Journal of Artificial Intelligence and Metaheuristics
Journal DOI
2833-5597ISSN (Online)
Volume 11 , Issue 1 , PP: 01-28, 2026 | Cite this article as | XML | Html | PDF | Full Length Article
Wei Hong Lim 1 * , Amel Ali Alhussan 2
Doi: https://doi.org/10.54216/JAIM.110101
Accurate prediction of electricity consumption is a critical requirement for improving operational efficiency, enhancing grid reliability, and supporting sustainability objectives in urban power distribution systems, particularly in regions experiencing steady population growth and increasing demand pressure. Motivated by the limitations of conventional statistical and physics-inspired forecasting approaches, as well as the strong sensitivity of deep learning architectures to hyperparameter configuration, t his s tudy p roposes a robust data-driven framework that integrates deep learning with advanced metaheuristic optimization for high-precision short-term electricity consumption forecasting. The main contribution of this work lies in the systematic development and evaluation of hybrid metaheuristic–Bidirectional Long Short-Term Memory (BiLSTM) models, in which multiple state-of-the-art optimization algorithms are employed to tune model hyperparameters. Particular emphasis is placed on the integration of the Ninja Optimization Algorithm with BiLSTM (NijOA + BiLSTM), which is designed to effectively navigate complex, high-dimensional hyperparameter search spaces encountered in deep learning–based load forecasting tasks. Baseline experiments demonstrate that BiLSTM outperforms other deep learning models, including Artificial Neural Network (ANN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU), achieving a baseline Root Mean Squared Error (RMSE) of 0.0964 and a coefficient of determination (R2) of 0.854. These results confirm t he a dvantage o f b idirectional t emporal l earning in capturing the nonlinear and time-dependent characteristics of electricity consumption recorded at high temporal resolution from SCADA systems. Following metaheuristic optimization, the NijOA + BiLSTMmodel delivers a substantial improvement in predictive performance. The optimized configuration reduces RMSE to 0.0038, Mean Squared Error (MSE) to 1.45 × 10−5, and Mean Absolute Error (MAE) to 0.00019, while increasing the correlation strength to r = 0.973 and the explanatory power to R2 = 0.97. Comparative analysis across different optimization strategies further confirms t he s uperiority o f t he NijOA + BiLSTM hybrid model over alternative configurations, including WAO + BiLSTM, BBO + BiLSTM, GA + BiLSTM, SFS + BiLSTM, DE + BiLSTM, and JAYA + BiLSTM. The implications of these findings are significant for real-world urban electricity distribution applications. The proposed framework enables highly accurate and reliable short-term electricity consumption forecasting, making it well suited for deployment within smart grid and distribution management systems. Such predictive capability can support informed operational decision-making, improve demand-side management strategies, reduce uncertainty in short-term planning, and contribute to the long-term sustainability and resilience of urban power distribution networks.
Short-term electricity consumption forecasting , Deep learning , BiLSTM , Metaheuristic optimization , SCADA data
[1] Q. Hassan et al., “The renewable energy role in the global energy transformations,” Renewable Energy Focus, vol. 48, p. 100 545, 2024, ISSN: 1755-0084. DOI: https://doi.org/10.1016/j. ref.2024.100545. [Online]. Available: https://www.sciencedirect.com/science/ article/pii/S1755008424000097.
[2] A. Sharma, S. N. Singh, M. M. Serratos, D. Sahu, and V. Strezov, “Urban energy transition in smart cities: A comprehensive review of sustainability and innovation,” Sustainable Futures, vol. 10, p. 100 940, 2025, ISSN: 2666-1888. DOI: https://doi.org/10.1016/j.sftr.2025. 100940. [Online]. Available: https://www.sciencedirect.com/science/article/ pii/S2666188825005052.
[3] H. Ahmad, M. Yaqub, and S. H. Lee, “Global trends in carbon neutrality: A scientometric review on energy transition challenges, practices, policies, and opportunities,” Environment, Development and Sustainability, pp. 1–26, 2025. DOI: https://doi.org/10.1007/s10668-025-06507-7.
[4] J. Wei, Y. Wu, and M. K. Anser, “Unpacking the drivers of sustainable development: A quantile-based analysis of digitalization, resource efficiency, and economic diversification,” Environment, Developmentand Sustainability, pp. 1–28, 2025. DOI: https://doi.org/10.1007/s10668-025-06751- x.
[5] A. Teshome Mossisa and A. T. Han, “Transitioning to renewable electric energy in rapidly urbanizing sub-saharan africa: Challenges and opportunities,” Energy Strategy Reviews, vol. 61, p. 101 842, 2025, ISSN: 2211 467X. DOI: https : / / doi . org / 10 . 1016 / j . esr . 2025 . 101842. [Online]. Available: https : / / www . sciencedirect. com / science / article / pii / S2211467X25002056.
