基于改进K-means算法的源荷匹配电网优化分区

Optimal Partitioning of Source-Load Matching Power Grid Based on Improved K-Means Algorithm

针对电网分区问题中基于经验的启发式方法的局限性,考虑分区问题中的新能源和负荷之间的匹配特性,建立电网优化分区的衡量指标;基于源荷匹配度,通过求解各区域的源荷匹配度系数,实现对电网进行优化分区;在传统K-means算法中引入误差平方和,筛选最佳聚类数值,规避聚类模型对分析结果的不利影响。算例采用某地区6座500 kV变电站运行数据,分析并计算了各主变压器下的源荷匹配度系数,并根据系数对该区域电网进行分区。结果表明,所提算法能有效均衡分区之间的短路能力,明显提升在整体聚类上的效果。

In view of the limitations of the heuristic method based on experience in the power grid partitioning problem,considering the matching characteristics between the new energy and the load in the power grid partitioning problem,the measurement index of the power grid optimal partitioning is established.Based on the source-load matching degree,theoptimal partitioning of power grid is realized by solving the source-load matching degree coefficients of each region.In the traditional K-means algorithm,the sum of error squares is introduced to screen the best clustering value to avoid the adverse impact of the clustering model on the analysis results.The calculation example uses the operation data of six 500 kV substations in a area to analyze and calculate the source-load matching coefficient under each main transformer.According to the coefficient,the power grid is partitioned.The results show that the proposed algorithm can effectively balance the short circuit capacity between partitions.The improved algorithm has significantly improved the overall clustering effect.