Kecan Kou, L. Lei, Lijuan Zhang, Shengsuo Cai, Gaoqing Shen
{"title":"Intelligent Selection: A Neural Network-Based MAC Protocol-Selection Mechanism for Wireless Ad hoc Networks","authors":"Kecan Kou, L. Lei, Lijuan Zhang, Shengsuo Cai, Gaoqing Shen","doi":"10.1109/ICCT46805.2019.8947101","DOIUrl":null,"url":null,"abstract":"In wireless ad hoc networks, a suitable MAC protocol can provide better QoS (Quality of Service) guarantees. However, in modern warfare environment, the combat missions change rapidly. A fixed MAC protocol may be not suitable for the highly changeable environments and combat missions. To solve this problem, we propose a neural network-based MAC protocol-selection mechanism to select the optimal MAC protocol for new missions based on the real-time environment information of the battlefield, i.e., the intelligent selection (IS) algorithm. In IS, we prepare the empirical data set with massive mission data, and construct the learning model through making use of the neural network. Experimental results demonstrate that the prediction accuracy of the proposed IS algorithm is over 0.93.","PeriodicalId":306112,"journal":{"name":"2019 IEEE 19th International Conference on Communication Technology (ICCT)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 IEEE 19th International Conference on Communication Technology (ICCT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCT46805.2019.8947101","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
In wireless ad hoc networks, a suitable MAC protocol can provide better QoS (Quality of Service) guarantees. However, in modern warfare environment, the combat missions change rapidly. A fixed MAC protocol may be not suitable for the highly changeable environments and combat missions. To solve this problem, we propose a neural network-based MAC protocol-selection mechanism to select the optimal MAC protocol for new missions based on the real-time environment information of the battlefield, i.e., the intelligent selection (IS) algorithm. In IS, we prepare the empirical data set with massive mission data, and construct the learning model through making use of the neural network. Experimental results demonstrate that the prediction accuracy of the proposed IS algorithm is over 0.93.