.png){kind=icon}
返回
Self-adaptive bifold-objective rate optimization algorithm for Wireless Sensor Networks
.png){kind=icon}
PRE
AI
DOI：10.1016/j.simpat.2024.102984.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Wireless Sensor Network (WSN) is a set of several sensor nodes that are used for monitoring heterogeneous physical objects. In WSNs, irregular and bursty traffic Leads to the congestion problem, which incites a decrease in Packet Delivery Ratio (PDR) and increases packet loss as well as end-to-end delay. In the recent era, manifold efforts have been carried out to reduce network congestion however, these solutions have slow and premature optimization. To address optimization issues, this paper presents a self-adaptive source-sending rate optimization algorithm, which is a hybrid version of Non-dominated Sorting Genetic Algorithm III (NSGA-III) and Bifold-objective Proportional Integral Derivative (BPID) called N3-BPID. These techniques play a significant role in optimizing source rates to reduce network congestion. NSGA-III is a reference-based evolutionary approach, which dynamically configures the PID coefficients to get an optimal response. Furthermore, a novel bifold-objective fitness function is designed that balances the trade-offs between two PIDs performance indexes such as the Integral of Absolute Error and the Integral of Square Error. Due to simplicity and efficiency, an identically weighted aggregation mechanism is applied to ensemble both objectives into a single one. The proposed work is implemented to demonstrate a smart border surveillance application using Network Simulator v3 and compared with the state-of-the-art congestion control model Cuckoo Fuzzy PID (CFPID). The experimental result reveals that the proposed algorithm has significantly outperformed existing schemes in terms of PDR by 6.82%, packet loss by 24.52%, end-to-end delay by 15.31%, and queue length deviation by 8.93%.
Keyword:
Genetic algorithm
NSGA-III
Congestion control
Wireless sensor network
期刊
IF:
4.6
论文数:
2.6K
被引数:
4.8K
机构
引用论文
.png){kind=icon}
分享收藏An Evolutionary Many-Objective Optimization Algorithm Using Reference-Point-Based Nondominated Sorting Approach, Part I: Solving Problems With Box Constraints使用基于参考点的非支配排序方法的进化多目标优化算法，第一部分: 解决框约束问题
PREAI
分享收藏
查看更多内容