Abstract
Increased connectivity is required to implement novel coordination and control schemes. IEC 61850-based communication solutions have become popular due to many reasons—object-oriented modeling capability, interoperable connectivity and strong communication protocols, to name a few. However, communication infrastructure is not well-equipped with cybersecurity mechanisms for secure operation. Unlike online banking systems that have been running such security systems for decades, smart grid cybersecurity is an emerging field. To achieve security at all levels, operational technology-based security is also needed. To address this need, this paper develops an intrusion detection system for smart grids utilizing IEC 61850’s Generic Object-Oriented Substation Event (GOOSE) messages. The system is developed with machine learning and is able to monitor the communication traffic of a given power system and distinguish normal events from abnormal ones, i.e., attacks. The designed system is implemented and tested with a realistic IEC 61850 GOOSE message dataset under symmetric and asymmetric fault conditions in the power system. The results show that the proposed system can successfully distinguish normal power system events from cyberattacks with high accuracy. This ensures that smart grids have intrusion detection in addition to cybersecurity features attached to exchanged messages.
Highlights
The integration of Information Technology (IT) with power systems gave birth to smart grids [1]
There are some intrusion detection systems proposed in the literature for Generic Object-Oriented Substation Event (GOOSE) messages [19,20], these works focus on statistical analysis based on parameters of current GOOSE messages
The major contributions of this work are as follows: (a) A novel machine learning-based intrusion detection system is developed for IEC
Summary
The integration of Information Technology (IT) with power systems gave birth to smart grids [1]. There are some intrusion detection systems proposed in the literature for GOOSE messages [19,20], these works focus on statistical analysis based on parameters of current GOOSE messages. There is no machine learning-based mechanism for detecting intrusion in power system communication networks employing. (a) A novel machine learning-based intrusion detection system is developed for IEC (b) A realistic power system communication dataset is obtained. This means new event has occurred and theinfirst message for this is used sent These parameters are pivotal in monitoring the events in a power system in the proposed intrusion detection system later. Problem.”InInorder order to to fill fill this theythey are used to trigger actions in in devices, this this knowledge gap, a machine learning-based intrusion detection algorithm is developed
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
