Advances and Evaluation of Intelligent Techniques in Short-Term Load Forecasting

Journal: Journal of Machine Learning and Deep Learning (JMLDL), Volume:1, Issue:1, Pages: 32-40 Download pdf

Authors: Jamshaid Iqbal Janjua, Tahir Abbas

Date: 12-2024

Abstract: In order to maintain the stability of the power grid, various load forecasting methods have emerged in endlessly. However, due to different characteristics such as algorithm generalization capabilities and model complexity, their applicability to load forecasting varies. This article discusses short-term power load forecasting in the past five years. In summary, this paper summarizes the various dimensions such as experimental data sets, data preprocessing, prediction algorithms, optimization models, and evaluation methods of current research status in power load forecasting. In addition to the advantages, disadvantages, and applicability of various prediction algorithms, this paper also sums up and prospects the development trends of the short-term power load forecasting system, so as to provide a reference for the selection of power system load forecasting models in the future.

Keywords: Short-Term Load Forecasting, Deep Learning Combination Model, Long Short-Term Memory Network, Machine Learning.

References:

[1] Athanasios Ioannis Arvanitidis, D. Bargiotas, Aspassia Daskalopulu, Dimitrios Kontogiannis, I. Panapakidis and L. Tsoukalas. "Clustering Informed MLP Models for Fast and Accurate Short-Term Load Forecasting." Energies (2022). https://doi.org/10.3390/en15041295.

[2] Behnam Farsi, Manar Amayri, N. Bouguila and U. Eicker. "On Short-Term Load Forecasting Using Machine Learning Techniques and a Novel Parallel Deep LSTM-CNN Approach." IEEE Access, 9 (2021): 31191-31212.

[3] Bastian Dietrich, J. Walther, M. Weigold and E. Abele. "Machine learning based very short term load forecasting of machine tools." Applied Energy, 276 (2020): 115440. https://doi.org/10.1016/j.apenergy.2020.115440.

[4] T. Alquthami, M. Zulfiqar, Muhammad Kamran, A. H. Milyani and M. B. Rasheed. "A Performance Comparison of Machine Learning Algorithms for Load Forecasting in Smart Grid." IEEE Access, PP (2022): 1-1. https://doi.org/10.1109/access.2022.3171270.

[5] International Renewable Energy Agency. Renewable energy statistics 2020.

https://www.irena.org/publications/2020/Jul/Renewable-energystatistics-2020. (2020-07-01) [2021-11-11]

[6] Yi Hu, B. Qu, Jie Wang, Jing J. Liang, Yanli Wang, Kunjie Yu, Yaxin Li and Kangjia Qiao. "Short-term load forecasting using multimodal evolutionary algorithm and random vector functional link network based ensemble learning." Applied Energy, 285(2021): 116415. https://doi.org/10.1016/J.APENERGY.2020.116415

[7] Songjiang Li, Peng Wang and L. Goel. "A Novel Wavelet-Based Ensemble Method for Short-Term Load Forecasting with Hybrid Neural Networks and Feature Selection." IEEE Transactions on Power Systems, 31 (2016): 1788-1798. https://doi.org/10.1109/TPWRS.2015.2438322.

[8] Weilin Guo, Liang Che, M. Shahidehpour and Xin Wan. "Machine-Learning based methods in short-term load forecasting." The Electricity Journal, 34 (2021): 106884. https://doi.org/10.1016/j.tej.2020.106884

[9] Haoyu Jiang, A. Wu, Bo Wang, P. Xu and Gang Yao. "Industrial Ultra-Short-Term Load Forecasting With Data Completion." IEEE Access, 8 (2020): 158928-158940. https://doi.org/10.1109/ACCESS.2020.3017655

[10] Rangelov, D., Boerger, M., Tcholtchev, N., Lämmel, P., & Hauswirth, M. (2023). Design and Development of a Short-Term Photovoltaic Power Output Forecasting Method Based on Random Forest, Deep Neural Network and LSTM Using Readily Available Weather Features. IEEE Access, 11, 41578-41595. https://doi.org/10.1109/ACCESS.2023.3270714.

[11] N. Giamarelos, Myron Papadimitrakis, M. Stogiannos, E. Zois, N. Livanos and A. Alexandridis. "A Machine Learning Model Ensemble for Mixed Power Load Forecasting across Multiple Time Horizons." Sensors (Basel, Switzerland), 23 (2023). https://doi.org/10.3390/s23125436.

[12] Wang, C., & Li, W. (2023). A hybrid model of modal decomposition and gated recurrent units for short-term load forecasting. PeerJ Computer Science, 9. https://doi.org/10.7717/peerj-cs.1514.

