Adaptive Routing Protocol to Optimize the Quality of Service of MANET Using Neural Network

Year : 2025 | Volume : 12 | Issue : 03 | Page : 01 09
    By

    Awadhesh Kumar Rai,

  • Akhilesh A. Waoo,

  1. Assistant Professor, Department of Computer Science and Engineering, Amicable Knowledge Solution University, Satna, Madhya Pradesh, India
  2. Professor (Dean), Department of Computer Science and Engineering, Amicable Knowledge Solution University, Satna, Madhya Pradesh, India

Abstract

A MANET is a group of mobile nodes that create a temporary network without relying on centralized administration or standard supporting devices, often functioning as a conventional network. These dynamic environments present significant challenges for traditional routing and switching protocols, particularly in delivering Quality of Service (QoS) benchmarks such as bandwidth, latency, packet delivery ratio, and robustness. This study proposes an Adaptive Routing Protocol (ARP) leveraging Neural Network (NN) techniques to enhance QoS in MANETs. The framework incorporates a feed-forward neural network trained on network-specific parameters such as node density, signal strength, mobility patterns, and historical performance metrics. The NN is a decision-making engine that dynamically adjusts routing paths and switching criteria based on real-time network conditions, optimizing data transmission efficiency. Simulations conducted using standard QoS metrics demonstrate that the proposed ARSP significantly outperforms existing protocols like AODV, DSR, and OLSR in terms of latency reduction, increased packet delivery ratios, and improved overall network throughput. The NN’s ability to learn and adapt to changing network conditions provides a flexible solution that can be applied to different MANET scenarios. This research underscores the potential of machine learning techniques, especially neural networks, in addressing the complex routing challenges in MANETs while ensuring optimal quality of service for diverse applications.

Keywords: Adaptive routing protocol, DDPG, MANET, neural network, quality of service

[This article belongs to Journal of Mobile Computing, Communications & Mobile Networks ]

How to cite this article:
Awadhesh Kumar Rai, Akhilesh A. Waoo. Adaptive Routing Protocol to Optimize the Quality of Service of MANET Using Neural Network. Journal of Mobile Computing, Communications & Mobile Networks. 2025; 12(03):01-09.
How to cite this URL:
Awadhesh Kumar Rai, Akhilesh A. Waoo. Adaptive Routing Protocol to Optimize the Quality of Service of MANET Using Neural Network. Journal of Mobile Computing, Communications & Mobile Networks. 2025; 12(03):01-09. Available from: https://journals.stmjournals.com/jomccmn/article=2025/view=228325


References

  1. Bhatia A, Kumar A, Jain A, Kumar A, Verma C, Illes Z, Aschilean I, Raboaca MS. Networked control system with MANET communication and AODV routing. Heliyon. 2022 Nov 1; 8(11): e11678.
  2. Vargheese M, Bhatia S, Basheer S, Dadheech P. Improved Multi-Path Routing for QoS on MANET. Comput Syst Sci Eng. 2023 Jun 1; 45(3): 2521–2536.
  3. Chen Z, Zhou W, Wu S, Cheng L. An adaptive on-demand multipath routing protocol with QoS support for high-speed MANET. IEEE Access. 2020 Mar 5; 8: 44760–73.
  4. Baumgartner M, Papaj J, Kurkina N, Dobos L, Cizmar A. Resilient enhancements of routing protocols in MANET. Peer-to-Peer Netw Appl. 2024 Sep; 17(5): 3200–21.
  5. Affandi FF, Mahiddin NA, Hashim AD. MANET performance evaluation for DSDV, DSR and ZRP. Int J Adv Technol Eng Explor. 2023 Feb 1; 10(99): 244–256.
  6. Safari F, Kunze H, Ernst J, Gillis D. A novel cross-layer adaptive fuzzy-based ad hoc on-demand distance vector routing protocol for MANETs. IEEE Access. 2023 May 18; 11: 50805–22.
  7. Hande JY, Sadiwala R. Optimization of energy consumption and routing in MANET using Artificial Neural Network. J Integr Sci Technol. 2024; 12(1): 718.
  8. Bai J, Sun J, Wang Z, Zhao X, Wen A, Zhang C, Zhang J. An adaptive intelligent routing algorithm based on deep reinforcement learning. Comput Commun. 2024 Feb 15; 216: 195–208.
  9. Shah N, El-Ocla H, Shah P. Adaptive routing protocol in mobile ad-hoc networks using genetic algorithm. IEEE Access. 2022 Dec 21; 10: 132949–64.
  10. Danilchenko K, Azoulay R, Reches S, Haddad Y. Deep Learning for MANET routing. IEEE Trans Mach Learn Commun Netw. 2023 Oct 12; 1: 412–24.
  11. Shanthini J, Punitha P, Karthik S. Improvisation of Node Mobility Using Cluster Routing-based Group Adaptive in MANET. Comput Syst Sci Eng. 2023 Mar 1; 44(3): 2619–2636.
  12. Jesús-Azabal M, García-Alonso J, Galán-Jiménez J. Evaluating the quality of service of Opportunistic Mobile Ad Hoc Network routing algorithms on real devices: A software-driven approach. Ad Hoc Netw. 2024 Oct 1; 163: 103591.
  13. Ali AA, Hussein MK, Subhi MA. A classifier-driven deep learning clustering approach to enhance data collection in MANETs. Mesop J CyberSecur. 2024 Sep 26; 4(3): 36–45.
  14. Ahmed HA, Al-Asadi HA. An optimized link state routing protocol with a blockchain framework for efficient video-packet transmission and security over mobile ad-hoc networks. J Sens Actuator Netw. 2024 Mar 11; 13(2): 22.
  15. Oyelakin AM. Approaches for solving routing and security issues in mobile Ad-Hoc Networks (MANETS): A Review. Journal of Information Technology and Computing. 2023 Dec 30; 4(2): 20–30.
Regular Issue Subscription Review Article
Volume 12
Issue 03
Received 15/05/2025
Accepted 03/09/2025
Published 29/09/2025
Publication Time 137 Days
201

Login


My IP

PlumX Metrics