HARNESS: High Availability Supportive Self Reliant Network Slicing in 5G Networks

被引:12
作者
Vittal, Shwetha [1 ]
Franklin, A. Antony [1 ]
机构
[1] Indian Inst Technol Hyderabad, Dept Comp Sci & Engn, Hyderabad 502205, India
来源
IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT | 2022年 / 19卷 / 03期
关键词
5G mobile communication; Delays; Noise measurement; Ultra reliable low latency communication; Scheduling; Quality of service; Network slicing; 5G; 5G core; approximation algorithm; network slicing; high availability; reliability; NP-completeness; Pareto distribution; self organizing network;
D O I
10.1109/TNSM.2022.3157888
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Mobile Network Operator (MNO)s avail the benefit of providing an isolated service with the network slice in a variety of forms like enhanced Mobile Broadband (eMBB), ultra Reliable Low Latency Communications (uRLLC), and massive Machine Type Communications (mMTC). However, they face challenges in handling situations of overload, congestion, and scaling with the arrival of unexpected control plane User Service Requests (USRs) leading to the dropping of USRs, and hence disturbing the slice's High Availability (HA). This paper presents a novel High Availability supportive self Reliant NEtwork Slicing System (HARNESS) for 5G Core, powered by intelligent and autonomous Self Organizing Network (SON) paradigm. In HARNESS, we propose algorithms to intelligently schedule and serve the significant portion of control plane USRs for both delay tolerant and delay sensitive slices, to ensure their uninterrupted HA service provision. Along with efficient resource utilization, the HARNESS shows improvements over the traditional HA provisioning methods, in preventing the occluding of crucial control plane USRs by 60% and reducing the average response time for these USRs by 50%. We developed the HARNESS framework in a 5G test-bed system using eXpress Data Path (XDP) and extended Berkeley Packet Filter (eBPF) mechanism for coherent and optimized end-to-end working of it. With this additional gear, HARNESS productively contributes to achieving 3.2% better slice service HA in the minimal two nodes active/active cluster configuration.
引用
收藏
页码:1951 / 1964
页数:14
相关论文
共 66 条
[1]   Load balancing in cloud computing - A hierarchical taxonomical classification [J].
Afzal, Shahbaz ;
Kavitha, G. .
JOURNAL OF CLOUD COMPUTING-ADVANCES SYSTEMS AND APPLICATIONS, 2019, 8 (01)
[2]   Improving Traffic Forecasting for 5G Core Network Scalability: A Machine Learning Approach [J].
Alawe, Imad ;
Ksentini, Adlen ;
Hadjadj-Aoul, Yassine ;
Bertin, Philippe .
IEEE NETWORK, 2018, 32 (06) :42-49
[3]  
Albers S., 2004, P SPAA, P84
[4]  
[Anonymous], 2020, U.S. Patent, Patent No. 187290
[5]  
[Anonymous], 2015, 002 ETSI GS NFVREL
[6]  
[Anonymous], 2019, YOU NEED ROB SIGN SO
[7]  
[Anonymous], 2021, 3GPP TS 23.501 V17.2.0
[8]  
[Anonymous], 2018, Facebook
[9]  
[Anonymous], 2019, 38413 3GPP TS
[10]  
[Anonymous], 2018, 3GPP TS 23.502 version 15.2.0 Release 15