Dynamic computing task unloading method for mobile terminal in cellular network

Abstract

The invention relates to a dynamic computing task unloading method for a mobile terminal in a cellular network. The method comprises the following steps: establishing a multi-user system model in the cellular network; judging whether the calculation task meets an unloading condition or not, namely whether the calculation task of each calculation resource requester can meet judgment conditions of time delay and energy consumption at the same time or not, and if the judgment conditions can be met at the same time, the task needs to be unloaded; otherwise, the task cannot be subjected to calculation unloading; and allocating the calculation resources with a dynamic auction algorithm: namely the base station serves as a third party, namely an auction man-in-the-middle, and the calculation tasks meeting the unloading judgment in the step (2) are dynamically unloaded through the multi-round multi-node dynamic auction algorithm. According to the invention, the base station uses the auction algorithm to realize multiple rounds of unloading, and timely and dynamically adjusts the unloading of the calculation task according to the change of the network state; on the premise of improving the utilization efficiency of the computing resources, the weight coefficients of the energy consumption and the time delay are introduced, and the energy consumption and the time delay are optimized to a certain extent.

Description

technical field [0001] The invention relates to the technical field of computing offloading in mobile communications, in particular to a dynamic computing task offloading method for a mobile terminal in a cellular network. Background technique [0002] With the rapid development of mobile communications, the number of mobile terminal (Mobile Terminal, MT) devices has increased dramatically, and the ensuing computing requirements have also increased day by day. Computing offloading technology was born to solve computing needs. In the existing computing offloading technology, it mainly offloads computing resources to edge servers (Edge Server, MS), but sometimes for intensive tasks, MS is Not enough. Each computing resource requester has a task in which the computing resource requester receives a detachable computing task request. In order to make full use of the surrounding idle computing resource devices, computing tasks need to be offloaded. On this basis, using the idle ...

AI Technical Summary

Problems solved by technology

[0004] However, whether it is OLCD or heuristic scheme, although the efficiency of unloading has been improved to a certain extent, the considerations are not comprehensive enough.

Among them, OLCD is only static task offloading, and the computing tasks and idle resources considered are unchanged, but in fact, computing tasks and idle resources will change dynamically, and OLCD does not consider these dynamic changes

Although the heuristic scheme considers the dynamic unloading scenario, it divides the total channel into several sub-channels equally, which reduces the rate of computing offloading and increases the delay. For urgent computing tasks, it cannot be processed in a timely manner.

Images