Decentralised grid scheduling approach based on multi-agent reinforcement learning and gossip mechanism

CAAI Transactions on Intelligence Technology

Jun Wu¹  Xin Xu² 

[1] College of Aerospace Science, National University of Defense Technology;College of Mechatronics and Automation, National University of Defense Technology;

关键词: multi-agent systems;    learning (artificial intelligence);    resource allocation;    scheduling;    grid computing;    decentralised grid scheduling approach;    multiagent reinforcement learning;    gossip mechanism;    resource allocation approaches;    decentralised job scheduling;    timely model information;    autonomous coordination;    GRL method;    decentralised scheduling architecture;    GRL-based schedulers;    grid job scheduling;    gossip-based reinforcement learning method;   

DOI  :  10.1049/trit.2018.0001

来源: DOAJ

【 摘 要 】

As an important class of resource allocation approaches, decentralised job scheduling in large-scale grids has to deal with the difficulties in acquiring timely model information and improving performance by autonomous coordination. In this study, a gossip-based reinforcement learning (GRL) method is proposed for decentralised job scheduling in grids. In the GRL method, a decentralised scheduling architecture based on multi-agent reinforcement learning is presented to improve the scalability and adaptability of job scheduling. A gossip mechanism is designed to realise autonomous coordination among the decentralised schedulers. Simulation results show that the proposed GRL-based schedulers can complete the task of grid job scheduling effectively and achieve load balancing efficiently.

【 授权许可】

Unknown