Real Time Electrical Load Prediction and Management through Deep Learning and Reinforcement Learning Techniques
Received: 9 November 2024 | Revised: 22 December 2024 and 10 January 2025 | Accepted: 27 January 2025 | Online: 5 February 2025
Corresponding author: Shimaa A. Ahmed
Abstract
Real-time electrical load prediction and management are critical to ensuring the stability and reliability of modern power systems, especially as global energy demand continues to grow. This research presents a groundbreaking solution by combining a hybrid deep learning approach with reinforcement learning to address the challenges of accurate forecasting and adaptive energy distribution. The proposed framework integrates Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks, leveraging their strengths to capture both spatial and temporal patterns in electrical load data. This hybrid model delivers highly accurate load forecasts and effectively handles complex and nonlinear consumption patterns that traditional methods fail to address. In addition to accurate forecasting, the research employs the Soft Actor-Critic (SAC) reinforcement learning algorithm, which enables adaptive decision-making for real-time load management. By dynamically adapting to fluctuating grid conditions, the SAC algorithm optimizes energy distribution, reduces peak demand stress, and enhances overall system efficiency. This integrated approach ensures that energy resources are allocated more effectively, improving grid stability and minimizing waste. The methodology is validated through rigorous experimentation using real-world datasets, such as the PJM dataset, and performance metrics, including Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and overall system efficiency. This research not only advances predictive analytics in electrical load management, but also provides utilities and consumers with a scalable and practical solution to optimize energy consumption, integrate renewable energy sources, and promote sustainability. The proposed hybrid deep learning and reinforcement learning framework serves as a vital tool for future energy systems, paving the way for smarter, more resilient power grids.
Keywords:
LSTM;, CNNs, MAE, RMSE, Soft Actor-Critic (SAC)Downloads
References
E. M. de Oliveira and F. L. Cyrino Oliveira, "Forecasting mid-long term electric energy consumption through bagging ARIMA and exponential smoothing methods," Energy, vol. 144, pp. 776–788, Feb. 2018.
S. K. Filipova-Petrakieva and V. Dochev, "Short-Term Forecasting of Hourly Electricity Power Demand: Reggresion and Cluster Methods for Short-Term Prognosis," Engineering, Technology & Applied Science Research, vol. 12, no. 2, pp. 8374–8381, Apr. 2022.
S. Maldonado, A. González, and S. Crone, "Automatic time series analysis for electric load forecasting via support vector regression," Applied Soft Computing, vol. 83, Oct. 2019, Art. no. 105616.
E. Aguilar Madrid and N. Antonio, "Short-Term Electricity Load Forecasting with Machine Learning," Information, vol. 12, no. 2, Feb. 2021, Art. no. 50.
N. T. Dung and N. T. Phuong, "Short-Term Electric Load Forecasting Using Standardized Load Profile (SLP) And Support Vector Regression (SVR)," Engineering, Technology & Applied Science Research, vol. 9, no. 4, pp. 4548–4553, Aug. 2019.
M. Abumohsen, A. Y. Owda, and M. Owda, "Electrical Load Forecasting Using LSTM, GRU, and RNN Algorithms," Energies, vol. 16, no. 5, Jan. 2023, Art. no. 2283.
G. P. Papaioannou, C. Dikaiakos, A. Dramountanis, and P. G. Papaioannou, "Analysis and Modeling for Short- to Medium-Term Load Forecasting Using a Hybrid Manifold Learning Principal Component Model and Comparison with Classical Statistical Models (SARIMAX, Exponential Smoothing) and Artificial Intelligence Models (ANN, SVM): The Case of Greek Electricity Market," Energies, vol. 9, no. 8, Aug. 2016, Art. no. 635.
I. K. Nti, M. Teimeh, O. Nyarko-Boateng, and A. F. Adekoya, "Electricity load forecasting: a systematic review," Journal of Electrical Systems and Information Technology, vol. 7, no. 1, Sep. 2020, Art. no. 13.
Z. Zhang, Q. Zhang, H. Liang, and B. Gorbani, "Optimizing electric load forecasting with support vector regression/LSTM optimized by flexible Gorilla troops algorithm and neural networks a case study," Scientific Reports, vol. 14, Sep. 2024, Art. no. 22092.
A. Alrasheedi and A. Almalaq, "Hybrid Deep Learning Applied on Saudi Smart Grids for Short-Term Load Forecasting," Mathematics, vol. 10, no. 15, Aug. 2022, Art. no. 2666.
D. Zhang, X. Jin, P. Shi, and X. Chew, "Real-time load forecasting model for the smart grid using bayesian optimized CNN-BiLSTM," Frontiers in Energy Research, vol. 11, May 2023, Art. no. 1193662.
G. Hafeez, K. S. Alimgeer, and I. Khan, "Electric load forecasting based on deep learning and optimized by heuristic algorithm in smart grid," Applied Energy, vol. 269, Jul. 2020, Art. no. 114915.
A. Sheikhi, M. Rayati, and A. M. Ranjbar, "Dynamic load management for a residential customer; Reinforcement Learning approach," Sustainable Cities and Society, vol. 24, pp. 42–51, Jul. 2016.
S. Kim and H. Lim, "Reinforcement Learning Based Energy Management Algorithm for Smart Energy Buildings," Energies, vol. 11, no. 8, Aug. 2018, Art. no. 2010.
S. Upadhyay, I. Ahmed, and L. Mihet-Popa, "Energy Management System for an Industrial Microgrid Using Optimization Algorithms-Based Reinforcement Learning Technique," Energies, vol. 17, no. 16, Aug. 2024, Art. no. 3898.
T. Yang, L. Zhao, W. Li, and A. Y. Zomaya, "Reinforcement learning in sustainable energy and electric systems: a survey," Annual Reviews in Control, vol. 49, pp. 145–163, Jan. 2020.
W. Shi, J. Cao, Q. Zhang, Y. Li, and L. Xu, "Edge Computing: Vision and Challenges," IEEE Internet of Things Journal, vol. 3, no. 5, pp. 637–646, Oct. 2016.
"PJM Learning Center - Who is PJM?," PJM. https://learn.pjm.com/who-is-pjm.
Downloads
How to Cite
License
Copyright (c) 2025 Shimaa A. Ahmed, Entisar H. Khalifa, Ashraf F. A. Mahmoud, Faroug A. Abdalla, Majid Nawaz, Asma Sulman
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
