Deep-Block Network for Cyberattack Mitigation and Assessment in Smart Grid Power System with Resilience Indices

Abstract

Distributed renewable energy sources, with widecommunication components in a microgrid infrastructure, makecyber security assessment and mitigation a developing cyber-physical system study. Extensive cybersecurity threads areprevailing in modernized smart grid. Hence, to detect and mitigatecyber threads an advanced cost-effective resilience cyber riskassessment and mitigation mechanism is needed. To enhancecyber-physical security in smart grids, a secured deep learningalgorithm with blockchain technology (BlockDeepNet) isproposed. Distributed secured data analysis is carried by usingdeep learning approach, while blockchain helps in theimplementation of secured decentralized resilient control. Tovalidate, real-time cosimulation on IEEE 15 bus system wasconducted. Also, for evaluating cyber security breach, four typesof cyberattacks were introduced to validate the effectiveness ofproposed security assessment and resilience operation. Weobtained normalized resilience indexkR1k2of 2.36 for gridcommunication failure, 0.91 for replay attack, 1.34 for false datainjection, and 1.74 for DoS attack. The obtained results onsimulation case study by real-time hardware in the loopimplementation showed that the proposed BlockDeepNetaccurately reduce load loss for various cyberattack and providerobust resiliency. Overall, this research provides a platform forcybersecurity assessment and enhanced resilience operation ofcyber-physical power energy system.