Utility Maximizing Load Balancing Policies

Consider a service system where incoming tasks are instantaneously dispatched to one out of many heterogeneous server pools. Associated with each pool is concave utility function which depends on the class and its current occupancy. We derive an upper bound for mean normalized aggregate in stationarity introduce two load balancing policies that achieve this large-scale regime. Furthermore, transient stationary behavior these asymptotically optimal characterized scale number pools, same