An Improved Self-Organizing Migration Algorithm for Short-Term Load Forecasting with LSTM Structure Optimization

<div>The changes of LSTM hyperparameters converge with AS-SOMA. (a) The change process of time step. (b) The change process of learning rate. (c) The change process of epochs. (d) The change process of batch size.</div>

Mathematical Problems in Engineering

fig14

Figure 14

Figure 14: An Improved Self-Organizing Migration Algorithm for Short-Term Load Forecasting with LSTM Structure Optimization 