Regression Model-Based Short-Term Load Forecasting for Load Despatch Centre
DOI:
https://doi.org/10.37385/jaets.v4i2.1682Keywords:
Short-term load forecasting, regression model, Gaussian process regression, probabilistic models, Subdivision electricity loadAbstract
Forecasting load is an integral part of the planning, operation, and control of power systems. This paper is part of a research effort aimed at developing better energy demand forecasting models for load dispatch centers (LDCs) in Indian states as part of an ambitious project utilizing artificial intelligence-based load forecasting models. In this paper, we present a half hourly load forecasting method for the energy management system of the project that will be used at 33 /11 kV and 0.415 kV substations with good accuracy. The paper uses the half-hourly load consumption dataset collected from MSEDCL for Maharashtra from July 1, 2020 through August 31, 2022. This paper evaluates 24 regression model-based half hourly based load forecasting algorithms for ALE PHATA load based on the load consumption dataset and the collected meteorological dataset. The 24 models in MATLAB Regression belong to five types of regression models: Linear Regression, Regression Trees, Support Vector Machines (SVM), Gaussian Process Regression (GPR), Ensemble of Trees, and Neural Networks. As a consequence of their nonparametric kernel-based probabilistic nature, the GPR family of models demonstrates the best load forecasting performance. Least squares estimation was used to determine the regression coefficients. There is a direct correlation between load in an electrical power system and temperature, due point, and seasons, as well as a correlation between load and previous load consumption. Therefore, the input variables are Wet Bulb Temperature at 2 Meters (C), Dew/Frost Point at 2 Meters (C), Temperature at 2 Meters (C), Relative Humidity at 2 Meters (%), Specific Humidity at 2 Meters (g/kg) and Wind Speed at 10 Meters (m/s). The mean absolute percentage error and the R squared are used to validate or verify the accuracy of the model, which is shown in the results section. Based on this study, two GPR models are recommended for load forecasting, the Rational Quadratic GPR and the Exponential GPR and Exponential GPR as final model.
Downloads
References
Badran, S., & Abouelatta, O. (2012). Neural network integrated with regression methods to forecast electrical load. International conference on electrical, electronics and biomedical engineering (ICEEBE2012) Penang (Malaysia).
Cao, Z., Wan, C., Zhang, Z., Li, F., & Song, Y. (2019). Hybrid ensemble deep learning for deterministic and probabilistic low-voltage load forecasting. IEEE Transactions on Power Systems, 35(3), 1881-1897. doi:10.1109/TPWRS.2019.2946701
Caro, E., Juan, J., & Cara, J. (2020). Periodically correlated models for short-term electricity load forecasting. Applied Mathematics and Computation, 364, 124642. doi:10.1016/j.amc.2019.124642
Ceperic, E., Ceperic, V., & Baric, A. (2013). A strategy for short-term load forecasting by support vector regression machines. Power Yet IEEE (Trans.), 28(4), 4356–4364.
Chane, K., Gebru, F. M., & Khan, B. (2021). Short Term Load Forecasting of Distribution Feeder Using Artificial Neural Network Technique. Journal of Informatics Electrical and Electronics Engineering (JIEEE), 2(1), 1-22.
Chang, Q., Wang, Y., Lu, X., Shi, D., Li, H., Duan, J., & Wang, Z. (2019, May). Probabilistic load forecasting via point forecast feature integration. In 2019 IEEE Innovative Smart Grid Technologies-Asia (ISGT Asia) (pp. 99-104). IEEE.
Chen, K., Chen, K., Wang, Q., He, Z., Hu, J., & He, J. (2018). Short-term load forecasting with deep residual networks. IEEE Transactions on Smart Grid, 10(4), 3943-3952.
Chen, B.J., Chang, M.W., & Lin, C. J. (2004). Load forecasting using support Ector machines: A study on EUNITE competition 2001 IEEE (Trans.) ower Syst, 19(4), 1821–1830.
Datar, N., Bhoyar, S., Khan, A., Dekapurwar, S., Wankhede, H., Sonone, S.(2021). Solar Power Monitoring system using IoT. Journal of Emerging Trends in Electrical Engineering, 3(1).
Deng, Z., Wang, B., Xu, Y., Xu, T., Liu, C., & Zhu, Z. (2019). Multi-scale convolutional neural network with time-cognition for multi-step short-term load forecasting. IEEE Access, 7, 88058–88071. doi:10.1109/ACCESS.2019.2926137
Feng, C., Sun, M., & Zhang, J. (2020). Reinforced deterministic and probabilistic load forecasting via Q-learning dynamic model selection IEEE (Trans.) mart Grid, 11(2), 1377–1386
García, S., Luengo, J., & Herrera, F. (2015). Data preprocessing in data mining. Retrieved from http://link.springer.com/book/10.1007/978-3-319-10247-4#about. Cham, Switzerland: Springer.
Gilanifar, M., Wang, H., Sriram, L. M. K., Oz Guven, E. E., & Arghandeh, R. (June 2020). Multitask Bayesian Spatiotemporal Gaussian Processes for Short-Term Load Forecasting. IEEE Transactions on Industrial Electronics, 67(6), 5132–5143. doi:10.1109/TIE.2019.2928275
Gochhait, S., Patil, H., Hasarmani, T., Patin, V., & Maslova, O. (2022, November). Automated Solar Plant using IoT Technology. In 2022 4th International Conference on Electrical, Control and Instrumentation Engineering (ICECIE) (pp. 1-6). IEEE.
Gochhait, S., Asodiya, R., Hasarmani, T., Patin, V., & Maslova, O. (2022, November). Application of IoT: A Study on Automated Solar Panel Cleaning System. In 2022 4th International Conference on Electrical, Control and Instrumentation Engineering (ICECIE) (pp. 1-4). IEEE.
