Hybrid Renewable Energy Systems with Smart Power Management – A Comparative Study

About 1.5 million publics in the world do not have access to electricity and getting them access to it, has become the most pressing issue. Due to power shortages, the electrical supply faces instability and the households integrated with the grids, encounters frequent power outages. This is because of the insufficient power generation, which is brought on by fluctuating voltage levels and antiquated transmission cables. Therefore, it is mandatory to identify a decentralized source of energy, for providing uninterruptable power supply. In developing countries, there is a great demand towards Renewable Energy Sources (RES) like wind, solar, biogas, etc. The formation of Hybrid renewable energy systems (HRES) develops a realistic, as well as appealing approach for resolving the energy demands. These cost effective resources have only a minor impact on non-conventional energies. Therefore, the utilization of RES, provides better economic growth and efficient power management. Besides, Microgrid (MG) is an embedded network, which incorporates RES along with different loads and it assists in energy management. The MGs, to achieve optimum functionality, necessitates energy efficient storage units. The RES utilized in MGs, aids in providing energy stability and in case of excess energy production, it is stored in the storage units. The HRES incorporates a variety of EMS (Energy Management Systems) to maintain stability and energy management. In this paper, the techniques and algorithms that assists in energy management are evidently discussed. The goal of this paper is to examine the manner in which model interpretability is increased by reviewing prior studies that used interpretable machine learning approaches for energy management. Moreover, a comparative analysis is carried out between the different techniques, in order to observe the best optimal energy managing technique.