This paper investigates the semantic extraction task-oriented dynamic multi-time scale user admission and resourceallocation in mobile edge computing (MEC) systems. Amid prevalence artifi cial intelligence applications in various industries,the offloading of semantic extraction tasks which are mainlycomposed of convolutional neural networks of computer vision isa great challenge for communication bandwidth and computing capacity allocation in MEC systems. Considering the stochasticnature of the semantic extraction tasks, we formulate a stochastic optimization problem by modeling it as the dynamic arrival of tasks in the temporal domain. We jointly optimize the system revenue and cost which are represented as user admission in the long term and resource allocation in the short term respectively. To handle the proposed stochastic optimization problem, we decompose it into short-time-scale subproblems and a long-time-scale subproblem by using the Lyapunov optimization technique. After that, the short-time-scale optimization variables of resource allocation, including user association, bandwidth allocation, and computing capacity allocation are obtained in closed form. The user admission optimization on long-time scales is solved by a heuristic iteration method. Then, the multi-time scale user admission and resource allocation algorithm is proposed for dynamic semantic extraction task computing in MEC systems. Simulation results demonstrate that, compared with the benchmarks, the proposed algorithm improves the performance of user admission and resource allocation efficiently and achieves a flexible trade-off between system revenue and cost at multi-time scales and considering semantic extraction tasks.

翻译：本文研究了移动边缘计算(MEC)系统中面向语义提取任务的动态多时间尺度用户准入与资源分配问题。在人工智能应用广泛渗透各行业的背景下，主要由计算机视觉卷积神经网络构成的语义提取任务卸载，对MEC系统的通信带宽与计算容量分配提出了严峻挑战。考虑到语义提取任务的随机特性，我们通过将任务建模为时间域上的动态到达过程，构建了随机优化问题。我们联合优化系统收益与成本，其中收益表征为长期用户准入，成本表征为短期资源分配。为处理所提出的随机优化问题，采用李雅普诺夫优化技术将其分解为短时间尺度子问题与长时间尺度子问题。随后，以闭式解形式获得包含用户关联、带宽分配与计算容量分配在内的短时间尺度资源分配优化变量。针对长时间尺度上的用户准入优化，采用启发式迭代方法求解。进而提出面向MEC系统动态语义提取任务计算的多时间尺度用户准入与资源分配算法。仿真结果表明，与基准方案相比，所提算法有效提升了用户准入与资源分配性能，并在考虑语义提取任务的多时间尺度上实现了系统收益与成本间的灵活权衡。