基于数据驱动的低感知度配电网动态无功优化
Dynamic Reactive Power Optimization of Low Perception Distribution Networks Based on Data-driven Approach
徐晓春 1卜强生 2俞婧雯 3赵娜 1王涛 1窦晓波3
作者信息
- 1. 国网江苏省电力有限公司淮安供电分公司,江苏淮安 223001
- 2. 国网江苏省电力公司电力科学研究院,江苏南京 210000
- 3. 东南大学电气工程学院,江苏南京 210096
- 折叠
摘要
由于配电网网络通信基础设施较差,且节点监控覆盖不完全,因此存在无法实时采集数据的节点,导致无法进行传统无功优化.为此,提出了一种数据驱动的低感知度配电网动态无功优化方法.通过K-means算法聚类节点历史负荷,对非实时观测节点依据特征分类;选择最优超参数基于时间卷积网络进行量测数据补全;最终通过改进后的社交网络搜索算法实现动态无功优化,并仿真验证了方法的有效性.
Abstract
Due to poor communication infrastructure in the distribution network and incomplete node monitoring coverage,there are nodes that cannot collect data in real-time,resulting in the inability to perform traditional reactive power optimization.To this end,a data-driven low perception dynamic reactive power optimization method for distribution networks was proposed.Cluster node historical loads using K-means algorithm,and classify non real-time observation nodes based on features;the optimal hyper parameters were selected to complete the measurement data based on the time convolution network;finally,the improved social network search algorithm was used to achieve dynamic reactive power optimization,and the effectiveness of the method was verified through simulation.
关键词
时间卷积网络/社交网络搜索算法/K-means算法/动态无功优化/数据驱动Key words
temporal convolutional network/social network search algorithm/K-means algorithm/dynamic reactive power optimization/data driven引用本文复制引用
基金项目
国家电网江苏省电力公司科技项目(J2021036)
出版年
2024
NETL
NSTL
万方数据