Scholarlink

This paper presents a comprehensive study on optimizing the Ad hoc On-Demand Distance Vector (AODV) routing protocol using Genetic Algorithms (GA) in Mobile Ad hoc Networks (MANETs). Through simulation, we evaluate the standard AODV and GA-enhanced AODV protocols on key metrics, including packet transmission, reception, and throughput, across a 6000-s period. Results demonstrate a 15% improvement in throughput and a 20% increase in packet delivery ratio with GA integration, compared to the baseline AODV. The GA-based optimization adjusts parameters such as crossover and mutation rates dynamically to enhance routing decisions. Our findings highlight the GA-enhanced protocol’s potential for real-world MANET applications, emphasizing its adaptability to dynamic environments and resource constraints. This study underscores the importance of heuristic optimization techniques in advancing MANET protocols and offers a foundation for further research into machine-learning-driven hybrid approaches.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Optimization of AODV Routing in MANET Using Genetic Algorithms: A Simulation-Based Comparative Analysis

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Abhishek Shukla,
  • Syed Wajahat Abbas Rizvi,
  • Soumen Kanrar

摘要

This paper presents a comprehensive study on optimizing the Ad hoc On-Demand Distance Vector (AODV) routing protocol using Genetic Algorithms (GA) in Mobile Ad hoc Networks (MANETs). Through simulation, we evaluate the standard AODV and GA-enhanced AODV protocols on key metrics, including packet transmission, reception, and throughput, across a 6000-s period. Results demonstrate a 15% improvement in throughput and a 20% increase in packet delivery ratio with GA integration, compared to the baseline AODV. The GA-based optimization adjusts parameters such as crossover and mutation rates dynamically to enhance routing decisions. Our findings highlight the GA-enhanced protocol’s potential for real-world MANET applications, emphasizing its adaptability to dynamic environments and resource constraints. This study underscores the importance of heuristic optimization techniques in advancing MANET protocols and offers a foundation for further research into machine-learning-driven hybrid approaches.