Optimizing resource allocation and enhancing security in smart grid environments through a decentralized access control system with power theft detection mechanism

The smart grid upgrades an existing power grid with intelligence, such that data sharing can occur about things like customer data and energy consumption. However, several methods related to access management and theft detection currently exist, can be inflexible, have high computational costs, and their generalizations can be impaired by noisy sensor data. This work develops a secure, and efficient smart grid system that combines decentralized access control, and power theft detection. The major aim of the current technique is to develop a decentralized access control service with user revocation abilities while increasing smart grid security using information technology management. The method described in this paper will first create input data from the Theft Detection in Smart Grid Environment Dataset and process the data with a Fuzzy–Enhanced Kalman Filter (FEKF) to remove noise and outliers from the input data. The input data is sensed for power theft detection through the usage of a Quantum–enhanced Artificial Neural Network (QANN) that enables precise detection of illicit activity. To optimize resource allocation and access request routing, the Ship Rescue Optimization (SRO) algorithm is applied. The system is implemented and evaluated using the Python programming platform. When compared to the existing methods like African Vultures Optimization Algorithm (AVOA), Particle Swarm Optimization (PSO), and Whale Optimization Algorithm with Flower Mating Optimization (WOA–FMO), the proposed SRO achieves outstanding performance with a high accuracy of 98 %.