Grid Computing for Load Balancing Strategies

In this paper, we addressed the problem of load balancing in large scale distributed systems. We study various load balancing strategies based on a tree representation of a Grid. The study allows transforming any Grid architecture into a unique tree with at most four levels. From this generic tree, we can derive three sub models depending on the elements that compose a Grid. Using this model, we defined a hierarchical load balancing strategy that privileges local balancing in first (load balance within groups without communication between groups). After load balancing at group level (if load is not balanced at group level) it will be balanced at region level and after balancing at region level (if load is not balanced at region level) it will be balanced at grid level.