Enhanced Scheduling Algorithms for Improved TCP Performance in Wireless IP Networks

Current and next-generation wireless networks rely on multi-user diversity and scheduling techniques to achieve greater system throughput and higher efficiencies for wireless data applications over a time-varying wireless channel. The most commonly used scheduling algorithm is Proportional Fair which aims at scheduling users when they experience relatively good channel conditions, while at the same time providing some degree of fairness across users. 

The effect of the scheduling algorithm on the TCP layer performance has not been fully investigated. In this paper, we show that the inter-scheduling intervals, as introduced by a scheduling algorithm, can have adverse effects on TCP and its congestion control mechanism and lead to spurious timeouts and unnecessarily low throughput. We propose an enhanced scheduling algorithm that is explicitly tuned towards throughput performance at the TCP layer. 

However this algorithm does not use any explicit information from the TCP layer and solely relies on information readily available at the link layer at which the scheduler resides. The performance of this improved algorithm is assessed through extensive simulations to show an improvement over Proportional Fair as far as the system throughput is concerned as well as the achieved fairness between users.