文献类型：期刊文献

英文题名：A novel technique with overhead in Multi-Path Network Aggregation by Machine Learning Framework (MPAA-MLF)

作者：Li, Xiangrong[1]

第一作者：李向荣

通讯作者：Li, XR[1]

机构：[1]Xinxiang Univ, Xinxiang 453003, Henan, Peoples R China

第一机构：新乡学院

通讯机构：[1]corresponding author), Xinxiang Univ, Xinxiang 453003, Henan, Peoples R China.|[11071]新乡学院;

年份：2023

外文期刊名：WIRELESS NETWORKS

收录：;EI(收录号：20231914070471);Scopus(收录号：2-s2.0-85158109365);WOS:【SCI-EXPANDED(收录号:WOS:000982783700002)】；

语种：英文

外文关键词：Wireless sensor networks; Multi-path network aggregation; Machine learning framework; Fuzzy inference system; Monti consensus clustering

摘要：Wireless Sensor Networks consist of a collection of nodes that transmit data from source to destination to make effective communication. The transmission is initiated by several routing protocols, which help to identify the optimal route to reach the destination. However, the existing researchers face overhead issues such as delay, transmission reliability, bandwidth, and residual energy. The network overhead difficulties reduce the packet delivery ratio, throughput and maximize the packet drop rate. The research issues are overcome by applying the Multi-Path Network Aggregation by Machine Learning Framework. This algorithm is used on the 500*500 simulation region, and every node is examined in terms of residual energy, transmission rate, and distance. These factors were examined using the Monti consensus clustering and fuzzy inference machine learning system. The consensus algorithm identifies the cluster head, and fuzzy rules are utilized to select the supercluster heads. In addition, the candidate nodes are selected to form the cluster, which helps to transmit the data from source to destination. The vector function and probability value are computed to identify the network aggregated multipaths. This process reduces the transmission delay and improves the overall network performance. The discussed MPAA-MLF was implemented using the NS2 simulator, ensuring 98.53% of the packet delivery rate.