An Aggregation Strategy of Flexible Industrial Load Based on K-Means Clustering

In response to the “carbon peaking and carbon neutrality” goals, the energy structure in China has undergone a great transformation. Construction of the new power system has begun. The proportion of renewable generation has increased gradually. However, the operation and scheduling of the power system are influenced by the increasing renewable generation. This paper develops a multi-timescale flexible industrial load aggregation response method based on the K-means clustering analysis. First, the K-means method is used to cluster the daily load curves of different industries to obtain the typical electricity consumption behaviors. Second, the visual models of flexible industrial load are established based on the results of clustering analysis. Finally, the optimization model is constructed to generate the aggregation strategy in different timescales. The effectiveness of the developed method is verified via a load aggregator simulation case.