Data-Driven Demand Forecasting Based on an Ensemble LSTM Model
Main Article Content
Abstract
User participation in power grid dispatching can effectively enhance grid flexibility; however, the inherent uncertainty of user behavior constrains the development of demand response. To address this issue, an incentive-based demand response implementation framework is first established, and the mechanism by which load aggregators (LAs) integrate demand-side resources to participate in electricity market operations is analyzed. User behavioral responses under incentive policies are further transformed into demand elasticity.Subsequently, based on the long short-term memory (LSTM) network, a data-driven demand elasticity forecasting method using an ensemble LSTM model is proposed. To improve forecasting performance, the source data are processed through smoothing and scaling operations, and weighting coefficients are incorporated into the loss function to enhance model robustness. Case study results demonstrate that, compared with the conventional LSTM model and the k-nearest neighbor (kNN) forecasting method, the proposed approach reduces the average prediction error of user demand elasticity by 5.33% and 28.8%, respectively. For total load forecasting, the mean absolute percentage error (MAPE) is reduced by 2.06% and 3.09%, respectively. In addition, the effects of smoothing and scaling preprocessing techniques on forecasting accuracy are investigated based on the ensemble LSTM model. The results indicate that appropriate preprocessing of the original data can effectively improve prediction accuracy.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Mind forge Academia also operates under the Creative Commons Licence CC-BY 4.0. This allows for copy and redistribute the material in any medium or format for any purpose, even commercially. The premise is that you must provide appropriate citation information.
References
Zhang J., Peng Y., Wu H., et al. Reliability and risk analysis of load aggregators in demand response programs[J]. Applied Energy, 2019, 252: 113432.
Chen J., Yang P., Chen Y., et al. Optimal operation of multi-energy systems in industrial parks considering integrated demand response[J]. Renewable Energy, 2021, 172: 1061-1074.
H. Ren, H. Lu, J. Lu and Z. Jing, "Analysis of LA demand response characteristics considering cyber physical system coupling and user’s response difference," Power Syst. Technol., vol. 44, no. 10, pp. 3927-3936, 2020.
A. Zhou, K. Ren, X. Li and W. Zhang, "MMSE: A multi-model stacking ensemble learning algorithm for purchase prediction," 2019 IEEE 8th Joint International Information Technology and Artificial Intelligence Conference (ITAIC), pp. 96-102, May 2019.
V. Kulkarni, S. K. Sahoo, S. B. Thanikanti, S. Velpula and D. I. Rathod, "Power systems automation, communication, and information technologies for smart grid: A technical aspects review," TELKOMNIKA (Telecommunication Computing Electronics and Control), vol. 19, no. 3, pp. 1017-1029, 2021.
W. Liao, P. Li, Q. Wu, S. Huang, G. Wu and F. Rong, "Distributed optimal active and reactive power control for wind farms based on ADMM," International Journal of Electrical Power & Energy Systems, vol. 129, p. 106799, 2021.
K. Gillingham, D. Rapson and G. Wagner, "The rebound effect and energy efficiency policy," Review of Environmental Economics and Policy, 2016.
S. Sharma, A. Majumdar, V. Elvira and E. Chouzenoux, "Blind Kalman filtering for short-term load forecasting," IEEE Transactions on Power Systems, vol. 35, no. 6, pp. 4916-4919, 2020.
X. Kong, C. Li, F. Zheng and C. Wang, "Improved deep belief network for short-term load forecasting considering demand-side management," IEEE Transactions on Power Systems, vol. 35, no. 2, pp. 1531-1538, 2019.
W. Kong, Z. Y. Dong, Y. Jia, D. J. Hill, Y. Xu and Y. Zhang, "Short-term residential load forecasting based on LSTM recurrent neural network," IEEE Transactions on Smart Grid, vol. 10, no. 1, pp. 841-851, 2017.
