Forecasting of Ship Power Load based on EMD-GA-LSTM Algorithm

This paper analyzed the characteristics of ship power load forecasting. Aiming at the shortcomings of traditional load forecasting, such as low accuracy and poor adaptability to working conditions, an improved EMD-GA-LSTM power load estimation algorithm was proposed. Through the combination of data preprocessing module, self-learning module and error feedback module, the advantages of different algorithms can be brought into play. The numerical results showed that the EMDGA-LSTM algorithm can improve the effect and forecasting accuracy of ship power load model forecasting.