As one of the key technologies of 5G, Cloud Radio Access Networks (C-RAN) with cloud BBUs (Base Band Units) pool architecture and distributed RRHs (Remote Radio Heads) can provide the ubiquitous services. When failure occurs at RRH, it can’t be alleviated in time and will lead to a significant drop in network performance. Therefore, the cell outage compensation (COC) problem for RRH in 5G C-RAN is very important. Although deep reinforcement learning (DRL) has been applied to many scenarios related to the self-organizing network (SON), there are fewer applications for cell outage compensation. And most intelligent algorithms are hard to obtain globally optimized solutions. In this paper, aiming at the cell outage scenario in C-RAN with the goal of maximizing the energy efficiency, connectivity of RRH while meeting service quality demands of each compensation user, a framework based on DRL is presented to solve it. Firstly, compensation users are allocated to adjacent RRHs by using the K-means clustering algorithm. Secondly, DQN is used to find the antenna downtilt and the power allocated to compensation users. Comparing to different genetic algorithms, simulation result shows that the proposed framework converges quickly and tends to be stable, and reaches 95% of the maximum target value. It verifies the efficiency of the DRL-based framework and its effectiveness in meeting user requirements and handling cell outage compensation.

作为5G的关键技术之一，具有云BBU（基带单元）池架构和分布式RRH（远程无线电头）的云无线电接入网络（C-RAN）可以提供无处不在的服务。当RRH发生故障时，无法及时缓解，这将导致网络性能大幅下降。因此，5G C-RAN中RRH的信元损耗补偿（COC）问题非常重要。尽管深度强化学习（DRL）已应用于与自组织网络（SON）相关的许多情况，但用于小区中断补偿的应用却很少。而且大多数智能算法很难获得全局优化的解决方案。本文针对C-RAN中的小区中断情况，旨在最大程度地提高能源效率，在满足每个补偿用户的服务质量要求的同时，提出了基于DRL的框架来解决RRH的连通性。首先，使用K-means聚类算法将补偿用户分配给相邻的RRH。其次，DQN用于查找天线下倾角和分配给补偿用户的功率。与不同的遗传算法比较，仿真结果表明，所提出的框架收敛迅速，趋于稳定，达到最大目标值的95％。它验证了基于DRL的框架的效率及其在满足用户需求和处理小区中断补偿方面的有效性。DQN用于查找天线下倾角和分配给补偿用户的功率。与不同的遗传算法比较，仿真结果表明，所提出的框架收敛迅速，趋于稳定，达到最大目标值的95％。它验证了基于DRL的框架的效率及其在满足用户要求和处理小区中断补偿方面的有效性。DQN用于查找天线下倾角和分配给补偿用户的功率。与不同的遗传算法比较，仿真结果表明，所提出的框架收敛迅速，趋于稳定，达到最大目标值的95％。它验证了基于DRL的框架的效率及其在满足用户要求和处理小区中断补偿方面的有效性。