用于智能矿山移动边缘计算的二维动态匹配算法

Two-dimensional dynamic matching algorithm for mobile edge computing in intelligent mine

  • 摘要: 针对智能矿山井下移动边缘计算(MEC)应用中存在的由于资源分配不合理,移动用户将任务卸载到非最优边缘服务器,导致额外的传输时间和执行延迟,从而造成总任务完成率下降的问题,提出了一种基于偏好的二维动态匹配算法,优化MEC系统中资源分配决策。将1个时隙内MEC系统中移动用户的位置、任务所需计算量等数据发送至边缘服务器,根据设定的偏好值大小,形成边缘服务器对移动用户的偏好表,同时移动用户根据物理距离的不同,对所有边缘服务器也形成偏好表,2张偏好表相结合形成一张二维动态偏好表,进而抽象为一个二维矩阵,通过基于偏好的二维动态匹配算法对二维矩阵进行处理,得到移动用户和边缘服务器的匹配优化结果。仿真结果表明:与常规MEC场景卸载算法相比,基于偏好的二维动态匹配算法能够有效缓解大量突发任务场景下总任务完成率下降的问题,在极端情况下总任务完成率能够达到60%以上。

     

    Abstract: In the application of mobile edge computing(MEC) in intelligent mine, the mobile users unload tasks to non-optimal edge servers due to unreasonable resource allocation, which leads to extra transmission time and execution delay, thus resulting in the decrease of the total task completion rate. In order to solve the above problem, a two-dimensional dynamic matching algorithm based on preference is proposed to optimize the resource allocation decision in MEC system. The data of the position of a mobile user in MEC system and the calculation amount required by a task in one time slot is sent to the edge server. The preference table of the edge server for the mobile user is formed according to the set preference value. At the same time, the preference table for all the edge servers is formed by the mobile user according to different physical distances. The two preference tables are combined to form a two-dimensional dynamic preference table, which is abstracted into a two-dimensional matrix. The two-dimensional matrix is processed by a two-dimensional dynamic matching algorithm based on preference, and the matching optimization results of mobile users and edge servers are obtained. The simulation results show that compared with the conventional MEC scene unloading algorithm, the preference-based two-dimensional dynamic matching algorithm can effectively alleviate the problem of the decrease of the total task completion rate in a large number of sudden task scenes, and can achieve the total task completion rate of more than 60% in extreme cases.

     

/

返回文章
返回