Context information based cyber security defense of protection system

With the development of substation automation system, it is now feasible for the Intelligent Electronic Devices (IEDs) based protection system to collect its measurements from electronic instrument transformers through communication network such as Ethernet based LAN. Application of wide area broadband network in power utilities introduces underlying danger for protection system to mal-operate when receiving fake data packages from intruder. This paper proposes to identify vicious fault using context information such as voltage and current of the same substation. When protection system detects fault based on measurements transmitted through network, it collects all measurements of the substation and feed these data to a Probabilistic Neural Network (PNN). Thereafter, the fault caused by fake data that differs from the known fault pattern can be identified and blocked.