Gochhait, S., Leena, H., Sudheesh, V., Kumar, V., Singh, V., Srinivasan, H., & Badam, D. (2020, June). Smart Lights: How it Enhances Connectivity. In 2020 International Conference for Emerging Technology (INCET) (pp. 1-4). IEEE.
Han, J., Pei, J., & Kamber, M. (2011). Data mining: Concepts and techniques. Amsterdam. The Netherlands: Elsevier.
Hammad, M. A., Jereb, B., Rosi, B., & Dragan, D. (2020). Methods and models for electric load forecasting: a comprehensive review. Logist. Sustain. Transp, 11(1), 51-76. doi:10.2478/jlst-2020-0004
Hong, W. C., & Fan, G. F. (2019). Hybrid empirical mode decomposition with support vector regression model for short term load forecasting. Energies, 12(6), 1–16. doi:10.3390/en12061093
Jawad, M., Nadeem, M. S. A., Shim, S.O., Khan, I. R., Shaheen, A., Habib, N., Aziz, W. (2020). Machine learning based cost-effective electricity load forecasting model using correlated meteorological parameters. IEEE Access, 8, 146847–146864. doi:10.1109/ACCESS.2020.3014086
Jiang, H., Zhang, Y., Muljadi, E., Zhang, J. J., & Gao, D. W. (2016). A short-term and high-resolution distribution system load forecasting approach using support vector regression with hybrid parameters optimization. IEEE Transactions on Smart Grid, 9(4), 3341-3350.
Liang, Y., Niu, D., Cao, Y., & Hong, W. C. (2016). Analysis and modeling for China’s electricity demand forecasting using a hybrid method based on multiple regression and extreme learning machine: A view from carbon emission. Energies, 9(11), 941. doi:10.3390/en9110941
Madhukumar, M., Sebastian, A., Liang, X., Jamil, M., & Shabbir, M. N. S. K. (2022). Regression model-based short-term load forecasting for university campus load. IEEE Access, 10, 8891-8905.
Massana, J., Pous, C., Burgas, L., Melendez, J., & Colomer, J. (2015). Short-term load forecasting in a non-residential building contrasting models and attributes. Energy and Buildings, 92, 322-330.
Massana, J., Pous, C., Burgas, L., Melendez, J., & Colomer, J. (2016). Short-term load forecasting for non-residential buildings contrasting artificial occupancy attributes. Energy and Buildings, 130, 519-531.
Mele, E. (2019). A review of machine learning algorithms used for load forecasting at microgrid level. In Sinteza 2019-International Scientific Conference on Information Technology and Data Related Research (pp. 452-458). Singidunum University.
Okoye, A. E., & Madueme, T. C. (2016). A theoretical framework for enhanced forecasting of electrical loads, 6(6, June) p. 554, ISSN 2250- 3153.
Olagoke, M. D., Ayeni, A. A., & Hambali, M. A. (2016). Short term electric load forecasting using neural network and genetic algorithm. Int. J. Appl. Inf. Yst, 10(4), 22–28.
Patil, V. S., Morey, A. P., Chauhan, G. J., Bhute, S. S., & Borkar, T. S. (2019). A Review Paper on Solar Power Monitoring System using an IoT. International Journal of Computer Sciences and Engineering, 7(8). doi:10.26438/ijcse/v7i8.212215
Pirbazari, A. M., Sharma, E., Chakravorty, A., Elmenreich, W., & Rong, C. (2021). An ensemble approach for multi-step ahead energy forecasting of household communities. IEEE Access, 9, 36218-36240.
Prakash, A., Xu, S., Rajagopal, R., & Noh, H. (2018). Robust building energy load forecasting using physically based kernel models. Energies, 11(4), 862. doi:10.3390/EN11040862
Qiuyu, L., Qiuna, C. A. I., Sijie, L. I. U., Yun, Y. A. N. G., Binjie, Y., Yang, W., & Xinsheng, Z. (2017, November). Short-term load forecasting based on load decomposition and numerical weather forecast. In 2017 IEEE Conference on Energy Internet and Energy System Integration (EI2) (pp. 1-5). IEEE.
Semero, Y. K., Zhang, J., & Zheng, D. (2018). PV power forecasting using n integrated GA-PSO-ANFIS approach and Gaussian process regression used feature selection strategy. CSEE Journal of Power and Energy Systems, 4(2), 210–218. doi:10.17775/CSEEJPES.2016.01920
Su, H., & Jung, C. (2018). Perceptual enhancement of low light images based on two-step noise suppression. IEEE Access, 6, 7005-7018.
Subhasri, G., & Jeyalakshmi, C. (2018). A study of IoT based solar panel tracking system. Advances in Computational Sciences and Technology, 11(7), 537-545.
Wahyudi, T., & Arroufu, D. S. (2022). Implementation of Data Mining Prediction Delivery Time Using Linear Regression Algorithm. Journal of Applied Engineering and Technological Science (JAETS), 4(1), 84–92. https://doi.org/10.37385/jaets.v4i1.918
Wahyudi, T., & Silfia, T. (2022). Implementation of Data Mining Using K-Means Clustering Method to Determine Sales Strategy In S&R Baby Store. Journal of Applied Engineering and Technological Science (JAETS), 4(1), 93–103. https://doi.org/10.37385/jaets.v4i1.913
Yang, L., & Shami, A. On Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practice. arXiv 2020. arXiv preprint arXiv:2007.15745.
Yildiz, B., Bilbao, J. I., & Sproul, A. B. (2017). A review and analysis of regression and machine learning models on commercial building electricity load forecasting. Renewable and Sustainable Energy Reviews, 73, 1104–1122, un. doi:10.1016/j.rser.2017.02.023