2690-6791ISSN (Online)
2769-786XISSN (Print)
Volume 18 , Issue 2 , PP: 60-71, 2026 | Cite this article as | XML | Html | PDF | Full Length Article
Nebras Jalel Ibrahim 1 * , Samah Faris Kamil 2 , Ghasaq Saad Jameel 3
Doi: https://doi.org/10.54216/JISIoT.180204
Reducing energy losses and increasing power grid efficiency need accurate prediction of power consumption accurate prediction of future energy consumption requires the use of time series data. To overcome the shortcomings of conventional techniques for forecasting energy consumption in India for the period from 2 January, 2019 to 23 May, 2020, we used an attention mechanism, which is still relatively new and not well known. In this paper, we propose a new approach for predicting energy consumption by combining local feature extraction with convolutional neural networks (CNNs), long short-term memory (LSTM) to capture long-term temporal dependencies, and attention mechanisms to deal with the issue of information loss brought on by extremely lengthy input time series data. After high-dimensional features are extracted from the input data using a one-dimensional CNN layer, temporal correlations within historical sequences are captured using an LSTM layer. In order to optimize the weighting of the LSTM outputs, strengthen the impact of important information, and enhance the prediction model as a whole, an attention mechanism is finally implemented. This integration improves the model's ability to represent complex spatio-temporal patterns. The mean absolute error (MAE) and root mean square error (RMSE) are used to assess the performance of the proposed model. The results demonstrate that the CNN-LSTM-Attention model outperforms conventional hybrid CNN-LSTM and LSTM models, demonstrating superior performance across a range of prediction scenarios. By supporting more reliable grid management, proactive intervention methods, and predictive maintenance, these developments contribute to reducing load imbalances and energy waste in India. The Future developments could see the proposed model extended to other time series prediction domains.
Power consumption , prediction , CNN , LSTM , Attention mechanism , Deep learning , Hybrid model
[1] G. Dave, T. Patel, and S. Mitra, "Global scenario on renewable energy and net zero goal emphasizing Indian standpoint: a short review," Energy Syst., pp. 1-22, 2025.
[2] A. Kurani, P. Doshi, A. Vakharia, and M. Shah, "A comprehensive comparative study of artificial neural network (ANN) and support vector machines (SVM) on stock forecasting," Ann. Data Sci., vol. 10, no. 1, pp. 183-208, 2023.
[3] Z. Han, J. Zhao, H. Leung, K. F. Ma, and W. Wang, "A review of deep learning models for time series prediction," IEEE Sensors J., vol. 21, no. 6, pp. 7833-7848, 2019.
[4] M. Waqas and U. W. Humphries, "A critical review of RNN and LSTM variants in hydrological time series predictions," MethodsX, p. 102946, 2024.
[5] P. W. Tien, S. Wei, J. Darkwa, C. Wood, and J. K. Calautit, "Machine learning and deep learning methods for enhancing building energy efficiency and indoor environmental quality–a review," Energy AI, vol. 10, p. 100198, 2022.
[6] P. Madhavi and S. V. Satyanarayana, "Data Analysis of electrical systems using machine learning algorithms," in 2022 First Int. Conf. Artif. Intell. Trends Pattern Recognit. (ICAITPR), 2022, pp. 1-4.
[7] M. Uppal, R. Kumari, and S. Shrivastava, "An Ensemble Approach for Short-Term Load Forecasting for DISCOMS of Delhi Across the COVID-19 Scenario," in 2021 9th IEEE Int. Conf. Power Syst. (ICPS), 2021, pp. 1-6.
[8] M. Suvarna, A. Katragadda, Z. Sun, Y. B. Choh, Q. Chen, and X. Wang, "Advances in Applied Energy," Adv. Appl. Energy, 2021.
[9] S. Gochhait and D. Sharma, "Regression model-based short-term load forecasting for load despatch centre," J. Appl. Eng. Technol. Sci. (JAETS), vol. 4, no. 2, pp. 693-710, 2023.
[10] K. Pradeep, T. Likhita, V. Sai Pavan, and A. Raghu Vira Pratap, "Machine-learning based approach to predict energy consumption of India States," in 2022 6th Int. Conf. Comput. Methodol. Commun. (ICCMC), 2022, pp. 1153-1156.
[11] R. Bareth and A. Yadav, "Day Ahead Load Demand Forecasting based on LSTM Machine Learning Model," in 2024 Third Int. Conf. Power, Control Comput. Technol. (ICPC2T), 2024, pp. 404-408.
