Optimal Model for Effective Power Scheduling using Levenberg-Marquardt Optimization Algorithm

Abstract

A well-organized scheduling method is needed to meet the time-varying power necessities. The distribution of power in forthcoming days must be scheduled. The system's accuracy extensively impinges on economic function and reliability. At peak load time, the load detaching procedure is necessary for decreasing the demand load. This complexity is conquered by the present system by forecasting the load centered on the constraints which affect the load. Predicting and scheduling load based on prior data is an exigent process. It isn't easy to manage the load when an unpredicted alteration occurs. It is feasible to precede the accessible demand for the load with the advances in artificial intelligence tools. The Levenberg-Marquardt Optimization-based backpropagation technique is employed in artificial neural networks for optimal learning purposes and to diminish error. The outcomes are then contrasted with correlation exploration.