Ultra-Reliable Risk-Aggregated Sum Rate Maximization via Model-Aided Deep Learning
This work addresses ultra-reliable communication in wireless networks, offering a novel method for risk-aware optimization, though it is incremental in applying deep learning to a specific domain.
The paper tackled the problem of maximizing weighted sum rate in wireless networks with a focus on user rate reliability by introducing a risk-aggregated formulation using Conditional Value-at-Risk (CVaR). The result was a novel α-Robust Graph Neural Network (αRGNN) that eliminated per user deep rate fades and substantially reduced statistical user rate variability while maintaining ergodic performance.
We consider the problem of maximizing weighted sum rate in a multiple-input single-output (MISO) downlink wireless network with emphasis on user rate reliability. We introduce a novel risk-aggregated formulation of the complex WSR maximization problem, which utilizes the Conditional Value-at-Risk (CVaR) as a functional for enforcing rate (ultra)-reliability over channel fading uncertainty/risk. We establish a WMMSE-like equivalence between the proposed precoding problem and a weighted risk-averse MSE problem, enabling us to design a tailored unfolded graph neural network (GNN) policy function approximation (PFA), named α-Robust Graph Neural Network (αRGNN), trained to maximize lower-tail (CVaR) rates resulting from adverse wireless channel realizations (e.g., deep fading, attenuation). We empirically demonstrate that a trained αRGNN fully eliminates per user deep rate fades, and substantially and optimally reduces statistical user rate variability while retaining adequate ergodic performance.