Task unloading and resource allocation scheme based on MEC

Abstract

Mobile edge computing (MEC) provides the advantages of low delay, low power consumption and high reliability based on a mobile network edge through provision of an IT service environment and cloud computing capacity, so the mobile edge computing becomes a hotspot of future 5G research. The invention discloses a task unloading and resource allocation scheme based on MEC. The scheme comprises the steps of setting an unloading decision and resource allocation joint optimization problem; optimizing an unloading decision through adoption of a coordinate descent method; carrying out subchannel allocation on users when user delay conditions are satisfied through adoption of an improved Hungarian algorithm and greedy algorithm; and converting energy consumption minimization problem into a power minimization problem, and converting the power minimization problem into a convex optimization problem, thereby obtaining the optimum sending powers of the users. According to the scheme, different delay requirements of different users can be satisfied, system total energy consumption can be minimized, and system performance can be effectively improved.

Description

Technical field [0001] The present invention relates to the technical field of mobile edge computing and wireless communication, and particularly relates to an MEC-based task offloading and resource allocation scheme. Background technique [0002] In recent years, with the continuous upgrading of mobile networks and intelligent mobile devices, the number of mobile Internet users has exploded. At present, the fifth generation of mobile communication (5G, the fifth generation of mobile technology) is facing new challenges with explosive data traffic growth and the coexistence of massive device connections. At the same time, the new business scenarios of 5G networks, such as interactive somatosensory games, face recognition, driverless driving, virtual reality, industrial Internet of Things communications, etc., are due to their impact on time delay, energy consumption, reliability and other indicators. Higher demand, in order to meet the corresponding development needs brought abo...

AI Technical Summary

Problems solved by technology

However, offloading tasks to the cloud data center located in the core network needs to go through the backhaul network, which will consume backhaul link resources. When a large number of services need to be offloaded to the cloud server, it will cause backhaul congestion and additional delay Therefore, in the emerging 5G scenarios in the future, a single cloud computing model will not be able to meet the business needs for low latency and high reliability as much as possible

Images