Effective capacity and QoS for wireless scheduling

Multiuser scheduling in a wireless context, where channel state information is exploited at the base station, can result in significant throughput gains to users. However, when QoS constraints are imposed (in the form of overflow probabilities), the benefits of multiuser scheduling are not clear. In this paper, we address this question for independent and identically distributed ON-OFF channel models, and study a "multiuser" formulation of effective capacity with QoS constraints. We consider a channel-aware greedy rule as well as the channel-aware max-queue rule, and showed that these algorithms that yield the same long-term throughput without QoS constraints have very different performance when QoS constraints are imposed. Next, we study the effective capacity for varying channel burstiness. From results on multiuser scheduling, we expect the long-term throughput to grow with increasing channel burstiness. However, we show that the throughput with QoS constraints decreases with increasing channel burstiness. The intuitive justification for this is that with increasing burstiness, even though the the long-term throughput increases, the channel access delay increases as well resulting in poor QoS performance.