RECLAIM: Renewable Energy Based Demand-Side Management Using Machine Learning Models

The diesel generators sets (DGs) and battery storage systems (BSS) are the essential energy sources in a modern high-rise buildings. In this paper DG, BSS Photovoltaic system (PV) has been considered to minimize grid power injection using centralized Energy Management System (EMS). Machine Learning (ML) techniques used predict performance of various regression models by comparing load curves. It includes Artificial Neural Network (ANN), Wide (WNN), Linear Regression (LR), Interaction (LR-I), Stepwise (LR-S), Fine Tree (RF-T), Coarse (RC-T) Gaussian Process (GPR) based techniques. Demand Side (DSM) such as peak shaving valley filling is integrated with ML technique Hybrid source (HS) system.The comparative analysis results depicts effective reshaping profile without scheduling or disconnecting loads. Matlab simulation software validate results.