Empirical Modeling and Machine Learning Prediction of Operational Electrical Load, Power Quality, and Carbon Emissions in a Korean Steel Manufacturing Plant

The project looks at how energy management, power quality, and environmental sustainability intersect in heavy industry, using a Korean steel‑making plant as a case study. Steel production uses a lot of energy, which makes it hard to forecast loads, keep power quality stable, and track carbon emissions. The paper being studied suggests an empirical model combined with machine learning to: – predict the plant’s electrical load, – evaluate power‑quality metrics, and – estimate the related carbon emissions. Because the abstract is very brief, it does not give full details about the machine‑learning architectures or the size of the data sets. For this reason, the project’s implementation support centers on setting

up comparative tests of basic regression models and sequence‑based models. Students can investigate how variables such as operating conditions, production schedules, and grid measurements can be used as inputs to forecast: – active power demand, – harmonic distortion levels, and – indirect greenhouse‑gas emissions. This research gives M.Tech students a solid framework for building simulation models that balance industrial output with grid stability and decarbonization goals, while also showing the trade‑offs between simple empirical formulas and more advanced data‑driven predictions.

Message: Hi FE, I need help with “Empirical Modeling and Machine Learning Prediction of Operational Electrical Load, Power Quality, and Carbon Emissions in a Korean Steel Manufacturing Plant” in “Electrical Engineering”