基于虚拟机迁移的能量收集MEC系统资源分配策略

针对现有研究没有考虑用户移动性对移动边缘计算（mobile edge computing，MEC）服务器反馈计算结果影响的情况，提出一种基于虚拟机迁移的能量收集MEC系统资源分配策略。考虑用户移动性影响，分别给出用户移动性模型和能量收集模型；采用虚拟机迁移方式，把用户卸载给初始MEC服务器的计算任务转移到当前MEC服务器，由当前MEC服务器完成计算任务，计算结果直接反馈给用户；综合考虑用户卸载计算任务和MEC服务器反馈计算结果，将功率和子载波分配问题建模为混合整数非线性规划问题，在满足能量消耗、子载波分配和发射功率的约束条件下，最大化系统能量效率。为了降低求解复杂度，通过引入遗传算法，获得次优解。仿真结果表明，与基于遗传算法的局部功率或子载波分配方法相比，提出的方法具有更高的能量效率。

Resource allocation strategy for energy harvesting MEC system based on virtual machine migration

The effect of user mobility on result feedback of mobile edge computing (MEC) server is not considered in the existing research. A resource allocation strategy based on virtual machine migration is proposed in the energy harvesting MEC system. Mobility model and energy harvesting model are presented by taking user mobility into account. By adopting the way of virtual machine migration, the computational tasks offloaded by the user are transferred from the initial MEC server to the current MEC server. The computational results are directly fed back to the user after the current MEC server completes the computational tasks. By jointly considering offloading computational task by the user and results feedback of MEC server, the problem of power and subcarrier allocation is modeled as a mixed integer nonlinear programming problem. The objective is to maximize the system energy efficiency while satisfying the constraints of energy consumption, subcarrier allocation, and transmitting power. In order to reduce the computational complexity, the suboptimal solution is obtained by introducing a genetic algorithm. Simulation results show that the proposed method has higher energy efficiency than partial power or subcarrier allocation methods based on the genetic algorithm.