Performance of OFDM Systems With Best- <inline-formula> <tex-math notation="TeX">$m$</tex-math></inline-formula> Feedback, Scheduling, and Delays for Uniformly Correlated Subchannels

Abstract

Contemporary cellular standards, such as Long Term Evolution (LTE) and LTE-Advanced, employ orthogonal frequency-division multiplexing (OFDM) and use frequency-domain scheduling and rate adaptation. In conjunction with feedback reduction schemes, high downlink spectral efficiencies are achieved while limiting the uplink feedback overhead. One such important scheme that has been adopted by these standards is best- m feedback, in which every user feeds back its m largest subchannel (SC) power gains and their corresponding indices. We analyze the single cell average throughput of an OFDM system with uniformly correlated SC gains that employs best- m feedback and discrete rate adaptation. Our model incorporates three schedulers that cover a wide range of the throughput versus fairness tradeoff and feedback delay. We show that, for small m, correlation significantly reduces average throughput with best- m feedback. This result is pertinent as even in typical dispersive channels, correlation is high. We observe that the schedulers exhibit varied sensitivities to correlation and feedback delay. The analysis also leads to insightful expressions for the average throughput in the asymptotic regime of a large number of users.