The research of grid short-term load forecasting considering with air quality index

The relationship between the air quality index (AQI) level and power load variation is analyzed, the method of load forecasting considering with AQI is proposed. First, the load can be classified by the cluster analysis, then the corresponding relationship between each type of load and AQI levels is analyzed, the variation of the load before and after the precautionary measures is also analyzed. In this paper, a weighted similarity and weighted support vector machine algorithm is proposed to address the short-term power load forecasting model based on the analysis of the influence of AQI level to load. The factors including weeks, weather, the highest temperature and the lowest temperature and AQI level are considered in this model. And the similar days are chose by the weighted similarity method. That the similarity is selected as the weight coefficient has solved the problem of the differences in sample data, in addition. Therefore, the accuracy of load forecasting is improved.