Study on Short Term Load Forecast based on Cloud Model

Abstract

At present, electric load forecasting method and model are all point forecasting to the load, the paper proposes a method of short-term load forecasting using the cloud model which represents the artificial intelligence with uncertainty. The forecasting results are many discrete data sets which are uncertain and change in some range, so they can represent the changing characteristic of electric load more actually. In the paper, the author firstly introduces the conception and characteristic of cloud model and gives the process of data discretization and conception zooming for the load data and the weather factors based on cloud model. Then the paper carries on the mining and inference of uncertainty rules using the associated knowledge algorithm based on cloud model (Cloud-Association- Rules), and finally uses the data of some area as the forecasting analysis example, gives two kinds of results expression which are the forecasting sets distribution chart and the excepted values graphic chart. The forecasting results can meet the practical standard of electric load forecasting.