Detection and mitigation of false data injection attack in DC–DC synchronous boost converter: A real‐time implementation using shallow neural network model

Abstract

AbstractWith implementing cyber‐physical systems, modern power systems are at continuous risk of cyber‐attacks. Sensor data that is communicated through the communication links is the most vulnerable entity. The attacker breaches the confidentiality of the data and affects the controller's performance, destabilizing the system. This article proposes a neural network‐based cyber‐attack detection and mitigation scheme to detect and mitigate false data injection attacks on the sensors. Neural networks are used to predict duty; a combination of a data sampler and binary attack detector detects the presence of an attack. Attack mitigation is performed in the final step by analysing the outputs of prediction and detection networks. The designed control scheme is demonstrated at the DC–DC converter level by considering the synchronous boost converter as a plant with an input voltage sensor, output voltage sensor, input current sensor, and output current sensor. The shallow neural network model is trained with appropriate hyperparameters to obtain a root mean square error of 0.003. The control scheme is designed and implemented in MATLAB Simulink platform and realized in real‐time hardware setup by deploying the neural network into the microcontroller and its results are explored.