CEEMDAN-QPSO-LSTM-based Short-term Electric Load Forecasting
In order to achieve high-precision short-term electric load forecasting,a new method combining complete en-semble empirical mode decomposition with adaptive noise (CEEMDAN),quantum particle swarm optimization (QPSO) and long short-term memory (LSTM)was proposed by this work.The algorithm was designed to first processed the data into several modal components through CEEMDAN,and then used the QPS-based modified LSTM for prediction to su-perimpose reconstructed output results.The proposed method was domenstrated by experimen to achieve higher prediction accuracy and better fitting effect than other algorithms.
万方数据
维普
