The LV substation short-term load forecasting is of great significance for achieving management of the distribution Internet of Things. In order to alleviate the communication pressure caused by uploading load data from all substations, this paper proposes a short-term substation load forecasting method based on edge computing. By using the 30-day historical load data stored by the intelligent distribution terminal as sample data, the sample data is cleaned using Nadaraya-Watson method. Due to the small amount of sample data, it is considered to normalize the sample and split it into standard unit curves and base value. Then, PCC matrix of historical load data is constructed, and the unit curve of similar days is obtained through AP clustering, and the unit curve of the test day is obtained through weighted summation. At the same time, forecast the base value of the test day and ultimately obtain the load curve of the test day. The result show that the proposed method can achieve reasonable prediction, and it occupies less computing resources in the main station. It has a positive significance for the operation and maintenance of the distribution network.
