Adaptive Hybrid Swallow Search Optimized Hybrid Deep Learning Model for Energy Demand Forecasting

International Journal of Electrical and Electronics Engineering

© 2026 by SSRG - IJEEE Journal

Volume 13 Issue 3

Year of Publication : 2026

Authors : G.S. Bibin, H. Vennila, M Chinchu

10.14445/23488379/IJEEE-V13I3P103

How to Cite?

G.S. Bibin, H. Vennila, M Chinchu, "Adaptive Hybrid Swallow Search Optimized Hybrid Deep Learning Model for Energy Demand Forecasting," SSRG International Journal of Electrical and Electronics Engineering, vol. 13,  no. 3, pp. 23-37, 2026. Crossref, https://doi.org/10.14445/23488379/IJEEE-V13I3P103

Abstract:

Energy consumption has become a critical challenge due to the environmental and economic implications of the current technological development. Artificial Intelligence techniques are used increasingly for optimal electricity demand forecasting and maintaining efficient energy management. However, existing AI-based models often fail to capture complex nonlinear demand patterns because they focus on short-term dependencies, which limits their ability to adapt to Dynamic Energy Consumption (EC) patterns. To overcome these drawbacks, a novel Energy Demand Forecasting using Optimized Resilient serial Cascaded Encoder-LSTM (EDFORCE) technique has been proposed in this paper. The proposed method necessitates historical data on electricity consumption and forecasts electricity demand based on season, day, and time interval. The proposed model uses a Gaussian Mixture Modelling (GMM) based data clustering to obtain season-based segmented data for demand modeling. Further, Attention-Enhanced serial Cascaded Encoder Long Short Term Memory (A-SCE-LSTM) networks are trained to forecast electricity demand, which is optimized by using the novel Hybrid Swallow Search-Adam Optimization (SWO-Adam) algorithm. The efficiency of the EDFORCE approach has been assessed using measures such as Accuracy (AC), Precision (PR), Recall (RE), F1-score (F1-s), Relative Root Mean Square Error (rRMSE), Mean Absolute Percentage Error (MAPE), Mean Bias Error (MBE), EC, and computation time. The proposed EDFORCE model achieves a higher accuracy of 97%, whereas the previous models, such as K-PCD, FNET, and VW AA-KELM model, achieve accuracy of 95%, 93%, and 92%. Additionally, the proposed EDFORCE model consumed 23.8%, 14.9%, and 1.3% less energy than the K-PCD, FNET, and VW AA-KELM models, respectively.

Keywords:

Energy Demand Forecasting, Gaussian Mixture Modelling, Swallow Search Optimization Algorithm, Serial Cascaded Encoder Long Short Term Memory Network.

References:

