IOT based energy management in smart grid under price based demand response based on hybrid FHO-RERNN approach

This manuscript presents a hybrid technique for IOT Based Energy Management (EM) in smart grid (SG) under-price based demand response (DR). The proposed method integrates the fire hawk optimizer (FHO) and Recalling Enhanced Recurrent Neural Network (RERNN), commonly called the FHO-RERNN method. The major goal of this research is to continuously monitor data from IoT-based communication architecture and optimally manage energy in a SG system by decreasing the power bill, reducing the peak-to-average ratio (PAR), and obtaining the preferred trade-off among electricity bills and user inconvenience in a SG. The FHO-RERNN method is used to optimize the energy consumption of a SG system. The method works by first predicting the energy demand of the SG system using RERNN. Then, FHO is used to optimize the energy consumption of the SG system by scheduling the operation of its various components. By then, the FHO-RERNN method is done in the MATLAB software as well as associated to several existing methods. From the simulation, it concludes that the performance of the FHO-RERNN method is compared to the existing methods. The proposed method takes lower time and cost, compared with existing approaches. Thus, the PAR value performance is 0.3 while compared to BCMO-ANFIS, CFA, GA methods.