An extended mechanism to prevent distributed denial of service attack in DV-Hop localisation algorithm in wireless sensor networks
by Simarjeet Kaur; Navdeep Kaur; Kamaljit Singh Bhatia
International Journal of Internet Protocol Technology (IJIPT), Vol. 14, No. 2, 2021

Abstract: Distance Vector (DV)-Hop localisation scheme is one of the most successful localisation schemes. However, when network is interrupted with Distributed Denial of Service (DDoS) attack then the localisation process of DV-Hop scheme is badly affected. This paper has examined the effects of the DDoS attack on the DV-Hop algorithm. So, a mechanism consisting of swarm optimisation and machine learning is proposed to guard against DDoS attack. The architecture also designs a novel fitness function for Artificial Bee Colony (ABC). To check the effectiveness of the proposed fitness function of ABC, Neural Network with Gradient satisfaction is applied. The cross validation architecture further uses Mean Square Error (MSE) for the back propagation model and effectiveness is checked through a regression model as well. The evaluation is done in terms of Localisation error and Transmission loss. The simulation results show the reduction of 33% for localisation error and 27% for transmission loss respectively.

Online publication date: Thu, 15-Jul-2021

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Internet Protocol Technology (IJIPT):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com