Towards a Management Paradigm with a Constrained Benchmark for Autonomic Communications

This paper describes a management paradigm to give effect to autonomic activation, monitoring and control of services or products in the future converged telecommunications networks. It suggests an architecture that places the various management functions into a structure that can then be used to select those functions which may yield to autonomic management, as well as guiding the design of the algorithms. The validation of this architecture, with particular focus on service configuration, is done via a genetic algorithm - population based incremental learning (PBIL). Even with this centralized adaptation strategy, the simulation results show that the proposed architecture and benchmark can be applied to this constrained benchmark, produces effective convergence performance in terms of finding nearly optimal configurations under multiple constraints