.png){kind=icon}
.png){kind=icon}
Return
OptiMISD: Optimized MCTS Integrated Sphere Decoder for Challenging MIMO Detection
.png){kind=icon}
PRE
AI
DOI：10.1109/TVT.2025.3588116.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
With rapid advancements in wireless communications, MIMO systems are evolving to include a greater number of antennas and higher modulation orders. In these challenging environments, traditional linear detectors such as the MMSE often fall short in delivering satisfactory performance. While tree-search based detectors like the sphere decoder (SD) and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$K$</tex-math></inline-formula>-Best detector can improve outcomes, they suffer from prohibitive complexity due to the vast search space. This article introduces OptiMISD—an optimized Monte Carlo tree search (MCTS) integrated sphere decoder, designed specifically for challenging MIMO detection scenarios. We propose three innovative techniques to enhance its efficacy: 1) a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">partial K-Best</i> approach, 2) a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">fast upper confidence for trees (UCT)</i> policy, and 3) a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">radius restriction</i> method. Our numerical results demonstrate that OptiMISD not only achieves a performance gain of over 3 dB compared to the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$K$</tex-math></inline-formula>-Best detector (with <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$K=64$</tex-math></inline-formula>) @ <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\text{BER}=10^{-4}$</tex-math></inline-formula> but also reduces complexity by up to 84.9%. Additionally, the principles of OptiMISD can be adapted to address other tree-search based challenges.
Keywords:
Monte Carlo tree search (MCTS)
multiple-input multiple-output (MIMO)
sphere decoder (SD)
$K$ -Best
Journal
IF:
7.1
Papers:
1.8W
Citations:
6.6W