A learnable genetic algorithm for QoS multicast routing

Abstract

By improving the conventional genetic algorithm, we put forward a learnable genetic algorithm combining machine learning and genetic algorithm. The central idea of the algorithm is that it generates new individuals by processes of hypothesis generation and instantiation, rather than by mutation and/or recombination as in conventional genetic algorithms. The algorithm is then used for the bandwidth-delay-constrained least-cost multicast routing problem. The features of this new algorithm are simplicity and effectivity.