Open Access iconOpen Access

ARTICLE

crossmark

Secrecy Outage Probability Minimization in Wireless-Powered Communications Using an Improved Biogeography-Based Optimization-Inspired Recurrent Neural Network

Mohammad Mehdi Sharifi Nevisi1, Elnaz Bashir2, Diego Martín3,*, Seyedkian Rezvanjou4, Farzaneh Shoushtari5, Ehsan Ghafourian2

1 Department of Industrial Engineering, Iran University of Science and Technology, Narmak, Tehran, 16846-13114, Iran
2 Department of Computer Science, Iowa State University, Ames, Iowa, IA, 50011, USA
3 ETSI de Telecomunicación, Universidad Politécnica de Madrid, Madrid, 28040, Spain
4 Department of Engineering, California State University East Bay, Hayward, California, 94542, USA
5 Department of Industrial Engineering, Bu-Ali Sina University, Hamedan, 65178-38695, Iran

* Corresponding Author: Diego Martín. Email: email

(This article belongs to the Special Issue: Artificial Intelligence for Addressing Security and Communications Challenges of Internet-connected Critical Infrastructures)

Computers, Materials & Continua 2024, 78(3), 3971-3991. https://doi.org/10.32604/cmc.2024.047875

Abstract

This paper focuses on wireless-powered communication systems, which are increasingly relevant in the Internet of Things (IoT) due to their ability to extend the operational lifetime of devices with limited energy. The main contribution of the paper is a novel approach to minimize the secrecy outage probability (SOP) in these systems. Minimizing SOP is crucial for maintaining the confidentiality and integrity of data, especially in situations where the transmission of sensitive data is critical. Our proposed method harnesses the power of an improved biogeography-based optimization (IBBO) to effectively train a recurrent neural network (RNN). The proposed IBBO introduces an innovative migration model. The core advantage of IBBO lies in its adeptness at maintaining equilibrium between exploration and exploitation. This is accomplished by integrating tactics such as advancing towards a random habitat, adopting the crossover operator from genetic algorithms (GA), and utilizing the global best (Gbest) operator from particle swarm optimization (PSO) into the IBBO framework. The IBBO demonstrates its efficacy by enabling the RNN to optimize the system parameters, resulting in significant outage probability reduction. Through comprehensive simulations, we showcase the superiority of the IBBO-RNN over existing approaches, highlighting its capability to achieve remarkable gains in SOP minimization. This paper compares nine methods for predicting outage probability in wireless-powered communications. The IBBO-RNN achieved the highest accuracy rate of 98.92%, showing a significant performance improvement. In contrast, the standard RNN recorded lower accuracy rates of 91.27%. The IBBO-RNN maintains lower SOP values across the entire signal-to-noise ratio (SNR) spectrum tested, suggesting that the method is highly effective at optimizing system parameters for improved secrecy even at lower SNRs.

Keywords


Cite This Article

APA Style
Nevisi, M.M.S., Bashir, E., Martín, D., Rezvanjou, S., Shoushtari, F. et al. (2024). Secrecy outage probability minimization in wireless-powered communications using an improved biogeography-based optimization-inspired recurrent neural network. Computers, Materials & Continua, 78(3), 3971-3991. https://doi.org/10.32604/cmc.2024.047875
Vancouver Style
Nevisi MMS, Bashir E, Martín D, Rezvanjou S, Shoushtari F, Ghafourian E. Secrecy outage probability minimization in wireless-powered communications using an improved biogeography-based optimization-inspired recurrent neural network. Comput Mater Contin. 2024;78(3):3971-3991 https://doi.org/10.32604/cmc.2024.047875
IEEE Style
M.M.S. Nevisi, E. Bashir, D. Martín, S. Rezvanjou, F. Shoushtari, and E. Ghafourian "Secrecy Outage Probability Minimization in Wireless-Powered Communications Using an Improved Biogeography-Based Optimization-Inspired Recurrent Neural Network," Comput. Mater. Contin., vol. 78, no. 3, pp. 3971-3991. 2024. https://doi.org/10.32604/cmc.2024.047875



cc Copyright © 2024 The Author(s). Published by Tech Science Press.
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 430

    View

  • 189

    Download

  • 0

    Like

Share Link