Energy Analytics and Comparative Performance Analysis Of Machine Learning Classifiers On Power Boiler Dataset

Energy utilization has exponentially increased expansively over the previous decade. Energy management is critical to future monetary thriving and natural security. Thermal energy plays a vital role in industrial development and in energy utilization. The thermal power station plans for variety on perfect utilization of heat sources accessories in the boiler. The aim of this paper is to enhance the competence to increase the energy utilization of chemical boiler. The machine learning techniques for thermal energy are being used over the past decade to predict the future thermal energy needs, accurately. M5P and Random Forest are energy demand forecasting techniques that are being adopted. The Objectives are achieved by the models that have been classified into three levels such as primary, secondary and tertiary air load. The scope of this application and techniques forecasting is quite large, and this article focuses on the methods used to predict boiler energy consumption.