Mobility support for fog computing and SDN approach.pdf -...

This preview shows page 1 - 2 out of 7 pages.

53 IEEE Communications Magazine May 2018 0163-6804/18/$25.00 © 2018 IEEE A BSTRACT The emerging real-time and computation-in- tensive services driven by the Internet of Things, augmented reality, automatic driving, and so on, have tight quality of service and quality of expe- rience requirements, which can hardly be sup- ported by conventional cloud computing. Fog computing, which migrates the features of cloud computing to the network edge, guarantees low latency for location-aware services. However, due to the locality feature of fog computing, main- taining service continuity when mobile users trav- el across different access networks has become a challenging issue. In this article, we propose a novel software-defined-networking-based fog computing architecture by decoupling mobili- ty control and data forwarding. Under the pro- posed architecture, we design efficient signaling operations to provide seamless and transparent mobility support to mobile users, and present an efficient route optimization algorithm by consider- ing the performance gain in data communications and system overhead in mobile fog computing. Numerical results from extensive simulations have demonstrated that the proposed scheme can not only guarantee service continuity, but also great- ly improve handover performance and achieve high data communication efficiency in mobile fog computing. I NTRODUCTION With the widespread deployment of advanced wireless and electronic technologies, smart devic- es have been equipped with sensors, cameras, communication chips, and so on, enabling them to collect a huge amount of data in the smart city environment [1]. According to the report from Harald et al. , 50 to 100 billion smart devices will connect to the Internet by 2020 [2], which will stimulate ever more rapid growth of data traf- fic. For example, Cisco has predicted that smart devices will generate 507.5 ZB/year by 2019 [3]. By data mining, analysis, and decision mak- ing with the collected big data from distributed devices, a number of promising services including smart home/building, smart healthcare, intelligent transportation, and so on will greatly change the way we work, live, and play [4]. Even though smart devices are becoming more and more powerful, running resource demanding applications at terminals is still constrained by lim- ited battery support and computation capacity [5, 6]. A feasible solution is to offload the huge processing to conventional cloud centers. Howev- er, delivering a large volume of collected data to remote centers not only induces heavy bandwidth and energy consumption that impose pressure on network infrastructure, but also prolongs the end- to-end delay of data traffic, which cannot be tol- erated by real-time applications [7]. For example, when a traffic accident occurs, it is first reported to a remote server located at the transportation administration department, and alert information generated by the server has to pass through the wired network and then be broadcast to near- by vehicles by vehicle-to-infrastructure commu- nications. As a result, the large round-trip time

  • Left Quote Icon

    Student Picture

  • Left Quote Icon

    Student Picture

  • Left Quote Icon

    Student Picture