Deep Reinforcement Learning Aided Cell Outage Compensation Framework in 5G Cloud Radio Access Networks

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.

[1]  Félix J. García Clemente,et al.  A Self-Adaptive Deep Learning-Based System for Anomaly Detection in 5G Networks , 2018, IEEE Access.

[2]  Ali Imran,et al.  Self-Healing in Emerging Cellular Networks: Review, Challenges, and Research Directions , 2018, IEEE Communications Surveys & Tutorials.

[3]  Qian Zhang,et al.  Local cooperation architecture for self-healing femtocell networks , 2014, IEEE Wireless Communications.

[4]  Andreas Mitschele-Thiel,et al.  Cognitive Cellular Networks: A Q-Learning Framework for Self-Organizing Networks , 2016, IEEE Transactions on Network and Service Management.

[5]  Mehdi Amirijoo,et al.  Effectiveness of cell outage compensation in LTE networks , 2011, 2011 IEEE Consumer Communications and Networking Conference (CCNC).

[6]  Navrati Saxena,et al.  Efficient Cell Outage Detection in 5G HetNets Using Hidden Markov Model , 2016, IEEE Communications Letters.

[7]  Tianle Deng,et al.  An Improved TCM-Based Approach for Cell Outage Detection for Self-Healing in LTE HetNets , 2016, 2016 IEEE 83rd Vehicular Technology Conference (VTC Spring).

[8]  Cheng Li,et al.  Dense-Device-Enabled Cooperative Networks for Efficient and Secure Transmission , 2018, IEEE Network.

[9]  Robert Schober,et al.  Analysis of Coverage in Heterogeneous Cellular Networks , 2016, IEEE Communications Letters.

[10]  David Palacios,et al.  Self-Healing Framework for Next-Generation Networks through Dimensionality Reduction , 2018, IEEE Communications Magazine.

[11]  Tarik Taleb,et al.  Self Organized Network Management Functions for Energy Efficient Cellular Urban Infrastructures , 2012, Mob. Networks Appl..

[12]  Liang Gong,et al.  Integrating network function virtualization with SDR and SDN for 4G/5G networks , 2015, IEEE Network.

[13]  Raouf Boutaba,et al.  Machine Learning for Cognitive Network Management , 2018, IEEE Communications Magazine.

[14]  Gang Cao,et al.  AIF: An Artificial Intelligence Framework for Smart Wireless Network Management , 2018, IEEE Communications Letters.

[15]  Xuelong Li,et al.  Recent Advances in Cloud Radio Access Networks: System Architectures, Key Techniques, and Open Issues , 2016, IEEE Communications Surveys & Tutorials.

[16]  Xiang-Gen Xia,et al.  Enabling UAV cellular with millimeter-wave communication: potentials and approaches , 2016, IEEE Communications Magazine.

[17]  Lorenza Giupponi,et al.  A Reinforcement Learning Based Solution for Self-Healing in LTE Networks , 2014, 2014 IEEE 80th Vehicular Technology Conference (VTC2014-Fall).

[18]  Xiaofei Wang,et al.  Artificial Intelligence-Based Techniques for Emerging Heterogeneous Network: State of the Arts, Opportunities, and Challenges , 2015, IEEE Access.

[19]  HongLiu,et al.  Web user clustering analysis based on KMeans algorithm , 2010, ICOIN 2010.

[20]  Xuesong Qiu,et al.  Multi-Cell Cooperative Outage Compensation in Cloud-RANs Based 5G Public Safety Network , 2017, IEEE Access.

[21]  Yong Li,et al.  System architecture and key technologies for 5G heterogeneous cloud radio access networks , 2015, IEEE Netw..

[22]  Jing Wang,et al.  A deep reinforcement learning based framework for power-efficient resource allocation in cloud RANs , 2017, 2017 IEEE International Conference on Communications (ICC).

[23]  Zhisheng Niu,et al.  DeepNap: Data-Driven Base Station Sleeping Operations Through Deep Reinforcement Learning , 2018, IEEE Internet of Things Journal.

[24]  Xiaohu You,et al.  A Cooperative Outage Detection Approach Using an Improved RBF Neural Network with Genetic ABC Algorithm , 2018, 2018 10th International Conference on Wireless Communications and Signal Processing (WCSP).

[25]  Ahmed E. Kamal,et al.  Fronthaul cell outage compensation for 5G networks , 2016, IEEE Communications Magazine.

[26]  Hui Tian,et al.  Cooperative Resource Allocation for Self-Healing in Small Cell Networks , 2015, IEEE Communications Letters.

[27]  Michel Kadoch,et al.  Adaptive SON and Cognitive Smart LPN for 5G Heterogeneous Networks , 2015, Mob. Networks Appl..

[28]  Qi Hao,et al.  Deep Learning for Intelligent Wireless Networks: A Comprehensive Survey , 2018, IEEE Communications Surveys & Tutorials.

[29]  Xuesong Qiu,et al.  Automated cell outage compensation mechanism based on downtilt adjustments in cellular networks , 2016, 2016 16th International Symposium on Communications and Information Technologies (ISCIT).

[30]  Richard Demo Souza,et al.  A Survey of Machine Learning Techniques Applied to Self-Organizing Cellular Networks , 2017, IEEE Communications Surveys & Tutorials.

[31]  Peng Yu,et al.  A distributed cell outage compensation mechanism based on RS power adjustment in LTE networks , 2014, China Communications.

[32]  Muhammad Ali Imran,et al.  A Survey of Self Organisation in Future Cellular Networks , 2013, IEEE Communications Surveys & Tutorials.

[33]  Nuo Xu,et al.  Optimal Power Allocation for SCMA Downlink Systems Based on Maximum Capacity , 2019, IEEE Transactions on Communications.

[34]  Raquel Barco,et al.  Adaptive Cell Outage Compensation in Self-Organizing Networks , 2018, IEEE Transactions on Vehicular Technology.

[35]  Ovidiu Iacoboaiea,et al.  SON Coordination in Heterogeneous Networks: A Reinforcement Learning Framework , 2016, IEEE Transactions on Wireless Communications.

[36]  Lorenzo Favalli,et al.  Dynamic Cell Sectorization Using Clustering Algorithms , 2007, 2007 IEEE 65th Vehicular Technology Conference - VTC2007-Spring.

[37]  Cheng Li,et al.  Task Assignment in Mobile Crowdsensing: Present and Future Directions , 2018, IEEE Network.