{"title":"LTE/Wi-Fi设备多路径调度的实验评估","authors":"Bahar Partov, D. Leith","doi":"10.1145/2980159.2980169","DOIUrl":null,"url":null,"abstract":"To improve network performance, LTE technology is rapidly being rolled out by network operators. At the same time almost all mobile devices also possess a WiFi interface which can potentially be used in tandem with LTE to further improve performance. Motivated by this and by the advantages of link aggregation, there is currently much interest in the transmission of data in parallel over LTE and WiFi. However, the design and evaluation of multi-path schedulers is challenging due to the fact that the path delays experienced in practice are non-stationary and, at present, poorly characterised. To start to address this challenge, in this paper we propose a trace-driven approach for performance evaluation of multi-path schedulers. This approach allows fair, reproducible comparisons that reflect actual performance since they are based on experimental data. We demonstrate the use of this approach to compare the performance of a number of schedulers.","PeriodicalId":433212,"journal":{"name":"Proceedings of the Tenth ACM International Workshop on Wireless Network Testbeds, Experimental Evaluation, and Characterization","volume":"105 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"10","resultStr":"{\"title\":\"Experimental evaluation of multi-path schedulers for LTE/Wi-Fi devices\",\"authors\":\"Bahar Partov, D. Leith\",\"doi\":\"10.1145/2980159.2980169\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"To improve network performance, LTE technology is rapidly being rolled out by network operators. At the same time almost all mobile devices also possess a WiFi interface which can potentially be used in tandem with LTE to further improve performance. Motivated by this and by the advantages of link aggregation, there is currently much interest in the transmission of data in parallel over LTE and WiFi. However, the design and evaluation of multi-path schedulers is challenging due to the fact that the path delays experienced in practice are non-stationary and, at present, poorly characterised. To start to address this challenge, in this paper we propose a trace-driven approach for performance evaluation of multi-path schedulers. This approach allows fair, reproducible comparisons that reflect actual performance since they are based on experimental data. We demonstrate the use of this approach to compare the performance of a number of schedulers.\",\"PeriodicalId\":433212,\"journal\":{\"name\":\"Proceedings of the Tenth ACM International Workshop on Wireless Network Testbeds, Experimental Evaluation, and Characterization\",\"volume\":\"105 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-10-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"10\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the Tenth ACM International Workshop on Wireless Network Testbeds, Experimental Evaluation, and Characterization\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/2980159.2980169\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the Tenth ACM International Workshop on Wireless Network Testbeds, Experimental Evaluation, and Characterization","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/2980159.2980169","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Experimental evaluation of multi-path schedulers for LTE/Wi-Fi devices
To improve network performance, LTE technology is rapidly being rolled out by network operators. At the same time almost all mobile devices also possess a WiFi interface which can potentially be used in tandem with LTE to further improve performance. Motivated by this and by the advantages of link aggregation, there is currently much interest in the transmission of data in parallel over LTE and WiFi. However, the design and evaluation of multi-path schedulers is challenging due to the fact that the path delays experienced in practice are non-stationary and, at present, poorly characterised. To start to address this challenge, in this paper we propose a trace-driven approach for performance evaluation of multi-path schedulers. This approach allows fair, reproducible comparisons that reflect actual performance since they are based on experimental data. We demonstrate the use of this approach to compare the performance of a number of schedulers.