Task Offloading Strategies for Cloud-Side Cooperation in Compute-Intensive Scenarios Based on Edge Computing

Abstract

In computationally intensive scenarios, a large number of the terminal device is accessed locally. In order for the service to complete, the device needs to complete their tasks within the short time period set by the developers. Mobile Edge Computing (MEC) is an emerging technology deployed at the edge network of devices such as terminals and base stations, which can effectively meet the needs of computation-intensive scenarios. In this paper, we study a task offloading strategy based on edge computing to solve computationally intensive scenarios. We propose a collaborative cloud-edge task offloading model based on the framework of Mobile Device (MD), Edge Node (EN), and Cloud Computing (CC). Then we analyze the communication and computational requirements of the model and propose a linear offloading solution idea. We leverage this idea to propose a scheme to minimize the overall delay in the scene. The problem of the model is transformed into a non-convex problem by transforming it into a convex optimization thus solving the optimal offloading decision. Simulation results show that the scheme can effectively solve the delay optimization problem for computationally intensive scenarios.