基于机器学习的OTFS系统信道估计与信号检测研究进展OA
Advancements in Machine Learning-Based Channel Estimation and Signal Detection for OTFS Systems
OTFS调制可以在高速移动场景下有效对抗ICI,能提供比传统的OFDM更显著的性能增益,充分提升高多普勒扩展场景下的通信系统频谱效率,改善通信系统质量,近年来得到广泛研究.OTFS系统的研究重点和难点在于信道估计与信号检测.人工智能已经成为一种有效的信息处理手段,在各行业都得到了广泛的应用.而机器学习是人工智能中的重要分支,通过将机器学习与OTFS技术相结合,可以有效解决信道估计与信号检测中的问题,提高系统性能、稳定性和可靠性.对目前基于机器学习的OTFS系统的信道估计与信号检测算法进行了较为全面的调研、分析、对比和归纳,进而梳理出技术挑战,并就未来的技术发展趋势进行了探讨.
OTFS modulation effectively combats ICI in high-mobility scenarios,offering significant performance gains over traditional OFDM and enhancing spectral efficiency and communication quality in high-Doppler environments,thus attracting extensive research interest in recent years.The primary focus and challenge in OTFS systems lie in channel estimation and signal detection.Artificial intelligence has emerged as a potent information processing tool,widely adopted across various industries.Machine learning,as a crucial branch of artificial intelligence,when integrated with the OTFS technique,addresses issues in channel estimation and signal detection,thereby improving system performance,stability,and reliability.This paper provides a comprehensive survey,analysis,comparison,and synthesis of current machine learning-based algorithms for channel estimation and signal detection in OTFS systems,identifies technical challenges,and discusses future technological development trends.
廖勇;韩小金
重庆大学微电子与通信工程学院,重庆 400044
电子信息工程
人工智能机器学习第六代移动通信正交时频空信道估计信号检测
artificial intelligencemachine learningsixth generation mobile communicationorthogonal time-frequency spacechannel estimationsignal detection
《移动通信》 2024 (007)
46-56 / 11
重庆市自然科学基金"面向超高速移动场景的OTFS系统信道估计与均衡研究"(CSTB2023NSCQ-MSX0025)
评论