Although the sphere decoder (SD) is a powerful detector for multiple-input multiple-output (MIMO) systems, it has become computationally prohibitive in massive MIMO systems, where a large number of antennas are employed. To overcome this challenge, we propose fast deep learning (DL)-aided SD (FDL-SD) and fast DL-aided KK -best SD (KSD, FDL-KSD) algorithms. Therein, the major application of DL is to generate a highly reliable initial candidate to accelerate the search in SD and KSD in conjunction with candidate/layer ordering and early rejection. Compared to existing DL-aided SD schemes, our proposed schemes are more advantageous in both offline training and online application phases. Specifically, unlike existing DL-aided SD schemes, they do not require performing the conventional SD in the training phase. For a 24×2424 \times 24 MIMO system with QPSK, the proposed FDL-SD achieves a complexity reduction of more than 90% without any performance loss compared to conventional SD schemes. For a 32×3232 \times 32 MIMO system with QPSK, the proposed FDL-KSD only requires K=32K = 32 to attain the performance of the conventional KSD with K=256K=256 , where KK is the number of survival paths in KSD. This implies a dramatic improvement in the performance–complexity tradeoff of the proposed FDL-KSD scheme.

中文翻译：

---

深度学习在大型 MIMO 系统球体解码中的应用


尽管球形解码器 (SD) 是多输入多输出 (MIMO) 系统的强大检测器，但在使用大量天线的大规模 MIMO 系统中，其计算量已变得过高。为了克服这一挑战，我们提出了快速深度学习 (DL) 辅助 SD (FDL-SD) 和快速 DL 辅助 KK 最佳 SD (KSD、FDL-KSD) 算法。其中，DL的主要应用是生成高度可靠的初始候选，以结合候选/层排序和早期拒绝来加速SD和KSD中的搜索。与现有的深度学习辅助SD方案相比，我们提出的方案在离线训练和在线应用阶段都更具优势。具体来说，与现有的 DL 辅助 SD 方案不同，它们不需要在训练阶段执行传统的 SD。对于采用 QPSK 的 24×2424 × 24 MIMO 系统，与传统的 SD 方案相比，所提出的 FDL-SD 实现了 90% 以上的复杂度降低，且没有任何性能损失。对于采用 QPSK 的 32×3232 × 32 MIMO 系统，所提出的 FDL-KSD 仅需要 K=32K = 32 即可获得 K=256K=256 的传统 KSD 的性能，其中 KK 是 KSD 中生存路径的数量。这意味着所提出的 FDL-KSD 方案的性能与复杂性权衡得到了显着改善。