The use of many distributed, heterogeneous resources as a large collective resource offers great potential and has become an increasingly popular idea. A key issue for these Grid platforms is middleware scalability and how middleware services can best be mapped to the resource platform structure. Optimizing deployment is a difficult problem with no existing, general solutions. In this paper we address a simpler sub-problem: how to carry out an adapted deployment on a cluster with hundreds of nodes? Efficient use of clusters alone or as part of the Grid is an important issue. We present a deployment model that predicts the maximum throughput of each element of a deployment. Our deployment construction algorithm uses this model to automatically create a mapping of middleware elements onto resources with the goal of maximizing throughput. We apply our approach to automatically deploy a distributed Problem Solving Environment (PSE) on a homogeneous cluster environment. We present experiments comparing the automatically-generated deployment against a number of other reasonable deployments.