Article: Modelling and predicting energy consumption patterns using generative adversarial networks for effective carbon management Journal: International Journal of Information and Communication Technology (IJICT) 2026 Vol.27 No.92 pp.79 - 110 Abstract: Effective carbon management requires accurate prediction of energy consumption patterns, yet conventional models struggle with complex temporal dependencies. This study proposes a novel integrated framework combining transformer-based generative adversarial networks with Bayesian optimisation (BO-TransGAN) for energy forecasting and carbon optimisation. Using 2,000 hourly records of energy use and emissions, data were pre-processed via imputation, outlier removal, and normalisation. The TransGAN captures nonlinear temporal dependencies through adversarial learning, while Bobcat optimisation tunes hyperparameters for enhanced convergence and stability. BO-TransGAN achieves 0.987 accuracy, 0.995 R<SUP align="right"><SMALL>2</SMALL></SUP>, minimal losses, and low training (2.12s) and run times (7.35s). It generates realistic synthetic sequences and provides actionable insights for reducing carbon emissions, offering a scalable tool for sustainable energy planning and real-time carbon management. Inderscience Publishers - linking academia, business and industry through research

Title: Modelling and predicting energy consumption patterns using generative adversarial networks for effective carbon management

Authors: Yongting Liu; Baotong Li

Addresses: State Grid Xinjiang Electric Power Co., Ltd., Urumqi, 830000, No. 68, Nanhu East Road, Shuimogou District, Urumqi, Xinjiang, China ' State Grid Xinjiang Electric Power Co., Ltd., Urumqi, 830000, No. 68, Nanhu East Road, Shuimogou District, Urumqi, Xinjiang, China

Abstract: Effective carbon management requires accurate prediction of energy consumption patterns, yet conventional models struggle with complex temporal dependencies. This study proposes a novel integrated framework combining transformer-based generative adversarial networks with Bayesian optimisation (BO-TransGAN) for energy forecasting and carbon optimisation. Using 2,000 hourly records of energy use and emissions, data were pre-processed via imputation, outlier removal, and normalisation. The TransGAN captures nonlinear temporal dependencies through adversarial learning, while Bobcat optimisation tunes hyperparameters for enhanced convergence and stability. BO-TransGAN achieves 0.987 accuracy, 0.995 R², minimal losses, and low training (2.12s) and run times (7.35s). It generates realistic synthetic sequences and provides actionable insights for reducing carbon emissions, offering a scalable tool for sustainable energy planning and real-time carbon management.

Keywords: carbon management; generative adversarial networks; GANs; energy consumption prediction; sustainable energy planning; energy-carbon pattern modelling.

DOI: 10.1504/IJICT.2026.155939

International Journal of Information and Communication Technology, 2026 Vol.27 No.92, pp.79 - 110

Received: 01 Mar 2026
Accepted: 18 May 2026
Published online: 26 Aug 2026 *

Title: Modelling and predicting energy consumption patterns using generative adversarial networks for effective carbon management

Keep up-to-date