为营造学院良好的学术环境氛围，本周将举办学术交流汇报，供师生和学生之间相互交流讨论，具体安排如下。        

日期：2020年9月22日（周二）  

时间：19：00（晚上七点）  

汇报人：18级 软件工程 吴文兵  

研究方向：移动边缘计算  

论文题目：An Energy-Efficient Off-Loading Scheme for Low Latency in Collaborative Edge Computing

论文简介：Mobile terminal users applications, such as smartphones or laptops, have frequent computational task demanding but limited battery power. Edge computing is introduced to offlfload terminals’ tasks to meet the quality of service requirements such as low delay and energy consumption. By offlfloading computation tasks, edge servers can enable terminals to collaboratively run the highly demanding applications in acceptable delay requirements. However, existing schemes barely consider the characteristics of the edge server, which leads to random assignment of tasks among servers and big tasks with high computational intensity (named as ‘‘big task’’) may be assigned to servers with low ability. In this paper, a task is divided into several subtasks and subtasks are offlfloaded according to characteristics of edge servers, such as transmission distance and central processing unit (CPU) capacity. With this multi-subtasks-to-multi-servers model, an adaptive offlfloading scheme based on Hungarian algorithm is proposed with low complexity. Extensive simulations are conducted to show the effificiency of the scheme on reducing the offlfloading latency with low energy consumption.   

已被IEEE ACCESS录用：Digital Object Identifier 10.1109/ACCESS.2019.2946683  

论文题目：A Probability Preferred Priori Offloading Mechanism in Mobile Edge Computing

论文简介：Mobile edge computing (MEC) can provide computation and storage capabilities via edge servers which are closer to user devices (UDs). The MEC offlfloading system can be viewed as a system where each UD is covered by single or multiple edge servers. Existing works prefer a posterior design when task offlfloads, which can lead to increased workloads. To investigate the task offlfloading of edge computing in multi-coverage scenario and to reduce the workload during task offlfloading, a probability preferred priori offlfloading mechanism with joint optimization of offlfloading proportion and transmission power is presented in this paper. We fifirst set up an expectation value which is determined by the offlfloading probability of heterogeneous edge servers, and then we form a utility function to balance the delay performance and energy consumption. Next, a distributed PRiori Offlfloading Mechanism with joint Offlfloading proportion and Transmission (PROMOT) power algorithm based on Genetic Algorithm (GA) is proposed to maximize the utility of UD. Finally, simulation results verify the superiority of our proposed scheme as compared with other popular methods.   

已被IEEE ACCESS录用：Digital Object Identifier 10.1109/ACCESS.2020.2975733  

论文题目：An Enhanced PROMOT Algorithm with D2D and Robust for Mobile Edge Computing

论文简介：With the development of the fifth-generation network (5G), the base station is becoming denser and denser, which leads to the user device is covered by multiple edge servers in mobile edge computing. Based on this, user devices have more options to decide on which server to offload the tasks. However, there may be still a few user devices located on the edge of a region that is not covered by any edge servers. The user device can only execute tasks locally resulting in excessive latency or energy consumption. To solve the problem, in this paper, an Enhanced PRiori Offloading Mechanism with joint Offloading proportion and Transmission (EPROMOT) power algorithm is proposed. Firstly, a mobile edge computing (MEC) model with device-to-device (D2D) technology is proposed. Then a tradeoff problem consists of the overhead of latency and energy consumption is formulated. Next, a Genetic algorithm is adopted to resolve the tradeoff problem. Besides a prevention mechanism is proposed to increase the robust when the edge server is shut down during the offloading time slot. Finally, experiments have performed to show the outperformance of the EPROMOT algorithm.   

已被Journal of Internet Technology录用。