Recurrent neural network for forecasting next 10 years loads of 9 Japanese utilities

In this paper, a recurrent neural network (RNN) is applied for long-term load forecasting. The proposed RNN is trained with the past 20 years (1975-1994) of actual data and is tested for target years (1995-1997, 2000, and 2005). In addition to the target year load forecasting, a sliding window training method is proposed for continuous retraining of the RNN. The actual data of 9 Japanese power utilities is used for forecasting the loads of 1975 to 1994. However, forecasted data is applied for forecasting the loads beyond 1994. Since the weather condition data is not available for longer than two weeks ahead, a sensitivity program is developed to produce the future temperature from the present one. Very reasonable results have been obtained for the seen (inner sample) and unseen (out-of-sample or loads of target years) data. In this study, total system load forecast reflecting current and future trends, tempered with good judgment which is the key to all planning, indeed financial success is carried out for 9 power utilities in Japan. The obtained results of this study will be useful for other country's utilities.