Federated Blockchain Model for Cyber Intrusion Analysis in Smart Grid Networks

Abstract

Smart internet of things (IoT) devices are used to manage domestic and industrial energy needs using sustainable and renewable energy sources. Due to cyber infiltration and a lack of transparency, the traditional transaction process is inefficient, unsafe and expensive. Smart grid systems are now efficient, safe and transparent owing to the development of blockchain (BC) technology and its smart contract (SC) solution. In this study, federated learning extreme gradient boosting (FL-XGB) framework has been developed along with BC to learn the intrusion inside the smart energy system. FL is best suited for a decentralized BC-enabled system to adapt learning models for trustworthy and reliable transactions. Many features and attributes of the Third International Knowledge Discovery and Data mining Tools Competition (KDD Cup 1999) dataset have been used in this study to perform experimental analysis. The likelihood of intrusions in the network is mathematically stated. The participant nodes run the BC based FL-Smart Contract (SC) algorithms to detect network intrusions. FL provided aggregated learning results from the experiment that was 99% accurate in predicting network intrusion. The experimentally determined block storage gain and retrieval gain were 97.5% and 95.4% respectively. The intrusion in the smart grid network was evaluated, and the data indicated that there was 1.2% illegal access. Moreover, the learning system's accuracy, retrieval and storage intrusions, legal access and transaction processing times were considered for comparison. The proposed system outperformed contemporary research-developed systems targeted for the same application. Therefore, this study provides a guaranteed intrusion learning system and secure transaction system for smart grids.