24-Hour Load Forecasting For Anomalous Weather Days Using Hourly Temperature

Abstract

Short-term load forecasting is essential to the electricity pricing and stable power system operations. The conventional weekday 24hour load forecasting algorithms consider the temperature model to forecast maximum load and minimum load. But 24hour load pattern forecasting models do not consider temperature effects, because hourly temperature forecasts were not present until the latest date. Recently, 3 hour temperature forecast is announced, therefore hourly temperature forecasts can be produced by mathematical techniques such as various interpolation methods. In this paper, a new 24hour load pattern forecasting method is proposed by using similar day search considering the hourly temperature. The proposed method searches similar day input data based on the anomalous weather features such as continuous temperature drop or rise, which can enhance 24hour load pattern forecasting performance, because it uses the past days having similar hourly temperature features as input data. In order to verify the effectiveness of the proposed method, it was applied to the case study. The case study results show high accuracy of 24-hour load pattern forecasting.