Optimal Cost And Energy Scheduling of Polyphase Energy Management System-Machine Learning Approach

The energy crisis has paved the way for the usage of a variety of alternative energy sources that have a lower environmental impact. Solar and wind energy are two viable alternative energy sources with stochastic behavior in nature. These renewable energy sources can be integrated with a diesel generator to create a poly-phase energy management system that can meet demand while keeping the important continuous load connected to it at a low cost. Due to their intermittent nature, these sources cannot provide a constant output because they are weather and time-dependent. As a result, having appropriate backup diesel generators to provide continuous power output throughout the day is always thought required. The stand-alone or grid-connected mode of operation for the poly-phase energy system with backup is available. Both of these modes necessitate careful selection and sizing of system components in order to meet demand on a continual basis, resulting in lower costs and greater reliability. So, in this paper, an attempt is made to design and develop a Machine Learning-based grid-connected polyphase energy management system that includes a combination of wind turbines and photovoltaic cells, as well as diesel generators, and is characterized by several objectives, including Loss of Power Supply Probability (LPSP) and Annualized Cost of System (ACS).