Grid load balancing using intelligent agents

Workload and resource management are essential functionalities in the software infrastructure for grid computing. The management and scheduling of dynamic grid resources in a scalable way requires new technologies to implement a next generation intelligent grid environment. This work demonstrates that AI technologies can be utilised to achieve effective workload and resource management. A combination of intelligent agents and multi-agent approaches is applied for both local grid resource scheduling and global grid load balancing. Each agent is a representative of a local grid resource and utilises predictive application performance data and iterative heuristic algorithms to engineer local load balancing across multiple hosts. At a higher level of the global grid, agents cooperate with each other to balance workload using a peer-to-peer service advertisement and discovery mechanism. A case study is included with corresponding experimental results to demonstrate that intelligent agents are effective to achieve resource scheduling and load balancing, improve application execution performance and maximise resource utilisation.