Using a Hybrid Algorithm with Intrusion Detection System based on Hierarchical Deep Learning for Smart Meter Communication Network

Abstract

Smart meters are central for renewable electricity generation and distributed integration. Smart metering concerns some intelligent metering devices use at the location of customer as well as processing, reading giving the information regular process on consumption to customer. Smart meters are Advanced Metering Infrastructure crucial element that they suggest two-way communication among the utilities of provider and consumers. Meter data modification could result in financial loss while physical damage to equipment, billing, required energy false prediction and so on. Data disclosing aids for monitoring activities of customer which cause attacks indirectly such as theft and so on. The proposed method is utilizing the new hybrid algorithm ACO-ABC Hybrid based on Swarm that integrates Ant Colony and Artificial Bee Colony (ABC) algorithms features for optimizing hyper-parameters and selection of feature. Algorithm of ACO-ABC is employed for implementing selection of feature and optimization of parameter before Intrusion Detection System based on Hierarchical Deep Learning (HDL). The results which are achieved from system of simulation proves that the proposed IDS based on DL detects attacks accurately. The comparison of proposed system with methods given in base paper and other papers using CICIDS2017 dataset ensures the efficiency of proposed system.