感知方法[J]. 电力系统自动化，2021，45(2) ：37-45.

[20] 曾亮，雷舒敏，王珊珊，等. 基于 OVMD-SSA-DELM-GM 模型的超短期风电功率预测方法[J] . 电网技术，2021，45(12) ：4701-4710.

[21] 杨淑霞，韩奇，徐琳茜，等. 基于鱼群算法优化 BP 神经网络的电力客户满意度综合评价方法[J] . 电网技术，2011，35(5) ：146-151.

[22] 梁恩豪，孙军伟，王延峰. 基于自适应樽海鞘算法优化 BP 的风光互补并网发电功率预测[J] . 电力系统保护与控制，2021，49(24) ：114-120.

[23] 张甲甲，万定生. 基于混合 GA 优化 LSTM 的中小流域流量预测研究[J]. 计算机仿真，2022，39(2) ：283-287.

[24] 薛建凯. 一种新型的群智能优化技术的研究与应用[D].上海：东华大学，2020.

[25] 麻秀范. 含分布式电源的配电网规划与优化运行研究[D].北京：华北电力大学，2013.

返回索引列表

Article retrieval

文章检索

基于SSA-DELM配电网光伏发电接纳能力研究