Nonconcave utility maximization in the OFDMA downlink

The problem of utility maximization in an OFDMA downlink is considered. Based on measurements of a scalable video codec, concave and nonconcave utility functions are proposed. Two approaches to solving the utility maximization problem in a modular fashion are considered, one based on Lagrange duality, the other based on a projected gradient algorithm. Both methods yield the optimum solution for concave utilities. In the nonconcave case, simulation results show almost identical performance for both methods under the assumption that the dual solution is found. In contrast, the dual approach fails if the dual subproblems can only be solved to local optimality.