Novel Adjustable Potential Assessing Method of Customer Loads Based on the Clustering Algorithm of Electricity Consumption Patterns

Tapping the regulation resources on the “load” side, upgrading the traditional source-load movement to source-load interaction, and improving the regulation capability of the power system are the new and important way to ensure the safe and economic operation of the new power system. This paper proposes a method for assessing the adjustable potential of users based on the clustering algorithm of power usage patterns. Firstly, the regularity of user electricity consumption and the classification method of electricity consumption pattern are studied. The abnormal data is excluded from the original data of user load. And the KNN algorithm is utilized to compensate the load data to ensure the integrity of the data. Secondly, the K-Means big data analysis algorithm is proposed to get the typical electricity consumption pattern of users. Thirdly, the baseline load on the regulation day is classified based on the affiliation function. Finally, based on the feasibility of the conversion of different power usage patterns, the calculated average error between the most likely regulation power of users and the actual value provides adjustable power data support for flexible load aggregation regulation.