Fog computing-based deep learning model for optimization of microgrid-connected WSN with load balancing

Abstract

The advancement of power grids leads to the concept of the microgrid. Microgrids are placed at the end of an entire grid-connected system. Wireless sensor networks (WSNs) are engaged in the management of power generation, electricity consumption, and power transmission and distribution. In power generation, WSNs detect the amount of power generated that is managed by a microgrid for large-scale applications. Also, a WSN needs to monitor the microgrid's transmission status for effective transmission of power. To overcome these challenges, this research aimed to incorporate a fog computing network for the optimization of a microgrid-connected WSN. In a grid-connected community (GCC), an energy model was developed to evaluate the energy and performance of microgrids with a WSN. The constructed FGWHO fog computing-based model was used to estimate the microgrid distance, power generation, and power demand within the network. Based on the collected information, the whale optimization algorithm was used to calculate the optimal values required for data transmission. The optimization model estimated the optimal distance, energy, and communication of the microgrids. These facilitated the reduced energy utilization and improved the throughput and the PDR of the grid-connected WSN.