In this paper, we study and present a management and orchestration framework for vehicular communications, which enables service continuity for the vehicle via an optimized application-context relocation approach. To optimize the transfer of the application-context for Connected and Automated Mobility (CAM) services, our MEC orchestrator performs prediction of resource availability in the edge infrastructure based on the Long Short-Term Memory (LSTM) model, and it makes a final decision on relocation by calculating the outcome of a Multi-Criteria Decision-Making (MCDM) algorithm, taking into account the i) resource prediction, ii) latency and bandwidth on the communication links, and iii) geographical locations of the vehicle and edge hosts in the network infrastructure. Furthermore, we have built a proof-of-concept for the orchestration framework in a real-life distributed testbed environment, to showcase the efficiency in optimizing the edge host selection and application context relocation towards achieving continuity of a service that informs vehicle about the driving conditions on the road.
翻译:在本文中,我们研究和提出车辆通信管理和管弦化框架,通过优化应用-文字迁移方法,使车辆能够保持服务连续性;为优化连通和自动化移动服务应用文字的转让,我们的MEC管弦乐队根据长期短期内存(LSTM)模式,对边缘基础设施的资源可用性进行预测,并通过计算多种标准决策算法的结果,对搬迁作出最后决定,同时考虑到资源预测,二)通信连接的耐久性和带宽,以及(三)网络基础设施中车辆和边端主机的地理位置;此外,我们还在现实生活中分布的试样环境中为管弦化框架建立了一个验证概念,以展示优化边端主机选择和应用背景迁移的效率,从而实现向车辆通报道路驾驶条件的服务连续性。