[13] Nespoli, A., Leva, S., Mussetta, M., & Ogliari, E. (2022). A Selective Ensemble Approach for Accuracy Improvement and Computational Load Reduction in ANN-based PV power forecasting. IEEE Access, PP, 1-1. https://doi.org/10.1109/ACCESS.2022.3158364.

[14] Qin, C., Srivastava, A., Saber, A., Matthews, D., & Davies, K. (2023). Geometric Deep-Learning-Based Spatiotemporal Forecasting for Inverter-Based Solar Power. IEEE Systems Journal, 17, 3425-3435. https://doi.org/10.1109/JSYST.2023.3250403.

[15] Box GEP, Jenkins GM. Time Series Analysis: Forecasting and Control. San Francisco: Holden-Day, 1976. 238–242.

[16] Zhou, W., Tao, H., Ding, S., & Li, Y. (2022). Electricity consumption and production forecasting considering seasonal patterns: An investigation based on a novel seasonal discrete grey model. Journal of the Operational Research Society, 74, 1346 - 1361. https://doi.org/10.1080/01605682.2022.2085065.

[17] Yang, J., Tang, Y., & Duan, H. (2022). Application of Fuzzy Support Vector Machine in Short-Term Power Load Forecasting. J. Cases Inf. Technol., 24, 1-10. https://doi.org/10.4018/jcit.295248.

[18] Zulfiqar, M., Kamran, M., Rasheed, M., Alquthami, T., & Milyani, A. (2022). A Short-Term Load Forecasting Model Based on Self-Adaptive Momentum Factor and Wavelet Neural Network in Smart Grid. IEEE Access, 10, 77587-77602. https://doi.org/10.1109/access.2022.3192433.

[19] Cai Qiuna, Chao Zhu, Su Binghong, et al. Short-term load forecasting method of neural network based on a new type of robust loss. Power Grid Technology, 2020, 44(11): 4132-4139.

[20] Han, M., Tan, A., & Zhong, J. (2022). Improved particle swarm optimization combined with least squares support vector machines for short-term load forecasting. , 12176, 1217612 - 1217612-11. https://doi.org/10.1117/12.2636473.

[21] Xu, J., Liu, M., Xiang, W., Chen, H., Mao, Y., & Jia, T. (2023). Short-term Load Forecasting Based on Multiple PSO-LSSVM under Electricity Market Environment. Journal of Physics: Conference Series, 2427. https://doi.org/10.1088/17426596/2427/1/012024.

[22] Zhang ZC, Hong WC. Application of variational mode decomposition and chaotic gray wolf optimizer with support vector regression for forecasting electric loads. Knowledge- Based Systems, 2021, 228: 107297.DOI:10.1016/j.knosys.2021.107297

[23] Qin, B., Huang, X., Wang, X., & Guo, L. (2023). Ultra-shortterm wind power prediction based on double decomposition and LSSVM. Transactions of the Institute of Measurement and Control, 45, 2627 - 2636. https://doi.org/10.1177/01423312231153258 .

[24] Dai YM, Zhao P. A hybrid load forecasting model based on support vector machine with intelligent methods for feature selection and parameter optimization. Applied Energy, 2020, 279: 115332.DOI:10.1016/j.apenergy.2020.115332

[25] Jahangir, H., Tayarani, H., Gougheri, S., Golkar, M., Ahmadian, A., & Elkamel, A. (2021). Deep Learning-Based Forecasting Approach in Smart Grids With Microclustering and Bidirectional LSTM Network. IEEE Transactions on Industrial Electronics, 68, 8298-8309. https://doi.org/10.1109/TIE.2020.3009604.

[26] Sadaei HJ, de Lima e Silva PC, Guimarães FG, et al. Short-term load forecasting by using a combined method of convolutional neural networks and fuzzy time series. Energy, 2019, 175: 365- 377.DOI:10.1016/j. energy.2019.03.081

[27] Yin LF, Xie JX. Multi-temporal-spatial-scale temporal convolution network for short-term load forecasting of power systems. Applied Energy, 2021, 283: 116328.DOI:10.1016/j.apenergy.2020.116328

[28] Imani M. Electrical load-temperature CNN for residential load forecasting. Energy, 2021, 227: 120480.DOI:10.1016/j.energy.2021.120480

[29] Fekri MN, Patel H, Grolinger K, et al. Deep learning for load forecasting with smart meter data: Online adaptive recurrent neural network. Applied Energy, 2021, 282: 116177.DOI:10.1016/j.apenergy.2020.116177

[30] Mahjoub, S., Chrifi-Alaoui, L., Marhic, B., & Delahoche, L. (2022). Predicting Energy Consumption Using LSTM, MultiLayer GRU and Drop-GRU Neural Networks. Sensors (Basel, Switzerland), 22. https://doi.org/10.3390/s22114062.

