One day-ahead load forecasting by artificial neural network

摘要

In this paper, a method based on “artificial neural network” is proposed for electric load prediction.The prediction of load for the next hour to several days out so-called short term load forecasting is one of the most important requirements for the operation and planning activities of an electrical utility. Presented method in this paper is the development of an artificial neural network based short-term load forecasting model. The model can forecast daily load profiles with a load time of one day for the next 24 h. Days of year with using average temperature are divided in this method. In addition, groups are divided according to the linearity rate of curve. Then, with considering weekday and weekend, the ultimate forecast load is obtained for each group. Moreover, an investigation is made on the effects of temperature and humidity on consuming curve. The results indicates the forecasting load curve of holidays at first forecast pick and valley and then the neural networkforecast is re-shaped with the newdata. The ANN-based load models are trained using hourly historical, load data and daily historical max/min temperature and humidity data.The results of testing the system on data from Yazd utility are reported.