The assignment of the pilot sequence is a critical challenge in massive MIMO systems, as sharing the same pilot sequence among multiple users causes interference, which degrades the accuracy of the channel estimation. This problem, equivalent to the NP-hard graph coloring problem, directly impacts real-time applications such as autonomous driving and industrial IoT, where minimizing channel estimation time is crucial. This paper proposes an optimized hybrid K-means clustering and Genetic Algorithm (SK-means GA) to improve the pilot assignment efficiency, achieving a 29.3% reduction in convergence time (82s vs. 116s for conventional GA). A parallel implementation (PK-means GA) is developed on an FPGA using Vivado High-Level Synthesis Tools (HLST) to further enhance the run-time performance, accelerating convergence to 3.5 milliseconds. Within Vivado implementation, different optimization techniques such as loop unrolling, pipelining, and function inlining are applied to realize the reported speedup. This significant improvement of PK-means GA in execution speed makes it highly suitable for low-latency real-time wireless networks (6G)

翻译：导频序列分配是大规模MIMO系统中的关键挑战，因为多个用户共享相同导频序列会导致干扰，从而降低信道估计的准确性。该问题等价于NP难图着色问题，直接影响自动驾驶和工业物联网等实时应用，其中最小化信道估计时间至关重要。本文提出一种优化的混合K-means聚类与遗传算法（SK-means GA）以提高导频分配效率，实现了收敛时间减少29.3%（传统遗传算法为116秒，本方法为82秒）。通过在FPGA上使用Vivado高层次综合工具（HLST）开发并行实现（PK-means GA），进一步提升了运行时性能，将收敛加速至3.5毫秒。在Vivado实现中，应用了循环展开、流水线化和函数内联等不同优化技术以实现所报告的加速效果。PK-means GA在执行速度上的显著改进使其非常适用于低延迟实时无线网络（6G）。