Ensemble learning unlocking point load forecasting accuracy: A novel framework based on two-stage data preprocessing and improved multi-objective optimisation strategy

Abstract

Accurate point power forecasts are critical for maintaining the security and stability of the grid. However, Load data is volatile and difficult to predict with high accuracy. To improve the stability and accuracy of the model, we proposed a novel hybrid load forecasting framework consisting of three modules. Firstly, we used Successive Variational Mode Decomposition (SVMD) in the data preprocessing module to extract trend features and denoise the data. To reduce the negative impact of feature redundancy on model predictions, we employed feature selection to identify four essential features to aid model training. Secondly, in the ensemble learning module, we address the limitations of single predictive models by combining the models Back Propagation (BP), Temporal Convolutional Network (TCN), Bidirectional Long Short-Term Memory (BiLSTM), Bidirectional Gated Recurrent Unit (BiGRU) and Transformer. Finally, in the improved multi-objective optimisation algorithm module, we implemented various strategies to enhance the optimisation algorithm. We designed some experiments using three load datasets from Australia. The results demonstrated that the mean absolute percentage error values are below 1.25%, with the best value reaching 0.9256%. In contrast, the best result for the mean absolute percentage error of the baseline models was 1.4431% in New South Wales. This represents a 35.9% improvement in load forecasting performance with our proposed model, highlighting its superior accuracy compared to competing approaches. It shows that our forecasting framework is far better than other rivals.