{"title":"Intelligent UAV-aided controller placement scheme for software-defined vehicular networks","authors":"Na Lin, Qi Zhao, Liang Zhao","doi":"10.1145/3457388.3458809","DOIUrl":null,"url":null,"abstract":"Recently, researchers have used long short-term memory (LSTM) networks and the bi-directional long short-term memory (Bi-LSTM) networks to process sequence data sets such as vehicle positions in software-defined vehicular networks (SDVN). In this paper, we present a three-component intelligent UAV-aided controller placement scheme (CPP) for SDVN. First, we use Bi-LSTM to model the real-time position of vehicles (traffic flow). Second, we implement a dynamic scheme to place controllers and UAVs (DCUPE) in the network based on the predicted flow. Third, in order to collect real-time traffic information and manage the network, we compute trajectories for the UAVs from real-time Bi-LSTM predictions of vehicle positions and an adaptive artificial bee colony algorithm for the traveling salesman problem (IDABC-TSP). We evaluate our proposed design as a function of energy cost, communication delay, and packet delivery ratio. Our experimental results show the effectiveness of our scheme on real geographical topologies.","PeriodicalId":136482,"journal":{"name":"Proceedings of the 18th ACM International Conference on Computing Frontiers","volume":"67 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 18th ACM International Conference on Computing Frontiers","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3457388.3458809","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Recently, researchers have used long short-term memory (LSTM) networks and the bi-directional long short-term memory (Bi-LSTM) networks to process sequence data sets such as vehicle positions in software-defined vehicular networks (SDVN). In this paper, we present a three-component intelligent UAV-aided controller placement scheme (CPP) for SDVN. First, we use Bi-LSTM to model the real-time position of vehicles (traffic flow). Second, we implement a dynamic scheme to place controllers and UAVs (DCUPE) in the network based on the predicted flow. Third, in order to collect real-time traffic information and manage the network, we compute trajectories for the UAVs from real-time Bi-LSTM predictions of vehicle positions and an adaptive artificial bee colony algorithm for the traveling salesman problem (IDABC-TSP). We evaluate our proposed design as a function of energy cost, communication delay, and packet delivery ratio. Our experimental results show the effectiveness of our scheme on real geographical topologies.