Task Allocation for Multi-APs with Mobile Edge Computing

Mobile Edge Computing(MEC) and Ultra-Dense Network(UDN) are two key technologies in next-generation network. UDN can bring a lot of convenience to MEC because small cells in UDN are close to users. However, the integration of these two technologies may bring many problems and one of the problems is task offloading. In this paper, we consider a practical application that contains many dependent subtasks. Some of these subtasks can be executed in parallel. We model the application as a Directed Acyclic Graph (DAG). The UE decides which subtask should be uploaded to which AP. We formulate this problem as a scheduling problem, which is NP-hard. In order to solve this problem, we propose a heuristic algorithm based on the list scheduling algorithm, called Unified Minimum Finish Time Algorithm. This algorithm jointly considers transmission time between APs and offloading time from UE to APs. Simulation results show that our proposed algorithm can significantly improve performance (compared to three baseline policies).

[1]  Byung-Gon Chun,et al.  CloneCloud: elastic execution between mobile device and cloud , 2011, EuroSys '11.

[2]  Sergio Barbarossa,et al.  Small Cell Clustering for Efficient Distributed Fog Computing: A Multi-User Case , 2015, 2015 IEEE 82nd Vehicular Technology Conference (VTC2015-Fall).

[3]  Alec Wolman,et al.  MAUI: making smartphones last longer with code offload , 2010, MobiSys '10.

[4]  Michael Pinedo,et al.  Scheduling: Theory, Algorithms and Systems Development , 1992 .

[5]  Min Dong,et al.  Joint offloading decision and resource allocation for multi-user multi-task mobile cloud , 2016, 2016 IEEE International Conference on Communications (ICC).

[6]  Pan Hui,et al.  ThinkAir: Dynamic resource allocation and parallel execution in the cloud for mobile code offloading , 2012, 2012 Proceedings IEEE INFOCOM.

[7]  Zhisheng Niu,et al.  A Cooperative Scheduling Scheme of Local Cloud and Internet Cloud for Delay-Aware Mobile Cloud Computing , 2015, 2015 IEEE Globecom Workshops (GC Wkshps).

[8]  Sergio Barbarossa,et al.  Small cell clustering for efficient distributed cloud computing , 2014, 2014 IEEE 25th Annual International Symposium on Personal, Indoor, and Mobile Radio Communication (PIMRC).

[9]  Bo Hu,et al.  User-centric ultra-dense networks for 5G: challenges, methodologies, and directions , 2016, IEEE Wireless Communications.

[10]  Min Dong,et al.  Joint offloading and resource allocation for computation and communication in mobile cloud with computing access point , 2017, IEEE INFOCOM 2017 - IEEE Conference on Computer Communications.

[11]  Vikram Krishnamurthy,et al.  Femto-Cloud Formation: A Coalitional Game-Theoretic Approach , 2014, 2015 IEEE Global Communications Conference (GLOBECOM).

[12]  Anthony A. Maciejewski,et al.  Task Matching and Scheduling in Heterogenous Computing Environments Using a Genetic-Algorithm-Based Approach , 1997, J. Parallel Distributed Comput..

[13]  Weisong Shi,et al.  Edge Computing: Vision and Challenges , 2016, IEEE Internet of Things Journal.

[14]  Jukka K. Nurminen,et al.  Energy Efficiency of Mobile Clients in Cloud Computing , 2010, HotCloud.

[15]  Tony Q. S. Quek,et al.  Offloading in Mobile Edge Computing: Task Allocation and Computational Frequency Scaling , 2017, IEEE Transactions on Communications.

[16]  Hui Tian,et al.  Fine-granularity based application offloading policy in cloud-enhanced small cell networks , 2016, 2016 IEEE International Conference on Communications Workshops (ICC).

[17]  K. Mani Chandy,et al.  A comparison of list schedules for parallel processing systems , 1974, Commun. ACM.