Advanced Multi-objective Evolutionary Algorithms Applied to Two Problems in Telecommunications

The bulk of research in optimization is aimed at single objective problems, where the aim is to nd a solution which maximises or minimises a single quality measure. However, as in nature, many problems in telecommunications are fundamentally multi-objective, particularly where the issues involved are related to quality of service, or cost/reliability tradeoos, or perhaps both. The results of optimization should ideally provide the network designer or service manager with a wide and high-quality spread of potential solutions which are uniformly spread across the Pareto tradeoo frontier. There has been considerable research in multi-objective optimization, but, until recently, the most prominently known multi-objective optimization algorithms have tended to be rather slow, and there has been no universally accepted way to properly compare the performance of diierent methods. In this paper, we describe two evolutionary computation based multi-objective optimization methods which have recently been shown to be both considerably faster than the classical set of such methods, and to outperform existing methods on a wide range of test problems, where performance comparisons are done using a sophisticated technique recently extended and developed by the authors. We focus on two application areas in telecommunications: the adaptive distributed database management problem, and the ooine-routing problem. The new and classical evolutionary multi-objective optimizers are compared on variants of both problems. The speed and quality of these new methods suggest that their adoption in live applications of these and other telecommunications related problems is feasible.