[6] T. S. Kishore, P. U. Kumar, and V. Ippili, “Review of global sustainable solar energy policies: Significance and impact,” Innovation and Green Development, vol. 4, no. 2, p. 100 224, 2025, ISSN: 2949-7531. DOI: https://doi.org/10.1016/j.igd.2025.100224. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S2949753125000219.
[7] W. Zhang and B. K. Sovacool, “The “triple burden” effect and “pressure-opportunity paradox” of net-zero transitions: Exploring the political economy of carbon border adjustment mechanism (cbam) implementation in the global south,” Energy Strategy Reviews, vol. 62, p. 101 913, 2025, ISSN: 2211-467X. DOI: https://doi.org/10.1016/j.esr.2025.101913. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S2211467X25002767.
[8] S. M. RAHMAN, A. RAIHAN, M. S. ALAM, and S. CHOWDHURY, “Greenhouse gas emission dynamics and climate change mitigation efforts toward sustainability in the middle east and north africa (mena) region,” Regional Sustainability, vol. 6, no. 4, p. 100 246, 2025, ISSN: 2666-660X. DOI: https: //doi.org/10.1016/j.regsus.2025.100246. [Online]. Available: https://www. sciencedirect.com/science/article/pii/S2666660X25000544.
[9] M. Imran, M. S. Alam, Z. Jijian, I. Ozturk, S. Wahab, and M. Do˘gan, “From resource curse to green growth: Exploring the role of energy utilization and natural resource abundance in economic development,” in Natural resources forum, Wiley Online Library, vol. 49, 2025, pp. 2025–2047. DOI: https://doi.org/10.1111/1477-8947.12461.
[10] S. Kahil, O. Jellouli, and M. Fihri, “Hybrid clustering and extreme value theory for anomaly detection in electricity consumption: A case study on tetouan’s grid,” Statistics, pp. 1–42, 2025. DOI: https: //doi.org/10.1080/02331888.2025.2571861.
[11] Y. Ji, Y. Zhu, S. Lu, L. Yang, and A. W.-C. Liew, “Wtc-ipst: A deep learning framework for short-term electric load forecasting with multi-scale feature extraction,” Knowledge-Based Systems, vol. 324, p. 113 907, 2025, ISSN: 0950-7051. DOI: https://doi.org/10.1016/j.knosys.2025. 113907. [Online]. Available: https://www.sciencedirect.com/science/article/ pii/S0950705125009530.
[12] Z. Zou, J. Wang, N. E, C. Zhang, Z. Wang, and E. Jiang, “Short-term power load forecasting: An integrated approach utilizing variational mode decomposition and tcn–bigru,” Energies, vol. 16, no. 18, 2023, ISSN: 1996-1073. DOI: 10.3390/en16186625. [Online]. Available: https://www.mdpi. com/1996-1073/16/18/6625.
[13] H.-M. Zuo, J. Qiu, Y.-H. Jia, Q.Wang, and F.-F. Li, “Ten-minute prediction of solar irradiance based on cloud detection and a long short-term memory (lstm) model,” Energy Reports, vol. 8, pp. 5146–5157, 2022, ISSN: 2352-4847. DOI: https : / / doi . org / 10 . 1016 / j . egyr . 2022 . 03 . 182. [Online]. Available: https : / / www . sciencedirect . com / science / article / pii / S2352484722007375.
[14] W. Khan, J. Y. Liao, S. Walker, and W. Zeiler, “Impact assessment of varied data granularities from commercial buildings on exploration and learning mechanism,” Applied Energy, vol. 319, p. 119 281, 2022, ISSN: 0306-2619. DOI: https://doi.org/10.1016/j.apenergy.2022.119281. [Online]. Available: https : / / www . sciencedirect . com / science / article / pii / S0306261922006389.
[15] E. Chaerun Nisa and Y.-D. Kuan, “Comparative assessment to predict and forecast water-cooled chiller power consumption using machine learning and deep learning algorithms,” Sustainability, vol. 13, no. 2, 2021, ISSN: 2071-1050. DOI: 10.3390/su13020744. [Online]. Available: https://www.mdpi. com/2071-1050/13/2/744.
[16] U. Kanewala, S. Weerakoon, and R. Nawarathna, “Exploring deep learning and tree-based ensemble models for chiller energy consumption predictions,” in 2021 IEEE 16th International Conference on Industrial and Information Systems (ICIIS), 2021, pp. 306–311. DOI: 10.1109 / ICIIS53135 . 2021.9660662.
[17] S. W. Kim and Y. I. Kim, “Hybrid trrm–deep learning approach for water-cooled centrifugal chiller cop prediction,” Case Studies in Thermal Engineering, vol. 76, p. 107 309, 2025, ISSN: 2214-157X. DOI: https://doi.org/10.1016/j.csite.2025.107309. [Online]. Available: https: //www.sciencedirect.com/science/article/pii/S2214157X25015692.
[18] K. Zhu et al., “Chiller system power prediction by physical-informed neural network,” Energies, vol. 18, no. 23, 2025, ISSN: 1996-1073. DOI: 10.3390/en18236363. [Online]. Available: https://www. mdpi.com/1996-1073/18/23/6363.
