Efficient power allocation using graph neural networks and deep algorithm unfolding
This work provides a more computationally efficient solution for power allocation in wireless networks, benefiting network operators and users by potentially improving network performance and reducing energy consumption.
This paper addresses optimal power allocation in single-hop ad hoc wireless networks. It proposes a hybrid neural architecture, UWMMSE, which achieves performance comparable to WMMSE while significantly reducing computational complexity.
We study the problem of optimal power allocation in a single-hop ad hoc wireless network. In solving this problem, we propose a hybrid neural architecture inspired by the algorithmic unfolding of the iterative weighted minimum mean squared error (WMMSE) method, that we denote as unfolded WMMSE (UWMMSE). The learnable weights within UWMMSE are parameterized using graph neural networks (GNNs), where the time-varying underlying graphs are given by the fading interference coefficients in the wireless network. These GNNs are trained through a gradient descent approach based on multiple instances of the power allocation problem. Once trained, UWMMSE achieves performance comparable to that of WMMSE while significantly reducing the computational complexity. This phenomenon is illustrated through numerical experiments along with the robustness and generalization to wireless networks of different densities and sizes.