A Mathematical and Hybrid Deep Learning Model for Real-Time Intrusion Detection in IoT-Based Electric Vehicle Charging Stations

Abstract

The recent frame of IoT and Industrial IoT security brings new type of intrusion detection systems. We propose a new method for Intrusion Detection in IoT based EVCS with the integration of Convolutional Neural Network, Long Short-term Memory model and Gated Recurrent Unit. This work uses a naturally pervasive, and representative real-world security focusing on IoT typical applications to address the capillary layer inherent challenges (e.g. at each EVCS vs through IT infrastructure as compared peripheral equipment). We have tested this both with Binary and Multiclass exhaustively. The benchmarks are perfectly accurate (100 % binary class, 97.44% six-class classification and near ~96/90%% in fifteen classes that certainly sets a new bar for the going forward!) Collectively, the entire ensemble architecture demonstrates a scalable high performance mean so again this ways these accomplishments certify that CNN-LSTM-GRU-based complex models can be used in space-strapped and processing constrained Intrusion Detection system for IoT to perform consistently robust. The ensemble algorithm, which is open sourced on the GitHub under our simulation framework codebase also represents a significant improvement in securing Internet of Things based EVCS from various cyber security threats.