面向新型配电系统的光伏充电站负荷预测方法研究

庞欢; 何思源; 郑子东; 王雯靓; 曹楠; 王宇蛟

庞欢,何思源,郑子东,王雯靓,曹楠,王宇蛟.面向新型配电系统的光伏充电站负荷预测方法研究[J].电测与仪表,2026,63(4):152-162.
Pang huan,He siyuan,Zheng zidong,Wang wenliang,Cao nan,Wang yujiao.Research on load forecasting method of photovoltaic charging station for new distribution system[J].Electrical Measurement & Instrumentation,2026,63(4):152-162.

面向新型配电系统的光伏充电站负荷预测方法研究

Research on load forecasting method of photovoltaic charging station for new distribution system

DOI：10.19753/j.issn1001-1390.2026.04.016

中文关键词: 新型电力系统光伏充电站分位数回归多层极限学习机区间预测

英文关键词:New power system, photovoltaic charging station, quantile regression, multilayer extreme learning machine, interval prediction

基金项目:国家电网公司科技资助项目（2023YF-138）

作者中文名	作者英文名	单位
庞欢	Pang huan	国网辽宁省电力有限公司阜新供电公司
何思源	He siyuan	国网辽宁省电力有限公司阜新供电公司
郑子东	Zheng zidong	国网辽宁省电力有限公司阜新供电公司
王雯靓	Wang wenliang	国网辽宁省电力有限公司阜新供电公司
曹楠	Cao nan	国网辽宁省电力有限公司阜新供电公司
王宇蛟	Wang yujiao	沈阳工程学院

摘要点击次数: 5

中文摘要:

在新型配电系统中，光伏充电站作为一种典型分布式资源聚合形态备受关注。由于分布式光伏发电与充电负荷都具有随机性、波动性等特点，光伏充电站负荷预测任务显得尤为复杂。本文考虑到光伏充电站接入对地区负荷曲线的动态影响，提出了一种基于多层极限学习机与分位数回归理论的光伏充电站负荷预测方法。文章首先对影响光伏充电站负荷的因素进行特征提取，提取关键特征量，其次结合分位数回归算法，构建多层核极限学习机深度神经网络模型，实现不同置信度水平下的光伏充电站负荷区间预测，并采用改进麻雀优化算法进行参数寻优，选择最优的模型进行负荷预测。最后，选取北方某地某光伏充电站的负荷数据进行算例分析。结果表明，本文提出的面向新型配电系统的光伏充电站负荷预测方法有较好的预测效果，可以更加精准的掌握负荷的预测信息。

英文摘要:

In the new power distribution system, PV charging stations have attracted much attention as a typical distributed resource aggregation form. Since both distributed PV generation and charging loads are characterized by randomness and volatility, the load forecasting task of PV charging stations is particularly complex. In this paper, considering the dynamic impact of PV charging station access on the regional load profile, a PV charging station load forecasting method based on multilayer limit learning machine and quantile regression theory is proposed. In the article, firstly, the factors affecting the load of PV charging station are feature extracted and key feature quantities are extracted, secondly, combined with the quantile regression algorithm, a multilayer kernel limit learning machine deep neural network model is constructed to realize the load interval prediction of PV charging station under different confidence levels, and the improved sparrow optimization algorithm is used for the parameter optimization and the optimal model is selected for the load prediction. Finally, the load data of a photovoltaic charging station in a place in the north is selected for example analysis. The results show that the PV charging station load prediction method proposed in this paper for the new distribution system has a better prediction effect and can grasp the load prediction information more accurately.

查看全文查看/发表评论下载PDF阅读器

关闭