Identification of False Stealthy Data Injection Attacks in Smart Meters Using Machine Learning and Blockchain

Abstract

The current challenging issue in the Advanced Metering Infrastructure (AMI) of the Smart Grid (SG) network is how to classify and identify smart meters under the effect of falsification attacks related to stealthy data, which are injected in such small numbers or percentages that it becomes hard to identify. The problem becomes challenging due to sudden variation in the pattern for the power consumption of electrical data, the existing approaches and techniques are making such stealthy data attacks unrecognizable. Therefore, to identify such a small portion of data attacks we proposed a novel solution using a combination of blockchain, Fog Computing (FC), and linear Support Vector Machine (SVM) with Principal Component Analysis (PCA). In this paper, we proposed a 3-tier blockchain-based architecture, an advanced system model and a classification algorithm in a blockchain-based FC environment. The blockchain system is used here to verify the electrical data transmission and transaction between the user and the utility centre. Whereas FC is used to provide real-time alert messages in case of any false attacks related to stealthy data. A detailed analysis of the generated results is conducted by benchmarking with the other state-of-the-art techniques. The algorithm and model show a marked improvement over other technologies and techniques. The simulation of the algorithm was conducted using iFogSim, Ganache, Truffle for compiling, Python editor tool, and ATOM IDE.