Review of Load Forecasting Based on Artificial Intelligence Models

Accurate load forecasting can efficiently reduce the day-ahead dispatch stress of power system or microgrid. The overview of load forecasting based on artificial intelligence models are comprehensively summarized in this paper. As the steps of load forecasting based on artificial intelligence model mainly include data preprocessing and model forecasting, the paper firstly reviewed the data preprocessing studied. According to the kinds of data obtained, the data can be classified into two categories: multivariate time series and single variate time series. Secondly the paper reviewed second step of load forecasting: the artificial intelligence models. According to the artificial intelligence model, it can be classified into machine learning model and deep learning model. The measurement index used in the evaluation model can be divided into dimensional index and non dimensional index. Finally, the combination model is often used as a method to further improve the prediction accuracy, which mainly includes two methods: combining by weight addition and combining by machine learning. The future trend on load forecasting researches is given in the end.