Efficient Load Demand Prediction in Complex Energy Systems Using Modified Optimization Algorithms

International Journal of Electrical and Electronics Engineering

© 2024 by SSRG - IJEEE Journal

Volume 11 Issue 11

Year of Publication : 2024

Authors : I.J. Jithin Kumar, S. Divyapriya

10.14445/23488379/IJEEE-V11I11P136

How to Cite?

I.J. Jithin Kumar, S. Divyapriya, "Efficient Load Demand Prediction in Complex Energy Systems Using Modified Optimization Algorithms," SSRG International Journal of Electrical and Electronics Engineering, vol. 11,  no. 11, pp. 381-398, 2024. Crossref, https://doi.org/10.14445/23488379/IJEEE-V11I11P136

Abstract:

Accurate load forecasting is essential for effective energy management, especially in regions with dynamic energy consumption patterns. While Support Vector Regression (SVR) is widely used for load forecasting, its performance degrades on large datasets due to computational constraints in kernel learning. To overcome this difficulty, this study suggests combining SVR with the Particle Swarm Optimization (PSO) and Modified Harris Hawk’s Optimization (MHHO) algorithms to develop two hybrid SVR models, SVR-PSO and SVR-MHHO. Results demonstrate that both SVR-MHHO and SVR-PSO outperform traditional SVR, with SVR-MHHO exhibiting superior performance. Leveraging MATLAB/Simulink-2021a®, a modified form of the HHO algorithm is developed to improve search efficiency. Specifically, SVR-MHHO achieved the highest R^2 values (0.9932, 0.8896, 0.9921, and 0.9287), lowest MSE values (0.0004, 0.0062, 0.0005, and 0.0078), and lowest MAPE values (0.1479, 0.1323, 0.0768, and 0.1896) across the cities of Delhi, Mumbai, Kolkata, and Bangalore, respectively. Additionally, SVR-MHHO demonstrated advantages over SVR-PSO for load demand prediction in all cities. This study highlights the efficacy of hybrid SVR algorithms and their potential for improving load forecasting accuracy in energy management applications.

Keywords:

PV panel, Microgrid, BESS, Peak load shaving, State of charge.

References:

