A new financial loss/gain wind power forecasting method based on deep machine learning algorithm by using energy storage system

Abstract Nowadays, with the development of the global economy, traditional non‐renewable energy resources can not only meet the increasing energy demand but also bring severe ecological and environmental problems. Wind power, as one of the most economical types of renewable energies source, has become one of the essential resources for clean energy production. Because of the randomness, intermittency, and fluctuation of natural wind, the output power of wind turbines is greatly affected by wind uncertainty. Therefore, wind power generation forecasting and scheduling may be challenging. In this paper, for the successful and accurate presence of wind power producers in the electricity energy market, a method based on forecasting wind power production, the electricity price, and Financial Loss/Gain (FLG) in coordination with energy storage is proposed. To predict the electricity price, wind power production, and FLG for the next 24 h, the hybrid method based on deep learning time series prediction based on the LSTMs method and input selection based on the MRMI method has been used. For this purpose, first, based on historical data, the wind power producer forecasts the electricity price and wind power production for the next 24 h. According to the same predicted values, initial offers are set for participation in the day‐ahead electricity market. After that, wind power producers modify their wind power production based on the FLG prediction method. Since the FLG signal has highly volatile behaviour, therefore it is not efficient to forecast and apply it directly to the proposed wind power production offers. Therefore, classifying FLG by the FCM method and predicting the FLG class labels is much more helpful in improving the proposed bid of wind power producers to the electricity market. Finally, the wind power producer can improve its profit from participating in the electricity market by interacting with the energy storage unit. The presented numerical results demonstrate the efficiency of the proposed method. For example, if the initial offers are modified based on the FLG method, it has caused the expected profit to improve by 4.44–27.69% in the desired months of the year 2018. Also, in three months, the total profit of the wind power producer and energy storage will be higher than if the profit of the wind power producer participates in the day‐ahead market with 100% accuracy.