Energy Management in Microgrids with Uncertainty in EV and Renewable Sources

Microgrids are usually referred to as small-scale producer that generates their power from renewable energy sources and distribute with maintaining high quality and fewer losses. Energy management is a critical aspect of microgrid operation, and different techniques can be applied to minimize operational costs and maximize the use of available sources. In this paper, we have developed an energy management system that includes a demand response and day ahead strategy to manage the load demand and power generation of renewable sources with the help of a deep learning method (T-LSTM) to reduce operational costs. In addition, a novel improved arithmetic optimization algorithm technique is applied to further optimize the system. In the demand response strategy, the microgrid operator involves consumers to reduce their electricity usage during periods of high demand or when electricity prices are high, either through direct communication or automated systems. The outcome of this study shows that the improved arithmetic optimization algorithm technique is effective in reducing operational costs by up to 13%. The findings of this research can assist in the development of efficient and cost-effective energy management systems for microgrids, which can help to improve the overall stability and sustainability of the energy infrastructure.