Multi agent system based smart grid anomaly detection using blockchain machine learning model in mobile edge computing network

Abstract

Based on Advanced Metering Infrastructures (AMIs), which enable bidirectional communication between the utility provider and the customer to improve reliability and customer satisfaction, smart grids are deemed completely indispensable in the next generation of electricity networks. Using blockchain machine learning in mobile edge computing for multi-agent systems (MAS), this research proposes a unique approach for smart grid anomaly detection. Here, a blockchain encoder adversarial multi-agent gradient neural network is used to identify anomalies in the smart grid network. Edge Computing reduces traffic and delays communication by shifting processing, data, and services from centralised clouds to Edge Servers (ESs). In terms of prediction accuracy, quality of service, scalability, and anomaly detection rate, experimental investigation is conducted for a variety of smart grid anomaly analysis datasets. The suggested method achieved 89 % scalability, 95 % prediction accuracy, 92 % QoS, and 85 % anomaly detection rate.