[31] Zang HX, Xu RQ, Cheng LL, et al. Residential load forecasting based on LSTM fusing self-attention mechanism with pooling. Energy, 2021, 229: 120682.DOI:10.1016/j.energy.2021.120682

[32] Ijaz, K., Hussain, Z., Ahmad, J., Ali, S., Adnan, M., & Khosa, I. (2022). A Novel Temporal Feature Selection Based LSTM Model for Electrical Short-Term Load Forecasting. IEEE Access, 10, 82596-82613. https://doi.org/10.1109/ACCESS.2022.3196476.

[33] Feng, C., Xu, K., & Ma, H. (2022). Research on Impulse Power Load Forecasting Based on Improved Recurrent Neural Networks. Computational Intelligence and Neuroscience, 2022. https://doi.org/10.1155/2022/2784563.

[34] Zhang, Y., & Li, G. (2023). Power load forecasting based on deep neural network. 12719, 127190V - 127190V-5. https://doi.org/10.1117/12.2685798.

[35] Alipour M, Aghaei J, Norouzi M, et al. A novel electrical netload forecasting model based on deep neural networks and wavelet transform integration. Energy, 2020, 205: 118106.DOI:10.1016/j.energy.2020.118106

[36] Qin, C., Srivastava, A., Saber, A., Matthews, D., & Davies, K. (2023). Geometric Deep-Learning-Based Spatiotemporal Forecasting for Inverter-Based Solar Power. IEEE Systems Journal, 17, 3425-3435. https://doi.org/10.1109/JSYST.2023.3250403.

[37] Aduama, P., Zhang, Z., & Sumaiti, A. (2023). Multi Feature Data Fusion-Based Load Forecasting of Electric Vehicle Charging Stations Using a Deep Learning Model. ArXiv, abs/2301.13774. https://doi.org/10.3390/en16031309.

[38] Massaoudi M, Refaat SS, Chihi I, et al. A novel stacked generalization ensemble-based hybrid LGBM-XGB-MLP model for short-term load forecasting. Energy, 2021, 214: 118874.DOI:10.1016/j.energy.2020.118874

[39] Sun Chao, Lu Qi, Zhu Sixian, et al. Ultra-short-term power load forecasting based on the double-layer XGBoost algorithm considering the influence of multiple features. High Voltage Technology, 2021, 47(8): 2885-2895.

[40] Chen Zhenyu, Liu Jinbo, Li Chen, et al. Ultra-short-term power load forecasting based on the combined model of LSTM and XGBoost. Power Grid Technology, 2020, 44(2): 614-620.

[41] Zhuang Jiayi, Yang Guohua, Zheng Haofeng, et al. CNN-LSTMXGBoost short-term power loading forecasting method based on multi-model fusion. China Electric Power, 2021, 54(5): 46-55.

[42] Zhang, J., Zhao, Z., Yan, J., & Cheng, P. (2023). Ultra-ShortTerm Wind Power Forecasting Based on CGAN-CNN-LSTM Model Supported by Lidar. Sensors (Basel, Switzerland), 23. https://doi.org/10.3390/s23094369.

[43] Liu, F., Dong, T., Hou, T., & Liu, Y. (2021). A Hybrid ShortTerm Load Forecasting Model Based on Improved Fuzzy CMeans Clustering, Random Forest and Deep Neural Networks. IEEE Access, 9, 59754-59765. https://doi.org/10.1109/ACCESS.2021.3063123.

[44] Nie Y, Jiang P, Zhang HP. A novel hybrid model based on combined preprocessing method and advanced optimization algorithm for power load forecasting. Applied Soft Computing, 2020, 97: 106809.DOI:10.1016/j.asoc.2020.106809

[45] Lazzeroni, P., Lorenti, G., & Repetto, M. (2023). A Data-Driven Approach to Predict Hourly Load Profiles From Time-of-Use Electricity Bills. IEEE Access, 11, 60501-60515. https://doi.org/10.1109/ACCESS.2023.3286020.

[46] Zeng Ming, Zhang Shuo. Analysis of comprehensive energy development in the "14th Five-Year Plan" power plan. China Electric Power Enterprise Management, 2020(13): 2628.DOI:10.3969/j.issn.1007-3361.2020.13.006.