M. H. Albadi and E. F. El-Saadany, "A summary of demand response in electricity markets," Electric Power Systems Research, vol. 78, no. 11, pp. 1989-1996, 2008.
C. L. Su and D. Kirschen, "Quantifying the effect of demand response on electricity markets," IEEE Transactions on Power Systems, vol. 24, no. 3, pp. 1199-1207, 2009.
J. W. Taylor, "Triple seasonal methods for short-term electricity demand forecasting," European Journal of Operational Research, vol. 204, no. 1, pp. 139-152, 2010.
S. A. Nabavi, S. Mohammadi, N. H. Motlagh, S. Tarkoma and P. Geyer, "Deep learning modeling in electricity load forecasting: Improved accuracy by combining DWT and LSTM," Energy Reports, vol. 12, pp. 2873-2900, 2024.
A. Baliyan, K. Gaurav and S. K. Mishra, "A review of short term load forecasting using artificial neural network models," Procedia Computer Science, vol. 48, pp. 121-125, 2015.
T. Gupta, R. Bhatia and S. Sharma, "An ensemble-based enhanced short and medium term load forecasting using optimized missing value imputation," Scientific Reports, vol. 15, no. 1, p. 21857, 2025.
Y. Ou, S. Huang, R. Yan, K. Zhou, Y. Shu and Y. Huang, "A Residual-Regulated Machine Learning Method for Non-Stationary Time Series Forecasting Using Second-Order Differencing," unpublished.
G. Yao, H. Liu and L. Dai, "Multi-agent reinforcement learning for adaptive resource orchestration in cloud-native clusters," Proceedings of the 2025 2nd International Conference on Intelligent Computing and Data Analysis, pp. 680-687, Aug. 2025.
Y. Zou, N. Qi, Y. Deng, Z. Xue, M. Gong and W. Zhang, "Autonomous resource management in microservice systems via reinforcement learning," 2025 8th International Conference on Computer Information Science and Application Technology (CISAT), pp. 991-995, Jul. 2025.
Y. Wu, Y. Qin, X. Su and Y. Lin, "Transformer-based risk monitoring for anti-money laundering with transaction graph integration," Proceedings of the 2025 2nd International Conference on Digital Economy, Blockchain and Artificial Intelligence, pp. 388-393, Jun. 2025.
J. Li, Q. Gan, R. Wu, C. Chen, R. Fang and J. Lai, "Causal Representation Learning for Robust and Interpretable Audit Risk Identification in Financial Systems," unpublished.
C. F. Chiang, D. Li, R. Ying, Y. Wang, Q. Gan and J. Li, "Deep Learning-Based Dynamic Graph Framework for Robust Corporate Financial Health Risk Prediction," unpublished.
S. Sun, "CIRR: Causal-Invariant Retrieval-Augmented Recommendation with Faithful Explanations under Distribution Shift," arXiv preprint arXiv:2512.18683, 2025.
C. Wang, T. Yuan, C. Hua, L. Chang, X. Yang and Z. Qiu, "Integrating Large Language Models with Cloud-Native Observability for Automated Root Cause Analysis and Remediation," unpublished.
Z. Zhang, W. Liu, J. Tao, H. Zhu, S. Li and Y. Xiao, "Unsupervised Anomaly Detection in Cloud-Native Microservices via Cross-Service Temporal Contrastive Learning," unpublished.
S. Peng, X. Zhang, L. Zhou and P. Wang, "YOLO-CBD: Classroom Behavior Detection Method Based on Behavior Feature Extraction and Aggregation," Sensors, vol. 25, no. 10, p. 3073, 2025.
J. Xie, Y. Wu, Y. Zhang, X. Zhang, Y. Xie and Y. Qu, "PLATO-TTA: Prototype-Guided Pseudo-Labeling and Adaptive Tuning for Multi-Modal Test-Time Adaptation of 3D Segmentation," Proceedings of the 33rd ACM International Conference on Multimedia, pp. 2226-2234, Oct. 2025.