Accurate and Efficient Performance Prediction for Mobile IoV Networks Using GWO-GR Neural Network

Authors

Lingwei Xu, Qilu University of Technology
Xinpeng Zhou, Qilu University of Technology
Yong Fu, Qilu University of Technology
Guanwu Jiang, Qingdao University of Science and Technology
Xu Yu, Qilu University of Technology
Miao Yu, Qingdao University
Neeraj Kumar, University of Petroleum and Energy Studies
Mohsen Guizani, Mohamed Bin Zayed University of Artificial IntelligenceFollow

Document Type

Article

Publication Title

IEEE Internet of Things Journal

Abstract

The explosive growth of Internet of Vehicle (IoV) applications has made information security a significant issue. Mobile IoV users are dynamic and the communication environment is very complex, which makes it very difficult to guarantee real-time secrecy communication performance. Thus, a reliable and effective evaluation and prediction of secrecy performance is critical. In this article, we have derived novel expressions for secrecy performance. A grey wolf optimization generalized regression (GWO-GR) algorithm is proposed to predict the secrecy performance and carry out the secrecy performance assessment. A generalized regression (GR) neural network is designed. Out of the input and output layers, the proposed GR network has a pattern layer and a summation layer, which can obtain a global convergence of network results. To further optimize the GR network, the grey wolf optimization algorithm is used to obtain the best spread factor for it, which can accelerate its rapid convergence. Through the simulated numerical results, we can obtain: 1) the proposed GWO-GR prediction algorithm is shown to provide better performance prediction results than other machine-learning-based methods; 2) in particular, the prediction accuracy is improved by 17.7%; and 3) the execution time has an 88.9% reduction.

First Page

16463

Last Page

16471

DOI

10.1109/JIOT.2022.3152739

Publication Date

2-18-2022

Keywords

Grey wolf optimization (GWO), Internet of Vehicle (IoV) communication networks, Performance prediction, Secrecy performance

Comments

IR Deposit conditions:

OA version (pathway a) Accepted version

No embargo

When accepted for publication, set statement to accompany deposit (see policy)

Must link to publisher version with DOI

Publisher copyright and source must be acknowledged

Recommended Citation

L. Xu et al., "Accurate and Efficient Performance Prediction for Mobile IoV Networks Using GWO-GR Neural Network," in IEEE Internet of Things Journal, vol. 9, no. 17, pp. 16463-16471, 1 Sept.1, 2022, doi: 10.1109/JIOT.2022.3152739.