A hybrid approach based internet of things assisted power monitoring system for smart grid

Abstract

The increasing complexity of modern energy systems, like electric vehicle charging and smart grids, necessitates efficient optimization techniques for power management. In modern energy systems, such as electric vehicle charging and smart grids, is their inability to accurately model the complex, non-linear relationships and dynamic conditions in modern energy systems. They may lack adaptability, leading to inefficiencies and suboptimal performance. This manuscript proposes a hybrid approach that depends on the Internet of Things (IoT) aided power monitoring system for smart-grid (SG). The proposed hybrid strategy is combined with Dwarf Mongoose Optimization (DMO) and Quantum Neural Network (QNN). Typically, it’s referred to as the DMO-QNN technique. The primary goal of the DMO-QNN approach is to improve the efficiency of IoT-based energy monitoring, which can monitor and evaluate electrical characteristics such as load power, voltage, current, and active power usage. The DMO technique ensures increased system efficacy, improves living quality, and streamlines processes in a range of sectors. The QNN predicts the optimal control signal for the sensor. The proposed strategy has improved the efficiency of electrical parameters, like voltage, current, load-power, and active-power consumption. According to the simulation research, the proposed approach outperforms the current approaches in terms of efficiency, with a 99% rate. Overall, the proposed system achieves peak efficiency, confirming its effectiveness for intelligent energy management in modern smart grid environments.