Open access
Jul 2026
A Multi-Scale Convolutional Neural Network with Residual Blocks and LSTM for Multi-Step Forecasting of Electricity Load
Experimental results show that MSCNN-ResLSTM achieves higher forecasting accuracy and greater stability across the full 24-step prediction horizon, consistently outperforming all competing baselines while effectively suppressing recursive error propagation.
Yu-Hang Zhang, Yi-Ting Zhao, Yu-Jing Meng et al.
· De Computis · 0 citations