An Information-Theoretic Approach to Accelerated Simulation of Hybrid-ARQ Systems

In order to reduce the long runtimes required to simulate hybrid automatic repeat-request (ARQ) systems, such as high-speed downlink packet access (HSDPA), we propose an information-theoretic approach to accelerate the simulation while still maintaining its fidelity. The approach is based on the concept of information-outage probability, and involves the computation of the mutual information between the code bits transmitted over the channel and the bit log-likelihood ratio coming out of the demodulator. Because the mutual information is measured at the demodulator output, the metric naturally accounts for the parameters of the channel and modulation as well as the length of the codeword. An information outage is declared whenever the measured mutual information is below a threshold (the code rate), and the frequency of simulated information outages provides an accurate prediction of the rate that the turbo decoder fails. Because the prediction is sufficiently accurate, it is possible to run the simulation without actually decoding the turbo code. The result is a 10-30 fold speedup in simulation runtime, while the predicted frame error rate and throughput results are still within 1-2 dB of the values obtained with a more accurate (though lengthier) simulation that decodes each turbo codeword.