Reinforced learning for demand side management of smart microgrid based forecasted hybrid renewable energy scenarios

Abstract

Energy management on residential loads is crucial since the loads vary and costs are also high. Hence, to deal with that, this paper proposes a novel demand management strategy using an energy retailing procedure. Initially, the power of PV and wind systems are forecasted using a recurrent neural network, and then the forecasted power is used to feed a household load of six devices that are non-linear. To manage the power, the loads are regularly updated in the Q-table; if any loads get shut, then the power retailing is performed, from which the average cost of the power consumed is reduced by African vulture optimization. Further, demand management is tested by varying the hybrid power sources. Under PV, wind and battery scenarios, the net present value and levelized cost of energy are 5115.31$ and 8.7$/kWh, respectively.