Traffic-Aware Spectrum Assignment in Wireless Networks

Radio frequency spectrum is a finite and scarce resource. However, past research efforts usually assume orthogonal channels of fixed bandwidth, prohibiting the effective use of the spectrum. Recently some work began to explore dynamic channel width adaptation. In this paper, by reducing the optimal channel width adaptation into the "elastic packing" problem, we devise distributed algorithms based on graph multi-interval coloring and max-coloring. We then integrate our algorithms into the multi-radio multi-channel wireless mesh networks. Simulation results show that our schemes can improve network performance significantly.