IoT-enabled EMS for grid-connected solar PV-fed DC residential buildings with hybrid HBA-DCGNN approach

This manuscript proposes a hybrid approach depending on the internet of things (IoT) for grid-tied solar photovoltaic (PV)-fed dc residential buildings. The hybrid approach combines the Honey Badger Algorithm (HBA) with density clustering and graph neural network (DCGNN), commonly referred to as the HBA-DCGNN method. The primary objective of the proposed method is to reduce customers' electricity costs while maintaining the desired level of comfort, such as interior temperature and appliance operation characteristics. The HBA algorithm optimizes power flow between the solar photovoltaic system, battery storage, and grid, while the DCGNN approach predicts solar PV power generation and energy demand in residential buildings. The proposed approach is done in MATLAB and is compared with the existing techniques, including the Random Forest Algorithm (RFA), Seagull Optimization Algorithm (SOA), and Wild Horse Optimizer (WHO). The outcome demonstrate that the proposed method lessens the costs of electricity by 1.12$ than the existing methods.