[19] M. H. Sulaiman and Z. Mustaffa, “Chiller energy prediction in commercial building: A metaheuristic-enhanced deep learning approach,” Energy, vol. 297, p. 131 159, 2024, ISSN: 0360-5442. DOI: https://doi.org/10.1016/j.energy.2024.131159. [Online]. Available: https: //www.sciencedirect.com/science/article/pii/S0360544224009320.
[20] M. H. Sulaiman and Z. Mustaffa, “Chiller power consumption forecasting for commercial building based on hybrid convolution neural networks-long short-term memory model with barnacles mating optimizer,” Next Energy, vol. 8, p. 100 321, 2025, ISSN: 2949-821X. DOI: https://doi.org/10. 1016/j.nxener.2025.100321. [Online]. Available: https://www.sciencedirect. com/science/article/pii/S2949821X25000845.
[21] T. Sathesh and Y.-C. Shih, “Optimized deep learning-based prediction model for chiller performance prediction,” Data & Knowledge Engineering, vol. 144, p. 102 120, 2023, ISSN: 0169-023X. DOI: https://doi.org/10.1016/j.datak.2022.102120. [Online]. Available: https: //www.sciencedirect.com/science/article/pii/S0169023X22001112.
[22] K. He et al., “Predictive control optimization of chiller plants based on deep reinforcement learning,” Journal of Building Engineering, vol. 76, p. 107 158, 2023, ISSN: 2352-7102. DOI: https : / / doi . org / 10 . 1016 / j . jobe. 2023 . 107158. [Online]. Available: https : / / www . sciencedirect.com/science/article/pii/S2352710223013384.
[23] K. He et al., “Efficient model-free control of chiller plants via cluster-based deep reinforcement learning,” Journal of Building Engineering, vol. 82, p. 108 345, 2024, ISSN: 2352-7102. DOI: https: / / doi . org / 10 . 1016 / j . jobe . 2023 . 108345. [Online]. Available: https : / / www . sciencedirect.com/science/article/pii/S2352710223025287.
[24] H. Y. P. Napitupulu, I. G. D. Nugraha, and R. F. Sari, “Development of optimization control system for chiller plant based on a predictive model with multi stack lstm and deep learning neural network multi output,” Journal of Building Engineering, vol. 98, p. 111 029, 2024, ISSN: 2352-7102. DOI: https: / / doi . org / 10 . 1016 / j . jobe . 2024 . 111029. [Online]. Available: https : / / www . sciencedirect.com/science/article/pii/S235271022402597X.
[25] Z. Du et al., “Knowledge-extracted deep learning diagnosis and its cloud-based management for multiple faults of chiller,” Building and Environment, vol. 235, p. 110 228, 2023, ISSN: 0360-1323. DOI: https://doi.org/10.1016/j.buildenv.2023.110228. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S036013232300255X.
[26] P. Li, B. Anduv, X. Zhu, X. Jin, and Z. Du, “Diagnosis for the refrigerant undercharge fault of chiller using deep belief network enhanced extreme learning machine,” Sustainable Energy Technologies and Assessments, vol. 55, p. 102 977, 2023, ISSN: 2213-1388. DOI: https://doi.org/10.1016/j. seta.2022.102977. [Online]. Available: https://www.sciencedirect.com/science/ article/pii/S2213138822010256.
[27] P. Li, B. Anduv, X. Zhu, X. Jin, and Z. Du, “Across working conditions fault diagnosis for chillers based on iot intelligent agent with deep learning model,” Energy and Buildings, vol. 268, p. 112 188, 2022, ISSN: 0378-7788. DOI: https://doi.org/10.1016/j.enbuild.2022.112188. [Online]. Available: https : / / www . sciencedirect . com / science / article / pii / S0378778822003590.
[28] Z. Jiang, M. J. Risbeck, S. C. Kulandai Samy, C. Zhang, S. Cyrus, and Y. M. Lee, “A timeseries supervised learning framework for fault prediction in chiller systems,” Energy and Buildings, vol. 285, p. 112 876, 2023, ISSN: 0378-7788. DOI: https://doi.org/10.1016/j.enbuild.2023. 112876. [Online]. Available: https://www.sciencedirect.com/science/article/ pii/S0378778823001068.
[29] P. Hosseini, “Deep-learning neural network prediction of a solar-based absorption chiller cooling system performance using waste heat,” Sustainable Energy Technologies and Assessments, vol. 53, p. 102 683, 2022, ISSN: 2213-1388. DOI: https : / / doi . org / 10 . 1016 / j . seta . 2022 . 102683. [Online]. Available: https : / / www . sciencedirect . com / science / article / pii / S2213138822007329.
[30] E.-S. M. El-Kenawy et al., “Nioa: A novel metaheuristic algorithm modeled on the stealth and precision of japanese ninjas,” Journal of Artificial Intelligence in Engineering Practice, vol. 1, no. 2, pp. 17–35, 2024.
