Optimal object placement, load distribution and load control for distributed telecommunication service applications

This paper presents a method for optimising the placement of software objects on network nodes, for multi-service distributed applications. Also addressed are the related problems of optimal distribution of traffic between distributed software object instances and optimal admission control for the network. The object placement problem is formulated as a Mixed Integer Programming (MIP) flow problem. The solution yields the placement of application objects that gives the maximum allowable arrival intensities to the network under the constraints of object installation costs. Given the optimal object placement, a further method is developed for optimising routing between object instances to maximise network revenue when arrival intensities vary over time from the original design point. This problem is formulated as a Linear Programming (LP) problem that is constrained by the solution of the original MIP problem. The solution gives the basis for a load distribution and load control algorithm for the optimised network. An example of a telecommunication service application (Intelligent Network services) executing on a distributed platform is given. The solutions to the example network have been simulated and results are presented in this paper.