Formation method of micro-computing cluster based on incentive mechanism in edge computing or fog computing environment

Abstract

The invention discloses a method for forming a micro-computing cluster based on an incentive mechanism in an edge computing or fog computing environment. By collecting and cooperating with a large number of devices, computing and communication resource sharing is realized to achieve low-latency and high-energy-efficiency mobile task execution. The invention firstly introduces an effective incentive mechanism to promote resource sharing between devices; then utilizes alliance game to promote mutually beneficial cooperative execution of tasks between devices. Among them, to prevent compromising the cooperative willingness of resource-rich devices, the proposed incentive mechanism groups devices into multiple microcomputing clusters, in each microcomputing cluster, devices can exchange mutually beneficial actions by helping other devices to compute or transfer tasks, thereby Makes all missions more efficient. The present invention designs a solution formed by a micro-computing cluster through a centralized and distributed algorithm, and further proves the high efficiency of the algorithm and its remarkable performance in reducing energy and delay overhead.

Description

technical field [0001] The invention relates to the technical fields of deep learning, edge computing and distributed computing, and in particular to a method for forming a micro-computing cluster based on an incentive mechanism in an edge computing or fog computing environment. Background technique [0002] With the unprecedented development of mobile communication technology (such as 5G), it is expected that billions of devices will be connected to the Internet and run various mobile applications, which will result in huge data generation on the device side. Processing such a huge amount of data requires huge computing power and energy supply. Due to physical size and power constraints, mobile devices have limited computing power and energy supply. To alleviate excessive computation and energy requirements, task offloading has been widely recognized as an efficient way of task processing. The basic idea of ​​task offloading is to migrate tasks from mobile devices with in...

AI Technical Summary

Problems solved by technology

But firstly, considering the heterogeneity of edge devices, how to carry out task collaboration between devices can effectively share computing and communication resources; secondly, how to select cooperative devices so that the task execution of each device can achieve mutual benefit A device cooperates with other devices to perform tasks that generate energy consumption overhead, so an effective incentive mechanism is needed to encourage devices to achieve mutually beneficial task execution

Images