Optimizing Orthogonal Multiple Access based on Quantized Channel State Information

TL;DR

This paper develops a novel, asymptotically optimal channel scheduling policy for orthogonal multiple access systems using quantized channel state information, balancing performance and computational complexity.

Contribution

It introduces a new smoothing-based scheduling scheme that combines disjoint allocation strategies, reducing complexity while maintaining optimality.

Findings

Asymptotically optimal scheduling policy with quantized CSI

Reduced computational complexity through smoothing approach

Convergent stochastic algorithms for Lagrange multiplier estimation

Abstract

The performance of systems where multiple users communicate over wireless fading links benefits from channel-adaptive allocation of the available resources. Different from most existing approaches that allocate resources based on perfect channel state information, this work optimizes channel scheduling along with per user rate and power loadings over orthogonal fading channels, when both terminals and scheduler rely on quantized channel state information. Channel-adaptive policies are designed to optimize an average transmit-performance criterion subject to average quality of service requirements. While the resultant optimal policy per fading realization shows that the individual rate and power loadings can be obtained separately for each user, the optimal scheduling is slightly more complicated. Specifically, per fading realization each channel is allocated either to a single (winner) user, or, to a small group of winner users whose percentage of shared resources is found by solving a linear program. A single scheduling scheme combining both alternatives becomes possible by smoothing the original disjoint scheme. The smooth scheduling is asymptotically optimal and incurs reduced computational complexity. Different alternatives to obtain the Lagrange multipliers required to implement the channel-adaptive policies are proposed, including stochastic iterations that are provably convergent and do not require knowledge of the channel distribution. The development of the optimal channel-adaptive allocation is complemented with discussions on the overhead required to implement the novel policies.