Edge computing task scheduling method based on combined load balancing

Abstract

The invention discloses an edge computing task scheduling method based on combined load balancing, and relates to the field of mobile edge computing, which comprises the following steps: S1, establishing a network scene model; s2, collecting user terminal information, and importing the user terminal information into a network scene model to determine time expenditure and energy expenditure; s3, determining edge clouds capable of being unloaded, and adjusting the network scene model; s4, determining an initial tabu table; s5, selecting one user terminal for unloading; s6, selecting an edge cloud by the user terminal; s7, if the user terminal which is not selected yet exists, returning to the step S5, otherwise, entering the step S8; s8, judging whether the energy consumption of the currentcycle is lower than that of the current cycle or whether the unloading success number is maximum or not, if yes, replacing the current cycle with the current cycle, and updating pheromones; s9, judging whether the maximum number of iterations is reached or not, if so, taking the current scheme as a task scheduling scheme, and otherwise, returning to the step S4. The ant colony algorithm and the load balancing characteristic are used, edge cloud computing resources are utilized to the maximum extent, system energy consumption is reduced, and user experience is improved.

Description

technical field [0001] The present invention relates to the field of mobile edge computing, in particular to an edge computing task scheduling method based on combined load balancing. Background technique [0002] There are more and more mobile device applications for today's users, and there are also applications that require a large amount of computing resources. However, due to the portability of mobile devices, the computing power and battery life of mobile devices are limited, so mobile devices use Such computationally intensive tasks are offloaded to auxiliary computing devices to assist users in processing, but traditional cloud computing (for example: Alibaba Cloud) is too far away from users, and the time spent on uploading tasks by users will be very high. task, which is taking too long. The advantages of edge computing over traditional cloud computing are: 1. Closer to users and less time delay; 2. High customization, users or operators can deploy edge clouds of ...

AI Technical Summary

Problems solved by technology

It takes different time for users in different locations to transfer to edge clouds in different locations, and the energy consumption will also be different. Moreover, if the task scheduling method is improper, some edge clouds will be too busy and some edge clouds will be idle, resulting in waste of computing resources.

Images