Citation

Mir, MD Nazmul Hossain and Biswas, Arindam Kishor and Bhuiyan, Md Shariful Alam and Abir, Md. Golam Rabbani and Mridha, M. F. and Hossen, Md. Jakir (2025) ABMF-Net: An Attentive Bayesian Multi-Stage Deep Learning Model for Robust Forecasting of Electricity Price and Demand. IEEE Open Journal of the Computer Society. pp. 1-12. ISSN 2644-1268

Text 5.pdf - Published Version Restricted to Repository staff only Download (687kB)

Abstract

This paper presents a novel deep learning model, the Attentive Bayesian Multi-Stage Forecasting Network (ABMF-Net), designed for robust forecasting of electricity price (USD/MWh) and demand (MW). The model incorporates an attention-based data selection mechanism, an encoder-decoder structure with masked time-series prediction, and a Bayesian neural network to generate both point and interval forecasts. Furthermore, a multi-objective Salp Swarm Algorithm (MSSA) is used to optimize forecasting accuracy and stability. Experimental evaluation on four real-world datasets from the Australian electricity market demonstrates that ABMF-Net achieves a MAPE as low as 1.89%, MAE of 0.67, RMSE of 0.98, and FICP of 0.98, outperforming LSTM, GRU, and Transformer models. Seasonal evaluations confirm the model's robustness across high-variability conditions. These results position ABMF-Net as a high-performing and reliable forecasting model for modern electricity markets.

Item Type:	Article
Uncontrolled Keywords:	Electricity Forecasting, Deep Learning, Attention Mechanism, Bayesian Neural Network, Interval Forecasting, Multi-Objective Optimization, Self-Supervised Learning, Time-Series Analysis, Uncertainty Quantification
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK452-454.4 Electric apparatus and materials. Electric circuits. Electric networks
Divisions:	Faculty of Engineering and Technology (FET)
Depositing User:	Ms Suzilawati Abu Samah
Date Deposited:	26 Jun 2025 06:38
Last Modified:	26 Jun 2025 06:38
URII:	http://shdl.mmu.edu.my/id/eprint/14094

Downloads

Edit (login required)