Cyber Security in Power Systems Using Meta-Heuristic and Deep Learning Algorithms

Supervisory Control and Data Acquisition system linked to Intelligent Electronic Devices over a communication network keeps an eye on smart grids’ performance safety. The lack of algorithms protecting the power protocols makes them vulnerable cyberattacks, which can result in hacker introducing false data into operational network. This delayed attack detection, might harm infrastructure, cause financial loss, or even fatalities. Similarly, attackers may be able feed with fake information hoax operator algorithm making bad decisions at crucial moments. paper attempts identify classify such cyber-attacks by using numerous deep learning optimizing features metaheuristic algorithm. We proposed Restricted Boltzmann Machine-based nature-inspired artificial root foraging optimization Using publicly available dataset produced Mississippi State University’s Oak Ridge National Laboratory, simulations are run Jupiter Notebook. Traditional supervised machine like Artificial Neural Networks, Convolutional Support Vector Machines measured demonstrate effectiveness algorithms. Simulations show that superior results, accuracy 97.8% for binary classification, 95.6% three-class 94.3% multi-class classification. Thereby outperforming its counterpart terms accuracy, precision, recall, f1 score.