Many-to-many computation migration method and system of self-organizing cloud

Abstract

The invention discloses a many-to-many computation migration method and system of the self-organizing cloud. A central scheduling manager collects and manages task requests sent from node devices, schedules task via a genetic ant colony task scheduling algorithm regularly, and returns a task scheduling result to a sound node device; the source node device receives the task scheduling result and then migrates the tasks to a target node device; and the target node device executes the tasks according to a task queue, and sends task output data back to the source node device after that the tasks are completed. According to the invention, the task scheduling problem in the peer-to-peer self-organizing cloud network environment is researched, a task scheduling model and a task scheduling strategy are described, and the task scheduling algorithm based on the genetic ant colony algorithm is designed for optimization objects as minimizing the average task execution time length, load balancing and minimizing average task execution energy consumption.

Description

technical field [0001] The invention relates to the field of computer theory, in particular to a self-organizing cloud many-to-many computing migration method and system. Background technique [0002] With the development of global informatization and intelligent technology, intelligent terminals and various IoT node devices are used as interfaces for people to enjoy intelligent and informationized life, as carriers for collecting, calculating and transmitting information at the bottom, and various intelligent The specific executor of digitalization and informatization functions plays an increasingly important role in people's lives. In the context of the continuous development of intelligent terminal devices, the self-organizing network will become the main organizational form for various terminal devices to work together and cooperate with each other to create higher application services. However, due to their inherent resource limitations, these devices are often unable ...

AI Technical Summary

Problems solved by technology

The first is that the node device migrates the computing task to the remote data center for execution and receives the execution result. The remote cloud usually has powerful computing capabilities, but requires the node device to have remote communication capabilities, and the network delay is large and not stable enough.

The second is that the node device migrates tasks to the local cloud. The local cloud is a highly available resource (such as a small server, base station resource, etc.) near the node device. This mode can reduce communication and time overhead, but the construction and maintenance costs are relatively high. high

[0005] The inventors have found th

Images