Advancing Substation Demand Forecasting Efficiency with AI/ML-Powered Solutions: A Comparative Exploration of Nonlinear Techniques Versus Conventional Methods

This scholarly work proposes enhancing resource planning efficiency in power substations by leveraging AI and ML-based forecasting. Power substations play critical role in managing electricity supply and demand but face challenges in resource allocation leading to inefficiencies and impacting both capital and operational expenditure. Traditional planning methods rely on manual data analysis resulting in time-consuming processes and potential errors. To address this study advocates use of AI and ML to streamline resource planning. It involves data pipeline construction, outlier detection using advanced ML and precise 11-year forecasts with various ML-based time series techniques ultimately improving planning and resource optimization.