Deep Convolutional Neural Network Model for Short-Term Electricity Price Forecasting
This provides more accurate price forecasts for electricity producers and traders in the competitive power market, but it is incremental as it adapts an existing method to a specific domain.
The paper tackled short-term electricity price forecasting by proposing a novel convolutional neural network (CNN) method that divides annual data into seasonal categories for training, achieving a mean absolute percentage error (MAPE) of about 5.5% and root mean square error (RMSE) of about 3.
In the modern power market, electricity trading is an extremely competitive industry. More accurate price forecast is crucial to help electricity producers and traders make better decisions. In this paper, a novel method of convolutional neural network (CNN) is proposed to rapidly provide hourly forecasting in the energy market. To improve prediction accuracy, we divide the annual electricity price data into four categories by seasons and conduct training and forecasting for each category respectively. By comparing the proposed method with other existing methods, we find that the proposed model has achieved outstanding results, the mean absolute percentage error (MAPE) and root mean square error (RMSE) for each category are about 5.5% and 3, respectively.