Search

Abstract: In daily power markets, forecasting electricity prices and loads are the most essential task and the basis for any decision making. An approach to predict the market behaviors is to use the historical prices, loads and other required information to forecast the future prices and loads. This paper introduces an approach for several hour ahead (1–6h) electricity price and load forecasting using an artificial intelligence method, such as a neural network model, which uses publicly available data from the NEMMCO web site to forecast electricity prices and loads for the Victorian electricity market. An approach of selection of similar days is proposed according to which the load and price curves are forecasted by using the information of the days being similar to that of the forecast day. A Euclidean norm with weighted factors is used for the selection of the similar days. Two different ANN models, one for one to six hour ahead load forecasting and another for one to six hour ahead price forecasting have been proposed. The MAPE (mean absolute percentage error) results show a clear increasing trend with the increase in hour ahead load and price forecasting. The sample average of MAPEs for one hour ahead price forecasts is 9.75%. This figure increases to only 20.03% for six hour ahead predictions. Similarly, the one to six hour ahead load forecast errors (MAPE) range from 0.56% to 1.30% only. MAPE results show that several hour ahead electricity prices and loads in the deregulated Victorian market can be forecasted with reasonable accuracy. [Copyright &y& Elsevier]

Abstract: This paper presents a practical method for short-term load forecast problem using artificial neural network (ANN) combined similar days approach. Neural networks applied in traditional prediction methods all use similar days data to learn the trend of similarity. However, learning all similar days data is a complex task, and does not suit the training of neural network. A Euclidean norm with weighted factors is used to evaluate the similarity between the forecast day and searched previous days. According to similar days approach, load curve is forecasted by using information of the days that are similar to weather condition of the forecast day. An accuracy of the proposed method is enhanced by the addition of temperature as a major climate factor, and special attention was paid to model accurately in different seasons, i.e. Summer, Winter, Spring, and Autumn. The one-to-six hour-ahead forecast errors (MAPE) range from 0.98 to 2.43%. Maximum and minimum percentage errors, and MAPE values obtained from the load forecasting results confirm that ANN-based proposed method provides reliable forecasts for several-hour-ahead load forecasting. [Copyright &y& Elsevier]