Collaborative computing unloading method based on optical fiber-wireless network

Abstract

The invention discloses a collaborative computing unloading method based on an optical fiber-wireless network, which considers a centralized cloud and edge cloud collaborative computing unloading problem of multiple users in a multi-wireless channel interference environment in the structure of a hybrid optical fiber-wireless network. The method comprises the steps of firstly collecting computing tasks and related information of the network, calculating the task processing time of each task under different unloading modes and the energy consumption of mobile equipment, eliminating tasks which do not meet time and energy consumption requirements in all unloading modes, and then designing a computing task unloading strategy with an objective of optimizing and calculating the total processingtime of the tasks by using a genetic algorithm. The collaborative computing unloading method based on the optical fiber-wireless network can realize the effective unloading of computing tasks for real-time applications, reduces the total processing time of the computing tasks and improves the user experience.

Description

technical field [0001] The present invention relates to the field of mobile edge computing offloading, and more specifically, to a collaborative computing offloading algorithm based on optical fiber-wireless networks. Background technique [0002] In recent years, with the popularity of mobile devices such as mobile phones, smart bracelets, and virtual reality (VR) glasses, many new computing-intensive and energy-intensive applications have emerged, such as face recognition, fingerprint recognition, augmented reality and Interactive games, etc. However, the computing and battery life of existing terminal devices are limited, and it is difficult for them to meet the needs of users in terms of delay and energy consumption for such new applications, seriously affecting user experience. [0003] To solve this problem, many research works offload computing tasks from mobile devices to a centralized cloud computing (Centralized Cloud Computing, CCC) center with abundant computing...

AI Technical Summary

Problems solved by technology

[0004] At present, many researches on MEC offloading only consider offloading tasks to MEC servers, but relatively few researches on computing resources in CCC centers. With more and more computing tasks, the resource bottleneck problem of the MEC server is becoming more and more serious

However, if only the computing resources of the CCC center are used, the transmission delay of the task will be too high

[0005] The computing offloading algorithm in the prior art only sets a threshold for the processing time of computing tasks, and few studies specifically optimize it, but the processing time of computing tasks is an item for evaluating the quality of service (Quality of Service, QoS) Very important metric, especially for online applications

Images