KNOM Review

The Korean Institute of Commucations and Information Sciences (한국통신학회)
권호 표지
DOI QR코드

DOI QR Code

IBN-based: AI-driven Multi-Domain e2e Network Orchestration Approach

IBN 기반: AI 기반 멀티 도메인 네트워크 슬라이싱 접근법

  • Khan, Talha Ahmed (JeJu National University Department of Computer Engineering) ;
  • Muhammad, Afaq (JeJu National University Department of Computer Engineering) ;
  • Abbas, Khizar (JeJu National University Department of Computer Engineering) ;
  • Song, Wang-Cheol (JeJu National University Department of Computer Engineering)
  • Received : 2020.11.14
  • Accepted : 2020.12.22
  • Published : 2020.12.31
⟨ Previous Next ⟩

Abstract

Networks are growing faster than ever before causing a multi-domain complexity. The diversity, variety and dynamic nature of network traffic and services require enhanced orchestration and management approaches. While many standard orchestrators and network operators are resulting in an increase of complexity for handling E2E slice orchestration. Besides, there are multiple domains involved in E2E slice orchestration including access, edge, transport and core network each having their specific challenges. Hence, handling of multi-domain, multi-platform and multi-operator based networking environments manually requires specified experts and using this approach it is impossible to handle the dynamic changes in the network at runtime. Also, the manual approaches towards handling such complexity is always error-prone and tedious. Hence, this work proposes an automated and abstracted solution for handling E2E slice orchestration using an intent-based approach. It abstracts the domains from the operators and enable them to provide their orchestration intention in the form of high-level intents. Besides, it actively monitors the orchestrated resources and based on current monitoring stats using the machine learning it predicts future utilization of resources for updating the system states. Resulting in a closed-loop automated E2E network orchestration and management system.

네트워크는 빠르게 성장하여 다중 도메인 복잡성을 유발하고 있다. 네트워크 트래픽 및 서비스의 다양성, 다양성 및 동적 특성은 향상된 오케스트레이션 및 관리 접근 방식을 필요로한다. 많은 표준 오케스트레이터와 네트워크 운영자가 E2E 슬라이스 오케스트레이션을 처리하기 위한 복잡성이 증가하고 있다. 또한 액세스, 에지, 전송 및 코어 네트워크를 포함하여 E2E 슬라이스 오케스트레이션과 관련된 여러 도메인이 각각 특정 문제를 가지고 있다. 따라서 멀티 도메인, 멀티 플랫폼 및 멀티 오퍼레이터 기반 네트워킹 환경을 수동으로 처리하려면 특정 전문가가 필요하며 이 접근 방식을 사용하면 런타임에 네트워크의 동적 변경을 처리할 수 없다 또한 이러한 복잡성을 처리하기위한 수동 접근 방식은 항상 오류가 발생하기 쉽고 지루한 일이다. 따라서 본 연구에서는 의도 기반 접근법을 사용하여 E2E 슬라이스 오케스트레이션을 처리하기 위한 자동화되고 추상화된 솔루션을 제안한다. 운영자로부터 도메인을 추상화하고 높은 수준의 의도 형태로 오케스트레이션 의도를 제공 할 수 있다. 또한 조정 된 리소스를 적극적으로 모니터링하고 머신 러닝을 사용하여 현재 모니터링 통계를 기반으로 시스템 상태 업데이트를 위한 향후 리소스 활용도를 예측한다. Closed-loop 자동화 E2E 네트워크 오케스트레이션 및 관리 시스템이 생성된다.

Keywords

Acknowledgement

This work was supported by the 2020 education, research and student guidance grant program funded by Jeju National University.

