Adaptively Offloading the Software for Mobile Edge Computing

In mobile edge computing (MEC), computation offloading is a promising way to support those resource-constrained mobile devices, since it moves some time-consuming computation activities to nearby edge servers. Owing to the geographical distribution of edge servers and mobility of mobile devices, the runtime environment of MEC is highly complex and dynamic, so it is challenging to efficiently support computation offloading in MEC. In the face of a highly complex and dynamic runtime environment, an "adaptive" model has become the inevitable demand for computation offloading in MEC, in which software perceives the environment, changes behavior and improves performance. However, it involves two main challenges: (1) Adaptability: The software often faces changes of runtime environment in MEC, so that the adaptation on offloading is needed. However, due to the inherent architecture of software, it is hard to utilize the dispersed computing resources and change the offloading scheme. (2) Effectiveness: When the environment changes, it needs to calculate which parts are worth offloading, and the reduced execution time must be greater than the network delay caused by computation offloading. In addition, the decision-making of offloading is expected to be made at runtime. This report introduces our research on adaptively offloading the software for MEC. First, the code of software can be automatically refactored to implement a special program structure supporting dynamic offloading in MEC [2, 3]. Second, the execution costs of offloading schemes can be accurately estimated without runtime execution [1, 3]. Third, new offloading strategies are proposed to reduce decision time to an acceptable level [4].