Cyber Security of Smart Metering Infrastructure Using Hybrid Machine Learning Technique

An intrusion detection system may be included into the advanced metering infrastructure in order to protect a smart grid from being compromised by malicious cyber activity. In contrast, signature-based intrusion detection can only identify previously identified threats, but anomaly-based intrusion detection may detect even the most minute shifts in the parameter that is the subject of the inquiry. The increasing use of smart grids in electronic systems makes it necessary to categorise, identify, and put into action preventative measures against potential dangers. This paper presents a hybrid machine learning technique for the prediction of cyber security of smart metering infrastructure. Python Spyder 3.7 is the programme that is used to carry out the simulation. The findings of the simulation give a better prediction model and increased performance than the approach that was previously used.