References

  1. 3GPP, TS 23.501 V15.0.0, Technical Specification Group Services and System Aspects; System Architecture for the 5G System; Release 15, Dec 2017.
  2. Eurecom, Open Air Interface Alliance. Open-Air Interface Project. Retrieved Oct. 22, 2018, from: https://gitlab.eurecom.fr/oai/
  3. ETSI, ETSI GS. NFV-MAN 001: Network Function Virtualisation (NFV): Management and Orchestration, 2014.
  4. Open Network Foundation, TR-521: SDN Architecture 1.1, 2016.
  5. Peter Hedman and NGMN P1 WS1 E2E Architecture team. Description of Network Slicing Concept, 2015.
  6. Open Network Foundation. Mobile-Central Office Rearchitected as a Datacenter (M-CORD) v4.1, Retrieved October. 22, 2018 From: https://guide.opencord.org/cord-4.1/
  7. GSA, Ericsson, Huawei, Nokia. 5G Network Slicing for Vertical Industries White Paper (2017), Retrieved Nov. 29, 2018, from https://www.huawei.com/minisite/5g/img/5g-network-slicing-for-vertical-industries-en.pdf
  8. Wireless World Research Forum. End to End Network Slicing, White Paper 3 (2017), Retrieved Nov. 29, 2018, from https://www.wwrf.ch/files/wwrf/content/files/publications/outlook/White%20Paper%203-End%20to%20End%20Network%20Slicing.pdf
  9. Godfrey Anuga Akpakwu, Bruno J. Silva, Gerhard P. Hancke and Adnan M. Abu-Mahfouz. "A Survey on 5G Networks for the Internet of Things: Communication Technologies and Challenges. IEEE Access, vol. 6, pp. 3619 - 3647, Feb. 2018 https://doi.org/10.1109/access.2017.2779844
  10. Kentis Angelos Mimidis, Ollora Zaballa Eder, Soler Jose "Policy Framework for the Next Generation Platform as a Service". Proceedings of 27th European Conference on Networks and Communications (EUCNC), 2018
  11. Malla Reddy Sama, Sergio Beker, Wolfgang Kiess and Srisakul Thakolsri. "Service-Based Slice Selection Function for 5G". IEEE Global Communication Conference (GLOBECOM), 2016
  12. Affirmed. Slice Selection Function, (Solution Provider) Retrieved Nov. 29, 2018, from : https://www.affirmednetworks.com/products-solutions/network-slicing/
  13. Abbas, K.; Afaq, M.; Ahmed Khan, T.; Rafiq, A.; Song, W.-C. Slicing the Core Network and Radio Access Network Domains through Intent-Based Networking for 5G Networks. Electronics 2020, 9, 1710. https://doi.org/10.3390/electronics9101710
  14. T. A. Khan, K. Abbass, A. Rafique, A. Muhammad and W. -C. Song, "Generic Intent-based Networking Platform for E2E Network Slice Orchestration & Lifecycle Management," 2020 21st Asia-Pacific Network Operations and Management Symposium (APNOMS), Daegu, Korea (South), 2020, pp. 49-54, doi: 10.23919/APNOMS50412.2020.9236962.
  15. Rafiq, A.; Mehmood, A.; Ahmed Khan, T.; Abbas, K.; Afaq, M.; Song, W.-C. Intent-Based End-to-End Network Service Orchestration System for Multi-Platforms. Sustainability 2020, 12, 2782. https://doi.org/10.3390/su12072782
  16. T. A. Khan, A. Mehmood, J. J. Diaz Rivera and W. Song, "Machine Learning Approach for Automatic Configuration and Management of 5G Platforms," 2019 20th Asia-Pacific Network Operations and Management Symposium (APNOMS), Matsue, Japan, 2019, pp. 1-6, doi: 10.23919/APNOMS.2019.8893119.
  17. Tarik Talib, Ibrahim Aflobi, Kontantinos Samdanis and Faqir Zarrar Yoysaf "On Multi-domain Network Slicing Orchestration Architecture & Federated Resource Control".
  18. Wang, Rui, et al. "End-to-End Quantum Secured Inter-Domain 5G Service Orchestration Over Dynamically Switched Flex-Grid Optical Networks Enabled by a q-ROADM." Journal of Lightwave Technology 38.1 (2019): 139-149. https://doi.org/10.1109/jlt.2019.2949864
  19. WANG Shihao, ZHUO Qinzheng, YAN Han, LI Qianmu, and QI Yong "A Network Traffic Prediction Method Based on LSTM", ZTE Communications 2019 No.2
  20. Khizar Abbas, Talha Ahmed Khan, Muhammad Afaq, Wang-Cheol Song. (2020). Multi-Domain Network Slicing using Intent-Based Networking. 한국통신학회 학술대회논문집, (), 222-223.
  21. Talha Ahmed Khan, Javier Diaz Rivera, Asif Mehmood, Wang-Cheol Song. (2018). Network Slicing Using Enhanced OpenAirInterface eNodeB and EPC under M-CORD Platform. Proceedings of Symposium of the Korean Institute of communications and Information Sciences, (), 182-183.
  22. Talha Ahmed Khan, Muhammad Afaq, Khizar Abbas, Adeel Rafiq, Asif Mehmood, Wang-Cheol Song. (2020). Generic Intent-Based Networking approach for end-to-end Slice Orchestration and Lifecycle Management. Proceedings of Symposium of the Korean Institute of communications and Information Sciences, (), 468-469.