Towards Optimal Power Control via Ensembling Deep Neural Networks
This addresses power control in wireless networks for improved efficiency, but it is incremental as it builds on existing DNN approaches with ensembling.
The paper tackled the non-convex optimization problem of maximizing sum rate in multi-user interference channels by proposing ePCNet, an ensemble of deep neural networks, which outperformed state-of-the-art methods by 1.2%-4.6% in simulations with reduced computational complexity.
A deep neural network (DNN) based power control method is proposed, which aims at solving the non-convex optimization problem of maximizing the sum rate of a multi-user interference channel. Towards this end, we first present PCNet, which is a multi-layer fully connected neural network that is specifically designed for the power control problem. PCNet takes the channel coefficients as input and outputs the transmit power of all users. A key challenge in training a DNN for the power control problem is the lack of ground truth, i.e., the optimal power allocation is unknown. To address this issue, PCNet leverages the unsupervised learning strategy and directly maximizes the sum rate in the training phase. Observing that a single PCNet does not globally outperform the existing solutions, we further propose ePCNet, a network ensemble with multiple PCNets trained independently. Simulation results show that for the standard symmetric multi-user Gaussian interference channel, ePCNet can outperform all state-of-the-art power control methods by 1.2%-4.6% under a variety of system configurations. Furthermore, the performance improvement of ePCNet comes with a reduced computational complexity.