Delay-based packet scheduling for High Speed Downlink Packet Access

Abstract

High Speed Downlink Packet Access (HSDPA) is a cellular system that was standardized by the 3rd Generation Partnership Project (3GPP). HSDPA can support data rates of up to 14.4 Mbps through the use of a shared channel. Due to its high transmission rates, the highly popular multimedia applications are converging over this network. Moreover, as the shared channel is assigned to a single user in a given time interval, the scheduling decision is considered as a crucial one. Conventional HSDPA scheduling schemes utilize the fluctuations in channel condition to maximize system throughput by selecting users with relatively good radio conditions. However, this raises the issue of fairness as users with relatively poor channel conditions might not be served and consequently may suffer from starvation. Furthermore, Real-Time (RT) applications have strict delay constraints and require that packets are transmitted within a certain delay threshold.

In this thesis, a Delay Based Scheduler (DBS) is proposed for HSDPA which aims at minimizing the average queuing delay at the packet scheduler without compromising system throughput and fairness. In addition, the scheme can balance the tradeoff between throughput maximization and the minimization of queuing delay through the attunement of a parameter, thus allowing the service provider to choose between these two metrics. The DBS maintains the delay constraints of RT applications by defining delay thresholds for each traffic class and dropping packets that exceed their delay limit. The DBS accommodates Quality of Service (QoS) prioritization by defining and utilizing desired QoS parameters in the scheduling assignment. Finally, it was mathematically shown that the DBS can converge to a Non-Real-Time (NRT) scheme known as the Max CIR algorithm, allowing the scheduler to support RT and NRT applications simultaneously. The performance of the DBS was evaluated and compared to other well known schemes. It was found that the DBS can minimize the aggregate queuing delay of the system and maintain similar throughput and fairness.