Hybrid Quantum Network with Snow Geese-Elk Herd Optimization for Smart Load Shedding in Grids with Electric Vehicles and Photovoltaic Systems

Abstract

The increasing penetration of variable renewable energy and the growth of electric vehicles (EV) have created an urge for more sophisticated load management methods to ensure grid stability. Conventional load shedding (LS) methods are typically not equipped to manage the unpredictability brought about by these modern additions to the grid. This study introduces an innovative smart load-shedding strategy that uses a hybrid optimization model. At its core is a Quantum Neural Network (QNN), which enables intelligent and data-based load prioritization by evaluating factors such as load criticality, energy usage, responsiveness to demand, and operational flexibility. The required LS amount is calculated through a combined use of Snow Geese Optimization (SGO) and the Elk Herd Optimizer (EHO), with specific attention given to the flexibility offered by EVs to address the variability in photovoltaic (PV) power generation. Testing has been performed on the IEEE 33-bus network reveal a notable decrease in total load demand by around 33%, contributing to improved grid stability, with voltage levels staying close to 0.99 p.u. Additionally, the average load across the network buses dropped by roughly 52%. This hybrid approach not only ensures better performance but also achieves quicker convergence compared to existing optimization methods. The proposed intelligent LS method presents an effective strategy for preserving grid stability amid growing integration of renewables and EV by incorporating QNN with SGO and EHO while accounting for EV adaptability.