[12] R. Bareth, A. Yadav, S. Gupta, and M. Pazoki, "Daily average load demand forecasting using LSTM model based on historical load trends," IET Gener., Transmiss. Distrib., vol. 18, no. 5, pp. 952-962, 2024.
[13] V. Veeramsetty, D. R. Chandra, F. Grimaccia, and M. Mussetta, "Short term electric power load forecasting using principal component analysis and recurrent neural networks," Forecasting, vol. 4, no. 1, pp. 149-164, 2022.
[14] A. Saji, A. Prakash, and M. S. Krishnan, "Electricity Demand Forecasting In Kerala Using Machine Learning Models," in 2023 3rd Int. Conf. Intell. Technol. (CONIT), 2023, pp. 1-6.
[15] S. Jayashree and A. Rajini, "Forecasting power consumption by deep learning approaches in the state of telangana," in 2023 3rd Int. Conf. Intell. Technol. (CONIT), 2023, pp. 1-7.
[16] D. Lakshmi, R. S. Tiwari, N. Nagpal, N. Kassarwani, G. Vishnuvarthanan, and A. Srivastava, "Comparative study on forecasting of schedule generation in delhi region for the resilient power grid using machine learning," IEEE Trans. Ind. Appl., vol. 60, no. 2, pp. 2107-2116, 2023.
[17] K. Amarasinghe, D. L. Marino, and M. Manic, "Deep neural networks for energy load forecasting," in 2017 IEEE 26th Int. Symp. Ind. Electron. (ISIE), 2017, pp. 1483-1488.
[18] T. Y. Kim and S. B. Cho, "Predicting residential energy consumption using CNN-LSTM neural networks," Energy, vol. 182, pp. 72-81, 2019.
[19] Y. H. Abdulameer and A. A. Ibrahim, "Forecasting of Electrical Energy Consumption Using Hybrid Models of GRU, CNN, LSTM, And ML Regressors,".
[20] N. Bhoj and R. S. Bhadoria, "Time-series based prediction for energy consumption of smart home data using hybrid convolution-recurrent neural network," Telemat. Inform, vol. 75, p. 101907, 2022.
[21] State-wise-power-consumption-in-india [Dataset]. Kaggle. Available: https://www.kaggle.com/datasets/twinkle0705/state-wise-power-consumption-in-india
[22] B. S. Vardhan, A. Swain, M. Khedkar, I. Srivastava, and N. D. Bokde, "An overview of Indian power sector and its Energy Management," Renew. Energy Focus, p. 100597, 2024.
[23] Z. Liu, Z. Zhu, J. Gao, and C. Xu, "Forecast methods for time series data: A survey," IEEE Access, vol. 9, pp. 91896-91912, 2021.
[24] C. L. Liu, T. Y. Chang, J. S. Yang, and K. B. Huang, "A deep learning sequence model based on self-attention and convolution for wind power prediction," Renew. Energy, vol. 219, p. 119399, 2023.
[25] A. Tasdelen and B. Sen, "A hybrid CNN-LSTM model for pre-miRNA classification," Sci. Rep., vol. 11, no. 1, p. 14125, 2021.
[26] A. J. Yousif and M. H. Al-Jammas, "Real-time Arabic Video Captioning Using CNN and Transformer Networks Based on Parallel Implementation," Diyala J. Eng. Sci., pp. 84-93, 2024.
[27] T. T. Hoa, T. M. Le, and C. H. Nguyen-Dinh, "Hybrid model of 1D-CNN and LSTM for forecasting Ethereum closing prices: a case study of temporal analysis," Int. J. Inf. Technol., pp. 1-13, 2025.
[28] D. Soydaner, "Attention mechanism in neural networks: where it comes and where it goes," Neural Comput. Appl., vol. 34, no. 16, pp. 13371-13385, 2022.
[29] A. J. Yousif and M. H. Al-Jammas, "Semantic-based temporal attention network for Arabic Video Captioning," Nat. Lang. Process. J., vol. 10, p. 100122, 2025.
[30] A. Wan, Q. Chang, A. B. Khalil, and J. He, "Short-term power load forecasting for combined heat and power using CNN-LSTM enhanced by attention mechanism," Energy, vol. 282, p. 128274, 2023.
[31] R. Yamashita, M. Nishio, R. K. G. Do, and K. Togashi, "Convolutional neural networks: an overview and application in radiology," Insights Imaging, vol. 9, no. 4, pp. 611-629, 2018.
