What does this research mean for the field?

A hybrid forecasting framework combining Variational Mode Decomposition, Singular Entropy, Convolutional Neural Networks, and Bayesian Optimization significantly improves short-term electricity load forecasting accuracy over standard deep learning models. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

This research aims to improve short-term load forecasting accuracy using a hybrid model that combines various advanced techniques.

May 19, 2026Open Access

A Hybrid Variational Mode Decomposition- Singular Entropy- Convolutional Neural Network - Bayesian Optimization Approach for Short-Term Load Forecasting

Puntos clave

This research aims to improve short-term load forecasting accuracy using a hybrid model that combines various advanced techniques.
Developed a hybrid framework using Variational Mode Decomposition, Singular Entropy, and Convolutional Neural Network with Bayesian Optimization.
Applied the model to half-hourly electricity load data from New South Wales and Victoria, Australia.
Measured performance using Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE).
Achieved lowest MAPE of 1.17% in Victoria and 2.31% in New South Wales.
Outperformed baseline models including LSTM, BI-LSTM, and traditional CNN approaches in accuracy.
Verified statistical significance of improvements through Wilcoxon signed-rank and Friedman tests.

Resumen

• Propose a hybrid VMD–SingEn–CNN–BO for short-term load forecasting. • VMD denoises; SingEn recalibrates; CNN learns; BO optimizes hyperparameters. • Achieves lowest MAE, MSE, RMSE, MAPE on VI and NSW datasets. • Outperforms LSTM, BI-LSTM, CNN, VMD-CNN baselines in accuracy. • Discusses accuracy–computation trade-off and offers tuning guidelines. Short-term load forecasting remains challenging because electricity demand is often noisy and nonstationary. This study proposes a hybrid VMD–SingEn–CNN–BO framework, in which Variational Mode Decomposition decomposes the load signal, Singular Entropy removes uninformative modes, and a compact convolutional neural network predicts the retained components. Bayesian optimization jointly tunes the decomposition, selection, and network hyperparameters. Experiments on half-hourly electricity load data from New South Wales and Victoria, Australia, from May 2009 to May 2014 show that the proposed model achieves the lowest MAPE among the compared baselines, reaching 1.17% and 2.31%, respectively. The statistical significance of the obtained improvements is further verified using the Wilcoxon signed-rank and the Friedman tests. The accuracy improvement comes at the expense of longer offline optimization time, while online forecasting remains efficient.

Leer artículo completoexternamente

Me gusta

Guardar

Ver artículo completo