A Short-term Electricity Load Forecasting Method Based on WOA-BiLSTM-Attention

Abstract Under the “double carbon” policy, it is time to build a new green and safe power system. Special attention should be paid low accuracy in short-term load prediction. Therefore, this paper presents technique for anticipating demand based on bidirectional long memory network with whale-optimized mechanism (WOA-BiLSTM-Attention), which used forecast analyze measured values certain area. The experimental findings reveal that suggested has much greater prediction convergence speed, as well superior stability, when compared LSTM, BiLSTM, BiLSTM mechanism, making good reference system planning stability.