The deployment of autonomous nodes in Internet of Things networks is challenging, particularly in the context of an obstacle-rich environment. In order to handle the obstacles and improve multi-agent path-finding, this work presents a novel technique called conflict-based search with relocation agent, which combines adaptive node relocation and conflict resolution to improve the coverage of the terrain with energy-efficient manner. Path finding with avoiding obstacles, load balancing, and maintain energy usage are some of the factors that conflict-based search with relocation agent algorithm balances to optimize node deployment. The approach ensures that agents can easily resolve conflicts, save energy, and navigate obstacles dynamically by modifying their trajectories. Experimental simulations show that the proposed approach significantly improves network scalability, communication overhead, path efficiency, collision avoidance, and energy efficiency. With dependable performance in real-world obstacle-rich contexts, the results confirm that the algorithm is a strong option for intelligent and adaptive node positioning.

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

A Multi-factor Approach to Optimized IoT Node Deployment Using Intelligent Agent Coordination

  • Nainsi Soni,
  • Vaibhav Shah,
  • Saurabh Kumar

摘要

The deployment of autonomous nodes in Internet of Things networks is challenging, particularly in the context of an obstacle-rich environment. In order to handle the obstacles and improve multi-agent path-finding, this work presents a novel technique called conflict-based search with relocation agent, which combines adaptive node relocation and conflict resolution to improve the coverage of the terrain with energy-efficient manner. Path finding with avoiding obstacles, load balancing, and maintain energy usage are some of the factors that conflict-based search with relocation agent algorithm balances to optimize node deployment. The approach ensures that agents can easily resolve conflicts, save energy, and navigate obstacles dynamically by modifying their trajectories. Experimental simulations show that the proposed approach significantly improves network scalability, communication overhead, path efficiency, collision avoidance, and energy efficiency. With dependable performance in real-world obstacle-rich contexts, the results confirm that the algorithm is a strong option for intelligent and adaptive node positioning.