Multi-user Computation Offloading Algorithm for Mobile Edge Computing

Mobile Edge computing (MEC), a new computing model to deal with the growing data, can better meet the needs of users. However, the simple edge computation offloading strategy is no longer suitable for the current MEC architecture. To solve the computation offloading problem of computation-intensive and time-sensitive tasks in Mobile Edge Computing (MEC), a joint partial offloading and task priority computation offloading algorithm was proposed. Firstly, the algorithm comprehensively considers the computing capability of the mobile device, the time delay and energy consumption of computing the task to determine whether the task needs to be offloaded. Then, the priority is determined for the tasks that need to be offloaded and the MEC servers. Finally, according to the determined priority, the tasks with high priority are offloaded to the MEC servers with strong computing capability to complete resource allocation. The experimental results show that compared with the traditional computation offloading algorithms, the proposed algorithm can effectively reduce the time delay and energy consumption cost of the MEC system.

I. Introduction

With the popularization of the Internet and the continuous development of Internet of Things technology, the amount of data that mobile devices need to process is increasing rapidly. In order to solve the problems of computing load, excessive storage load and low real-time response capacity in remote data center, the concept of Mobile Edge Computing (MEC) is proposed [1]. Through providing computing services at the network edge, the MEC model can reduce the time delay and energy consumption costs associated with data transmission. Whether the tasks generated by mobile devices are offloaded, how many tasks are offloaded, and which MEC server they are offloaded play a vital role in improving the quality of user experience. However, there are still some shortcomings in the existing computation offloading algorithms in the MEC environment, for example, the optimization goal is too simple, the number and scale of tasks are too small, and the quality of user experience is poor.