Wavelength routing beyond the standard graph coloring approach

When lightpaths are routed in the planning stage of transparent optical networks, the textbook approach is to use algorithms that try to minimize the overall number of wavelengths used in the. We demonstrate that this method cannot be expected to minimize actual costs when the marginal cost of instlling more wavelengths is a declining, function of the number of wavelengths already installed, as is frequently the case. We further demonstrate how cost optimization can theoretically be improved with algorithms based on Prim's algorithm. Finally, we test this theory with simulaion on a series of actual network topologies, which confirm the theoretical analysis.