Open Access

ARTICLE

Bidirectional LSTM-Based Energy Consumption Forecasting: Advancing AI-Driven Cloud Integration for Cognitive City Energy Management

Sheik Mohideen Shah¹, Meganathan Selvamani¹, Mahesh Thyluru Ramakrishna^2,*, Surbhi Bhatia Khan^3,4,5, Shakila Basheer⁶, Wajdan Al Malwi⁷, Mohammad Tabrez Quasim⁸

1 Department of Computer Science and Engineering, Srinivasa Ramanujan Centre, SASTRA Deemed University, Kumbakonam, 612001, India
2 Department of Computer Science and Engineering, Faculty of Engineering and Technology, JAIN (Deemed-to-be University), Bangalore, 562112, India
3 School of Science, Engineering and Environment, University of Salford, Manchester, M54WT, UK
4 University Centre for Research and Development, Chandigarh University, Mohali, 140413, Punjab, India
5 Centre for Research Impact and Outcome, Chitkara University Institute of Engineering and Technology, Chitkara University, Rajpura, 140401, Punjab, India
6 Department of Information Systems, College of Computer and Information Science, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh, 11671, Saudi Arabia
7 College of Computer Science Informatics and Computer Systems Department, King Khalid University, Abha, 61421, Saudi Arabia
8 Department of Computer Science and Artificial Intelligence, College of Computing and Information Technology, University of Bisha, Bisha, 61922, Saudi Arabia

* Corresponding Author: Mahesh Thyluru Ramakrishna. Email:

(This article belongs to the Special Issue: Empowered Connected Futures of AI, IoT, and Cloud Computing in the Development of Cognitive Cities)

Computers, Materials & Continua 2025, 83(2), 2907-2926. https://doi.org/10.32604/cmc.2025.063809

Received 24 January 2025; Accepted 03 March 2025; Issue published 16 April 2025

Abstract

Efficient energy management is a cornerstone of advancing cognitive cities, where AI, IoT, and cloud computing seamlessly integrate to meet escalating global energy demands. Within this context, the ability to forecast electricity consumption with precision is vital, particularly in residential settings where usage patterns are highly variable and complex. This study presents an innovative approach to energy consumption forecasting using a bidirectional Long Short-Term Memory (LSTM) network. Leveraging a dataset containing over two million multivariate, time-series observations collected from a single household over nearly four years, our model addresses the limitations of traditional time-series forecasting methods, which often struggle with temporal dependencies and non-linear relationships. The bidirectional LSTM architecture processes data in both forward and backward directions, capturing past and future contexts at each time step, whereas existing unidirectional LSTMs consider only a single temporal direction. This design, combined with dropout regularization, leads to a 20.6% reduction in RMSE and an 18.8% improvement in MAE over conventional unidirectional LSTMs, demonstrating a substantial enhancement in prediction accuracy and robustness. Compared to existing models—including SVM, Random Forest, MLP, ANN, and CNN—the proposed model achieves the lowest MAE of 0.0831 and RMSE of 0.2213 during testing, significantly outperforming these benchmarks. These results highlight the model’s superior ability to navigate the complexities of energy usage patterns, reinforcing its potential application in AI-driven IoT and cloud-enabled energy management systems for cognitive cities. By integrating advanced machine learning techniques with IoT and cloud infrastructure, this research contributes to the development of intelligent, sustainable urban environments.

---

Keywords

---