الفهرس | Only 14 pages are availabe for public view |
Abstract Recently,there has been extensive utilization of smart grids as an internet of things application(IoT)in the field of power distribution .This is due to their flexi-bility to support the two-way flow of electricity and data .The critical nature of smart grids evokes traditional network attacks .Existing Smart grid(SG) solutions are less capable of ensuring secure and trustworthy operations .The large-scale nature of SGs and relianceonnetworkprotocolsfortrustmanagementmadeitsubjectedtocyber-attacks.Aparticularexampleofsuchasevereattackisthefalsedatainjection(FDI). FDI refers to a network attack, where smart meters’ measurements are manipulated to inject false data to mislead the decisions of the power utility,causing catastrophic results. In this thesis,the proposed solution exploits the secure nature of blockchains to construct a data management framework based on a public blockchain .The proposed framework enables trustworthy data storage,verification,and exchange between SG components and decision-makers. Miners are able to invest their computational power to verify blockchain transactions in a fully distributed manner.The mining logic employs machine learning(ML)techniques to identify the locations of compromised meters in the network,which are responsible for generating FDI attacks In return, miners receive virtual credit,which may be used to pay their electric bills.The presenteddesigncircumventssinglepointsoffailureandintentionalFDIattempts. The numerical results compare the accuracy of three different ML-based mining logic techniquesintwoscenarios:focusedanddistributedFDIattacksfordifferentattack levels.Finally,proposing a majority-decision mining technique for the practical case of an unknown FDI attack level |