An intelligent learning scheme for adaptive modulation

In recent years adaptive modulation has been shown to improve data throughput and system capacity in a wireless system. The basic idea is to adapt the modulation and/or coding scheme to the fading channel quality, using different schemes for different channel conditions. Therefore one primary issue is to determine the switching thresholds between the modulation schemes. Typically these thresholds are fixed in a system. This paper proposes a novel adaptive learning scheme that is capable of dynamically adjusting the thresholds so as to maximize the throughput, while maintaining a target frame error rate at the same time. A key feature of the proposed self-learning scheme is that no dedicated training signal is required, instead it utilizes the long-term average throughput and frame error rate to continuously update the thresholds as the data is being transmitted.