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

• Main Authors: LU ZHANXIANG, ZHANG HONGGUANG, WU FAN, TANG BIHUA, FAN WENHAO
• Format: Patent
• Language: Chinese; English
• Published: 07.07.2017
• Subjects: ELECTRIC COMMUNICATION TECHNIQUE; ELECTRICITY; TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION

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 ta