Mitigation of cost consumption and manage power flows in multi-purpose microgrid using GRU controller-based energy management system

The demand for energy on the global is rising quickly, and the majority of that demand is met by the production of traditional fossil fuels. An original idea for incorporating renewable and hybrid energy sources to a grid was known as microgrid model. For proper power sharing between each component in the microgrid to ensure efficient, dependable, and cost-effective operation, Energy Management Systems (EMS) were crucial in microgrids through multiple energy resources and storage systems. Improper source prediction at the appropriate period was the issue that occurred in the EMS. This problem with efficiency causes a number of power-related issues on the load side and raises electricity costs. To mitigate this impacts, a novel deep learning controller-based EMS was proposed to manage the power flows at all period and reduce the cost of end users. Minimization of microgrid total electricity cost and total annual emission were considered as the primary objectives of the proposed model. Microgrid was designed with PV, tidal, grid, and battery, and in the demand side both hospital and home usages were considered. An actual dataset was developed according to the load activation power demand with its corresponding source power cost. Using this dataset, the deep learning controller was designed, and its performance was further improved through the coati optimization algorithm. The designed controller was fit in the EMS to select the proper source at the appropriate load demand period. The working states of the proposed model were observed under grid linked, and grid disliked mode of operation. The proposed deep learning controller offers 99.7% accuracy and 99.5% precision, and the results were compared to several other existing approaches. The outcomes demonstrate that the deep learning EMS approach was capable of interacting with many power sources and offer effective power management at a reasonable cost.