Scholarlink

Several real-time applications can benefit from wireless sensor networks (WSNs) because of their size, cost-effectiveness, and ease of distribution. It is possible for WSNs to change dynamically as a result of external or internal factors, requiring depreciating dispensable redesign. WSNs are traditionally explicitly programmed, making them hard to react dynamically. Q-learning based on K-Means can be used to avoid such scenarios. Q-learning is used to build a learning mechanism from past simulation data. In order to achieve minimal transmission delay, the work is estimated based on throughput, delay, network lifetime, and packet delivery ratio (PDR). The Q-learning-based mechanism is also investigated as an outcome of the simulation and rounds. Throughput, delay, network lifetime, and PDR analysis of the proposed mechanism are all validated by the comparative investigation against three existing models.

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

Optimal Cluster and Node Balancing Technique Using K-Mean Based on Q-Learning for Wireless Sensor Network

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Mohan Raparthi,
  • Sarath Babu Dodda,
  • Srihari Maruthi,
  • Ismail Keshta,
  • Abhishek Agarwal

摘要

Several real-time applications can benefit from wireless sensor networks (WSNs) because of their size, cost-effectiveness, and ease of distribution. It is possible for WSNs to change dynamically as a result of external or internal factors, requiring depreciating dispensable redesign. WSNs are traditionally explicitly programmed, making them hard to react dynamically. Q-learning based on K-Means can be used to avoid such scenarios. Q-learning is used to build a learning mechanism from past simulation data. In order to achieve minimal transmission delay, the work is estimated based on throughput, delay, network lifetime, and packet delivery ratio (PDR). The Q-learning-based mechanism is also investigated as an outcome of the simulation and rounds. Throughput, delay, network lifetime, and PDR analysis of the proposed mechanism are all validated by the comparative investigation against three existing models.