Enhanced Power Demand Forecasting Accuracy in Heavy Industries Using Regression Learner – based Approached Machine Learning Model
Keywords:
power demand, forecasting, heavy industries; load; power generation; load; forecasted demandAbstract
For effective management of power systems in heavy industries, accurate power demand forecasting is essential. Traditional statistical models have been tried for this goal, but they frequently struggle to capture the intricate patterns and connections in the data. This paper proposes a method for predicting these power demands, it involves preparing the baseline data, training a surrogate model using a machine learning algorithm, and performing cross-validation to evaluate the performance of the model. To address the diversity in load behaviors and demand spike patterns, a statistical analysis-based machine learning algorithm selection approach is proposed to guide the accurate development of the surrogate model. This study provides a comprehensive framework for predicting the power demand, selecting appropriate machine learning algorithms, and avoiding overestimation. Results enable management to make better decisions, optimize energy usage, reduce costs, avoid penalties, and surcharges.
References
Y. -J. Lee and H. -J. Choi, "Forecasting Building Electricity Power Consumption Using Deep Learning Approach," 2020 IEEE International Conference on Big Data and Smart Computing (BigComp), Busan, Korea (South), 2020, pp. 542-544, doi: 10.1109/BigComp48618.2020.000-8.
Elamary, A. S., & Taha, I. B. (2021). Determining the shear capacity of steel beams with corrugated webs by using optimised regression learner techniques. Materials, 14(9), 2364.
Abd Rahaman, N. S., & Jumadi, N. A. (2021). Comparison of Regression Analysis using Origin, Matlab, and Regression Learner App in Formulating the Linear Equation for Leg Flexibility Index. Evolution in Electrical and Electronic Engineering, 2(2), 164-172.
Ekici, S., Unal, F., & Ozleyen, U. (2019). Comparison of different regression models to estimate fault location on hybrid power systems. IET Generation, Transmission & Distribution, 13(20), 4756-4765.
Karamdel, S., Liang, X., Faried, S. O., & Shabbir, M. N. S. K. (2022, December). A Regression Model-Based Short-Term PV Power Generation Forecasting. In 2022 IEEE Electrical Power and Energy Conference (EPEC) (pp. 261-266). IEEE.
Wang, Y., Wang, D., & Tang, Y. (2020). Clustered hybrid wind power prediction model based on ARMA, PSO-SVM, and clustering methods. IEEE Access, 8, 17071-17079.
E. Yuniarti, N. Nurmaini, B. Y. Suprapto and M. Naufal Rachmatullah, "Short Term Electrical Energy Consumption Forecasting using RNN-LSTM," 2019 International Conference on Electrical Engineering and Computer Science (ICECOS), Batam, Indonesia, 2019, pp. 287-292,
P. Virdi, Y. Narayan, P. Kumari and L. Mathew, "Discrete Wavelet Packet based Elbow Movement classification using Fine Gaussian SVM," 2016 IEEE 1st International Conference on Power Electronics, Intelligent Control and Energy Systems (ICPEICES), Delhi, India, 2016, pp. 1-5, doi: 10.1109/ICPEICES.2016.7853657.
P. Kumar and M. Biswas, "SVM with Gaussian kernel-based image spam detection on textual features," 2017 3rd International Conference on Computational Intelligence & Communication Technology (CICT), Ghaziabad, India, 2017, pp. 1-6, doi: 10.1109/CIACT.2017.7977283.
Narayan, V., & Daniel, A. K. (2022). Energy Efficient Protocol for Lifetime Prediction of Wireless Sensor Network using Multivariate Polynomial Regression Model. Journal of Scientific & Industrial Research, 81(12), 1297-1309.
