Hybrid Deep Learning Prediction Model For Blackhole Attack Protection In Wireless Communication

Abstract

Wireless communication consists of minimum battery storage with self organizing devices which are localized in random manner in order to monitor the environment to support the real time applications. Wireless communication maintains open access which leads to increase the malicious activities in the network. Mainly black hole attack is created in the network. As so to increase the battery power and to increase the network security in this paper we introduced Hybrid Deep Learning Prediction (HDLP) model in the wireless network. Our model mainly divided into two sections namely cluster based network and Auto Encoding for Key Management. The wide simulation experiments are conducted to analysis the performance of the network against black hole attack. The proposed model is also simulated and it is compared with the earlier model such as Deep Multi Task Learning (DMTL) and Deep Learning Based Defense Mechanism (DLDM). As the results, we found that our proposed model performed well in terms of Accuracy, End to End Delay, Energy Efficiency and Energy Consumption when compared with the earlier models.