Abstract
Exact performance analysis of dynamic load-balancing policies for distributed systems is known to be very difficult due to state dependent load-balancing decisions and the large size of state spaces. Therefore, approximate methods are usually used. There have been two useful methods for analyzing dynamic load-balancing policies, namely, the state-aggregation method and the decomposition method. This paper proposes a method which uses a combination of these two methods and introduces a new concept called a correlation window for analyzing dynamic load-balancing policies.