[1] Ritwik Mohan, and Nikhil Pachauri, “An Ensemble Model for the Energy Consumption Prediction of Residential Buildings,” Energy, vol. 314, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Bahrudin Hrnjica, and Ali Danandeh Mehr, Energy Demand Forecasting using Deep Learning, Smart Cities Performability, Cognition & Security, pp. 71-104, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Razak Olu-Ajayi et al., “Building Energy Consumption Prediction for Residential Buildings using Deep Learning and Other Machine Learning Techniques,” Journal of Building Engineering, vol. 45, pp. 1-11, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Taher M. Ghazal et al., “Energy Demand Forecasting using Fused Machine Learning Approaches,” Intelligent Automation & Soft Computing, vol. 31, no. 1, pp. 539-553, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Nikolaos G. Paterakis et al., “Deep Learning Versus Traditional Machine Learning Methods for Aggregated Energy Demand Prediction,” 2017 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe), Turin, Italy, pp. 1-6, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Jason Runge, and Radu Zmeureanu, “A Review of Deep Learning Techniques for Forecasting Energy Use in Buildings,” Energies, vol. 14, no. 3, pp. 1-26, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Eunjeong Choi, Soohwan Cho, and Dong Keun Kim, “Power Demand Forecasting using Long Short-Term Memory (LSTM) Deep-Learning Model for Monitoring Energy Sustainability,” Sustainability, vol. 12, no. 3, pp. 1-14, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[8] R. Mathumitha, P. Rathika, and K. Manimala, “Intelligent Deep Learning Techniques for Energy Consumption Forecasting in Smart Buildings: A Review,” Artificial Intelligence Review, vol. 57, no. 2, pp. 1-33, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Jatin Bedi, and Durga Toshniwal, “Empirical Mode Decomposition based Deep Learning for Electricity Demand Forecasting,” IEEE Access, vol. 6, pp. 49144-49156, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Adebayo Olusegun Aderibigbe et al., “Enhancing Energy Efficiency with AI: A Review of Machine Learning Models in Electricity Demand Forecasting,” Engineering Science & Technology Journal, vol. 4, no. 6, pp. 341-356, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[11] G. Vijendar Reddy et al., “Electricity Consumption Prediction using Machine Learning,” E3S Web of Conferences, vol. 391, pp. 1-9, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Paulo Vitor B. Ramos et al., “Residential Energy Consumption Forecasting using Deep Learning Models,” Applied Energy, vol. 350, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Darius Peteleaza et al., “Electricity Consumption Forecasting for Sustainable Smart Cities using Machine Learning Methods,” Internet of Things, vol. 27, pp. 1-13, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Javier Manuel Aguiar-Pérez, and María Ángeles Pérez-Juárez, “An Insight of Deep Learning based Demand Forecasting in Smart Grids,” Sensors, vol. 23, no. 3, pp. 1-30, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Mohammad Mahdi Forootan et al., “Machine Learning and Deep Learning in Energy Systems: A Review,” Sustainability, vol. 14, no. 8, pp. 1-49, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Jihye Shin et al., “Enhanced Data Processing and Machine Learning Techniques for Energy Consumption Forecasting,” Electronics, vol. 13, no. 19, pp. 1-27, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Ke Yan et al., “Multi-Step Short-Term Power Consumption Forecasting with a Hybrid Deep Learning Strategy,” Energies, vol. 11, no. 11, pp. 1-15, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Kamal Chapagain et al., “Short-Term Electricity Demand Forecasting using Deep Neural Networks: An Analysis for Thai Data,” Applied System Innovation, vol. 6, no. 6, pp. 1-29, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Zeynep Hilal Kilimci et al., “An Improved Demand Forecasting Model using Deep Learning Approach and Proposed Decision Integration Strategy for Supply Chain,” Complexity, vol. 2019, no. 1, pp. 1-15, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Fouzi Harrou et al., “Energy Consumption Prediction in Water Treatment Plants using Deep Learning with Data Augmentation,” Results in Engineering, vol. 20, pp. 1-14, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Zhanyu Feng et al., “Energy Consumption Prediction Strategy for Electric Vehicle based on LSTM-Transformer Framework,” Energy, vol. 302, pp. 1-35, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Mohd Herwan Sulaiman et al., “Utilizing the Kolmogorov-Arnold Networks for Chiller Energy Consumption Prediction in Commercial Building,” Journal of Building Engineering, vol. 96, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Farhan Hussain, M. Hasanuzzaman, and Nasrudin Abd Rahim, “Multivariate Machine Learning Algorithms for Energy Demand Forecasting and Load Behavior Analysis,” Energy Conversion and Management: X, vol. 26, pp. 1-24, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Hao Yang et al., “K-PCD: A New Clustering Algorithm for Building Energy Consumption Time Series Analysis and Predicting Model Accuracy Improvement,” Applied Energy, vol. 377, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Aditya Pai H et al., “Enhanced Household Energy Consumption Forecasting using Multivariate Long Short-Term Memory (LSTM) Networks with Weather Data Integration,” Results in Engineering, vol. 27, pp. 1-18, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Adel Binbusayyis, and Mohemmed Sha, “Energy Consumption Prediction using Modified Deep CNN-BiLSTM with Attention Mechanism,” Heliyon, vol. 11, no. 1, pp. 1-24, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Shuchen Zhao et al., “Short and Long-Term Renewable Electricity Demand Forecasting based on CNN-Bi-GRU Model,” ICCK Transactions on Emerging Topics in Artificial Intelligence, vol. 2, no. 1, pp. 1-15, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Marzia Ahmed et al., “Daily Allocation of Energy Consumption Forecasting of a Power Distribution Company using Optimized Least Squares Support Vector Machine,” Results in Control and Optimization, vol. 18, pp. 1-13, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Sujan Ghimire et al., “Explainable Deeply-Fused Nets Electricity Demand Prediction Model: Factoring Climate Predictors for Accuracy and Deeper Insights with Probabilistic Confidence Interval and Point-based Forecasts,” Applied Energy, vol. 378, pp. 1-34, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Yuqing Wang, and Xiao Yang, “Cloud Computing Energy Consumption Prediction based on Kernel Extreme Learning Machine Algorithm Improved by Vector Weighted Average Algorithm,” 2025 5th International Conference on Artificial Intelligence and Industrial Technology Applications (AIITA), Xi'an, China, pp. 1-7, 2025.
[Google Scholar] [Publisher Link]