[1] Mohamed I. Ibrahem, “Privacy-Preserving and Efficient Electricity Theft Detection and Data Collection for AMI Using Machine Learning, Doctoral Dissertation, Tennessee Technological University, 2021.
[Google Scholar] 
[2] Yanbing Lin et al., “An Ensemble Model Based on Machine Learning Methods and Data Preprocessing for Short-Term Electric Load Forecasting,” Energies, vol. 10, no. 8, 2017.
[CrossRef] [Google Scholar]  [Publisher Link]
[3] Gamze Nalcaci, Ayse Özmen, and Gerhard Wilhelm Weber, “Long-Term Load Forecasting: Models Based on MARS, ANN and LR Methods,” Central European Journal of Operations Research, vol. 27, pp. 1033-1049, 2019.
[CrossRef] [Google Scholar]  [Publisher Link]
[4] O. Demirel, A. Kakilli, and M. Tektas, “Electric Energy Load Forecasting Using ANFIS and ARMA Methods,” Journal of the Faculty of Engineering and Architecture of Gazi University, vol. 25, no. 3, pp. 601-610, 2010.
[Google Scholar]  [Publisher Link]
[5] Jiarui Zhang, “Research on Power Load Forecasting Based on the Improved Elman Neural Network,” Chemical Engineering Transactions, vol. 51, pp. 589-594, 2016.
[CrossRef] [Google Scholar]  [Publisher Link]
[6] Eisa Almeshaiei, and Hassan Soltan, “A Methodology for Electric Power Load Forecasting,” Alexandria Engineering Journal, vol. 50, no. 2, pp. 137-144, 2011.
[CrossRef] [Google Scholar]  [Publisher Link]
[7] Sheraz Aslam et al., “A Survey on Deep Learning Methods for Power Load and Renewable Energy Forecasting in Smart Microgrids,” Renewable and Sustainable Energy Reviews, vol. 144, 2021.
[CrossRef] [Google Scholar]  [Publisher Link]
[8] Xavier Serrano-Guerrero et al., “A New Interval Prediction Methodology for Short-Term Electric Load Forecasting Based on Pattern Recognition,” Applied Energy, vol. 297, 2021.
[CrossRef] [Google Scholar]  [Publisher Link]
[9] Mahmoud M. Badr et al., “Privacy-Preserving Federated-Learning-Based Net-Energy Forecasting,” SoutheastCon 2022, pp. 133-139, 2022.
[CrossRef] [Google Scholar]  [Publisher Link]
[10] Chafak Tarmanini et al., “Short Term Load Forecasting Based on ARIMA and ANN Approaches,” Energy Reports, vol. 9, pp. 550-557, 2023.
[CrossRef] [Google Scholar]  [Publisher Link]
[11] Nooriya A. Mohammed, and Ammar Al-Bazi, “An Adaptive Backpropagation Algorithm for Long-Term Electricity Load Forecasting,” Neural Computing and Applications, vol. 34, no. 1, pp. 477-491, 2022.
[CrossRef] [Google Scholar]  [Publisher Link]
[12] Badar ul Islam, and Shams Forruque Ahmed, “Short-Term Electrical Load Demand Forecasting Based on LSTM and RNN Deep Neural Networks,” Mathematical Problems in Engineering, 2022.
[CrossRef] [Google Scholar]  [Publisher Link]
[13] Majed A. Alotaibi, “Machine Learning Approach for Short-Term Load Forecasting Using Deep Neural Network,” Energies, vol. 15, no. 17, 2022.
[CrossRef] [Google Scholar]  [Publisher Link]
[14] Sivakavi Naga Venkata Bramareswara Rao et al., “Day-Ahead Load Demand Forecasting in Urban Community Cluster Microgrids Using Machine Learning Methods,” Energies, vol. 15, no. 17, 2022.
[CrossRef] [Google Scholar]  [Publisher Link]
[15] Eduardo Machado et al., “Electrical Load Demand Forecasting Using Feed-Forward Neural Networks,” Energies, vol. 14, no. 22, 2021.
[CrossRef] [Google Scholar]  [Publisher Link]
[16] Seyed Mohammad Jafar Jalali et al., “A Novel Evolutionary-Based Deep Convolutional Neural Network Model for Intelligent Load Forecasting,” IEEE Transactions on Industrial Informatics, vol. 17, no. 12, pp. 8243-8253, 2021.
[CrossRef] [Google Scholar]  [Publisher Link]
[17] Arash Moradzadeh et al., “A Secure Federated Deep Learning-Based Approach for Heating Load Demand Forecasting in Building Environment,” IEEE Access, vol. 10, pp. 5037-5050, 2021.
[CrossRef] [Google Scholar]  [Publisher Link]
[18] Shafiul Hasan Rafi et al., “A Short-Term Load Forecasting Method Using Integrated CNN and LSTM Network,” IEEE Access, vol. 9, pp. 32436-32448, 2021.
[CrossRef] [Google Scholar]  [Publisher Link]
[19] Lulu Wen, Kaile Zhou, and Shanlin Yang, “Load Demand Forecasting of Residential Buildings Using a Deep Learning Model,” Electric Power Systems Research, vol. 179, 2020.
[CrossRef] [Google Scholar]  [Publisher Link]
[20] Ghulam Hafeez, Khurram Saleem Alimgeer, and Imran Khan, “Electric Load Forecasting Based on Deep Learning and Optimized by Heuristic Algorithm in Smart Grid,” Applied Energy, vol. 269, 2020.
[CrossRef] [Google Scholar]  [Publisher Link]
[21] Vladimir N. Vapnik, The Nature of Statistical Learning Theory, 2n ed., Springer Science & Business Media, Springer New York, 2000.
[CrossRef] [Google Scholar]  [Publisher Link]
[22] D. Han, L. Chan, and N. Zhu, “Flood Forecasting Using Support Vector Machines,” Journal of hydroinformatics, vol. 9, no. 4, pp. 267-276, 2007.
[CrossRef] [Google Scholar]  [Publisher Link]
[23] J. Kennedy, and R. Eberhart, “Particle Swarm Optimization,” Proceedings of the ICNN’95 - International Conference on Neural Networks, Perth, Australia, pp. 1942-1948, 1995.
[CrossRef] [Google Scholar]  [Publisher Link]
[24] Ali Asghar Heidari et al., “Harris Hawk’s Optimization: Algorithm and Applications,” Future Generation Computer Systems, vol. 97, pp. 849-872, 2019.
[CrossRef] [Google Scholar]  [Publisher Link]
[25] Dieu Tien Bui et al., “A Novel Swarm Intelligence Technique for Spatial Assessment of Landslide Susceptibility,” Sensors, vol. 19, no. 16, 2019.
[CrossRef] [Google Scholar]  [Publisher Link]
[26] Abdelhady Ramadan et al., “Photovoltaic Cells Parameter Estimation Using an Enhanced Teaching-Learning-Based Optimization Algorithm,” Iranian Journal of Science and Technology, Transactions of Electrical Engineering, vol. 44, pp. 767-779, 2020.
[CrossRef] [Google Scholar]  [Publisher Link]