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

Abstract

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.

Keywords

• 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