A trace-based approach for modeling wireless channel behavior

Abstract

The loss behavior of wireless networks has become the focus of many recent research efforts. Although it is generally agreed that wireless communications experience higher error rates than wireline, the nature of these lossy links is not fully understood. This paper describes an effort to characterize the loss behavior of the AT&T WaveLAN, a popular in-building wireless interface. Using a trace-based approach, packet loss information is recorded, analyzed, and validated. Our results indicate that WaveLAN experiences an average packet error rate of 2 to 3 percent. Further analysis reveals that these errors are not independent, making it hard to model them with a simple two-state Markov chain. We derive another model based on the distributions of the error and error-free length of the packet streams. For validation, we modulate both the error models and the traces in a simulator. Trace-driven simulations yield an average TCP throughput of about 5 percent less than simulations using our best error model.