aspg-28-4259-1792155080 20261016125120 American Scientific Publishing Group admin@americaspg.com American Scientific Publishing Group Journal of Artificial Intelligence and Metaheuristics JAIM 2833-5597 2026 11 1 Wei Hong Lim Faculty of Engineering, Technology and Built Environment, UCSI University, Kuala Lumpur 56000, Malaysia Amel Ali Alhussan Department of Computer Sciences, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia Accurate prediction of electricity consumption is a critical requirement for improving operational efficiency, en-hancing 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, this study proposes a robust data-driven framework that integrates deep learning with advanced metaheuristic optimization for high-precision short-term electricity consump-tion 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 opti-mization 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 ANN, RNN, LSTM, and GRU. Following metaheuristic optimization, the NijOA + BiLSTM model delivers a substantial improvement in predictive performance, reducing RMSE to 0.0038, MSE to 1.45 × 10−5, and MAE to 0.00019, while increasing the correlation strength to r = 0.973 and explanatory power to R2 = 0.97. 2026 01 15 4259 https://creativecommons.org/licenses/by/4.0/ 10.54216/JAIM.110101 https://www.americaspg.com/journal/28/article/4259 https://www.americaspg.com/storage/articles/manuscripts/01KTJC38AJ7A79JHW1WE55FSHJ.pdf