The end-to-end quality of service (QoS) and quality of experience (QoE) guarantee is quite important for network optimization. The current 5G and conceived 6G network in the future with ultra high density, bandwidth, mobility and large scale brings urgent requirement of high efficient end-to-end optimization methods. The conventional network optimization methods without learning and intelligent decision ability are hard to handle the high complexity and dynamic scenarios of 6G. Recently, machine learning based QoS and QoE aware network optimization algorithms emerge as a hot research area and attract much attention, which is widely acknowledged as the potential solution for end-to-end optimization in 6G. However, there are still many critical issues of employing machine learning in networks, especially in 6G. In this paper, we give a comprehensive survey on the recent machine learning based network optimization methods to guarantee the end-to-end QoS and QoE. To easy to follow, we introduce the investigated works following the end-to-end transmission flow from network access, routing to network congestion control and adaptive steaming control. Then we discuss some open issues and potential future research directions.

中文翻译：

---

面向 6G 的智能端到端通信机器学习调查：从网络接入、路由到流量控制和流媒体适配

端到端的服务质量 (QoS) 和体验质量 (QoE) 保证对于网络优化非常重要。当前的5G和未来设想的6G网络具有超高密度、带宽、移动性和大规模，迫切需要高效的端到端优化方法。传统的网络优化方法缺乏学习和智能决策能力，难以应对6G的高复杂度和动态场景。最近，基于机器学习的 QoS 和 QoE 感知网络优化算法成为热门研究领域并备受关注，被广泛认为是 6G 端到端优化的潜在解决方案。然而，在网络中使用机器学习仍然存在许多关键问题，尤其是在 6G 中。在本文中，我们对最近基于机器学习的网络优化方法进行了全面调查，以保证端到端的 QoS 和 QoE。为了便于理解，我们介绍了从网络访问、路由到网络拥塞控制和自适应流控制的端到端传输流程的研究工作。然后我们讨论一些未解决的问题和潜在的未来研究方向。