Power consumption prediction for steel industry

TL;DR

This paper presents a novel predictive model combining linear regression and KNN clustering to accurately estimate power consumption in the steel industry, aiding sustainable and efficient energy management.

Contribution

The study introduces a unique hybrid model that improves energy consumption prediction accuracy in the steel industry, addressing challenges posed by process variability.

Findings

Model achieves high prediction accuracy for steel industry energy use

Combines linear regression with KNN clustering for better load type identification

Supports sustainable practices through improved energy management

Abstract

The use of steel is essential in many industries, including infrastructure, transportation, and modern architecture. Predicting power consumption in the steel industry is crucial to meet the rising demand for steel and promoting city development. However, predicting energy consumption in the steel industry is challenging due to several factors, such as the type of steel produced, the manufacturing process, and the efficiency of the manufacturing facility. This research aims to contribute by creating a predictive model that estimates power consumption in the steel industry. The unique approach combines linear regression to predict a continuous variable related to power consumption and the KNN clustering method to identify the demanding load type. This study's novelty lies in the development of a model that accurately predicts energy consumption in the steel industry, leading to more sustainable and efficient practices. This research contributes to enabling industries to anticipate and optimize their energy consumption, leading to more sustainable practices and economic development.