移动边缘计算中的时延和能耗均衡优化算法

为了提升移动边缘计算（MEC）网络中的任务卸载效用，提出了一种基于任务卸载增益最大化的时延和能耗均衡优化算法.通过分析通信资源和计算资源对时延和能耗这2种性能指标的制约关系，将原问题分解为联合发射功率子信道分配子问题和MEC计算频率分配子问题.通过Karush-Kuhn-Tucker条件，导出了最优的MEC计算频率闭式解.此外，提出了一种基于二分法的发射功率分配算法和基于匈牙利二部图匹配的子信道分配算法.仿真结果表明，提出的算法相比传统算法可以显著提升用户的任务卸载效用.

A Delay and Energy Tradeoff Optimization Algorithm for Task Offloading in Mobile-Edge Computing Networks

In order to enhance the task offloading utility in mobile-edge computing (MEC) networks,a delay and energy tradeoff optimization algorithm was proposed for maximizing the users' task offloading gains. The original optimization problem was decomposed into two sub-problems,i.e.,the joint transmit power and sub-channel allocation sub-problem and the MEC computing frequency allocation sub-problem,upon the analysis of the restriction of communication and computation resources to the delay and energy consumption performances. The optimal MEC computing frequency was directly derived in the closed form by the Karush-Kuhn-Tucker condition. In addition,an efficient bisection method based transmit power allocation algorithm and a bipartite graph matching based sub-channel allocation algorithm were proposed,respectively. Numerical simulation results showed that,the proposed algorithm could improve the task offloading utility remarkably when compared with some traditional algorithms.