Early warning of core network capacity in space-terrestrial integrated networks

doi:10.23919/JSEE.2024.000072

Journal of Systems Engineering and Electronics ›› 2024, Vol. 35 ›› Issue (4): 855-864.doi: 10.23919/JSEE.2024.000072

• EMERGING DEVELOPMENTS ON SPACE-TEERRESTRIAL INTEGRATED NETWORK AND RELATED KEY TECHNOLOGIES • Previous Articles

Early warning of core network capacity in space-terrestrial integrated networks

Sai HAN¹^,*(), Ao LI¹(), Dongyue ZHANG¹(), Bin ZHU¹(), Zelin WANG¹(), Guangquan WANG¹(), Jie MIAO²(), Hongbing MA²()

¹ China Unicom Research Institute, Beijing 100044, China
² China United Network Communications Group Company Limited, Beijing 100033, China

Received:2023-04-10 Online:2024-08-18 Published:2024-08-06
Contact: Sai HAN E-mail:hans29@chinaunicom.cn;lia12@chinaunicom.cn;zhangdy131@chinaunicom.cn;zhubin15@chinaunicom.cn;wangzl172@chinaunicom.cn;wanggq122@chinaunicom.cn;miaojie9@chinaunicom.cn;mahb@chinaunicom.cn
About author:
HAN Sai was born in 1988. She received her Ph.D. degree from Technical University of Brausch-weig in 2016. She is a senior engineer in China Unicom Research Institute. Her research interests include autonomous network and network intelligence. E-mail: hans29@chinaunicom.cn

LI Ao was born in 1994. She received her M.S. degree from University of Manchester in 2017. She is an engineer in China Unicom Research Institute. Her research interests include autonomous network and network intelligence. E-mail: lia12@chinaunicom.cn

ZHANG Dongyue was born in 1995. She received her M.S. degree from Beijing Forestry University in 2019. She is an engineer in China Unicom Research Institute. Her research interests include autonomous network and network intelligence. E-mail: zhangdy131@chinaunicom.cn

ZHU Bin was born in 1980. He received his B.S. degree from Beijing University of Posts and Telecommunications in 2006. He is an engineer in China Unicom Research Institute. His research interests include key issues of satellite-terrestrial integrated networks. E-mail: zhubin15@chinaunicom.cn

WANG Zelin was born in 1983. He received his M.S. degree from Northwestern Polytechnical University in 2008. He is a senior engineer in China Unicom Research Institute. His research interests include Internet protocol (IP), cloud-network, whitebox, and software defined network. E-mail: wangzl172@chinaunicom.cn

WANG Guangquan was born in 1968. He received his B.S. degree from Nanjing University of posts and Telecommunications in 1989. He is a professorate senior engineer in China Unicom Research Institute. His research interests include network planning, new technology evolution, and standard establishment. E-mail: wanggq122@chinaunicom.cn

MIAO Jie was born in 1983. He received his Ph.D. degree from Beijing University of Posts and Telecommunications. He is a senior engineer in China United Network Communications Group Company Limited. His research interests include network function virtualization, 5G network slice, and automatic support system. E-mail: miaojie9@chinaunicom.cn

MA Hongbing was born in 1967. He received his M.S. degree from Beijing University of posts and Telecommunications in 1989. He is a professorate senior engineer in China United Network Communications Group Company Limited. His research interests include new technology research in wireless communication, standard establishment, and technical testing. E-mail: mahb@chinaunicom.cn
Supported by:
This work was supported by the National Key Research Plan (2021YFB2900602).

Abstract

Abstract:

With the rapid development of low-orbit satellite communication networks both domestically and internationally, space-terrestrial integrated networks will become the future development trend. For space and terrestrial networks with limited resources, the utilization efficiency of the entire space-terrestrial integrated networks resources can be affected by the core network indirectly. In order to improve the response efficiency of core networks expansion construction, early warning of the core network elements capacity is necessary. Based on the integrated architecture of space and terrestrial network, multidimensional factors are considered in this paper, including the number of terminals, login users, and the rules of users’ migration during holidays. Using artifical intelligence (AI) technologies, the registered users of the access and mobility management function (AMF), authorization users of the unified data management (UDM), protocol data unit (PDU) sessions of session management function (SMF) are predicted in combination with the number of login users, the number of terminals. Therefore, the core network elements capacity can be predicted in advance. The proposed method is proven to be effective based on the data from real network.

Key words: space-terrestrial integrated networks, core network, element capacity, artificial intelligent (AI)

Sai HAN, Ao LI, Dongyue ZHANG, Bin ZHU, Zelin WANG, Guangquan WANG, Jie MIAO, Hongbing MA. Early warning of core network capacity in space-terrestrial integrated networks[J]. Journal of Systems Engineering and Electronics, 2024, 35(4): 855-864.

Figures/Tables 12

Fig 1

Fig 2

Fig 3

Table 1

Fig 4

Fig 5

Fig 6

Table 2

Fig 7

Table 3

Fig 8

Table 4

References 41

1	TANG F L. Dynamically adaptive cooperation transmission among satellite-ground integrated networks. Proc. of the Conference on Computer Communications, 2020: 1559−1568.
2	DING H X, ZHU S C, MENG S C L, et al Matching-based resource allocation for satellite-ground network. Sensors, 2022, 22 (21): 8436- 8447. doi: 10.3390/s22218436
3	YANG L, MA W D, WEI D B Offloading strategy in satellite-ground network. Journal of Physics: Conference Series, 2022, 2290 (1): 012118- 012125. doi: 10.1088/1742-6596/2290/1/012118
4	LIU Y, DING S H, HUANG J X, et al. Vertical handover of satellite-ground fusion network based on time and location under early access strategy. Proc. of the International Conference on Smart Computing and Communication, 2022: 384−393.
5	ZHAO M, CHEN C, LIU L, et al Orbital collaborative learning in 6G space-air-ground integrated networks. Neurocomputing, 2022, 497, 94- 109. doi: 10.1016/j.neucom.2022.04.098
6	LIU Y, PENG M G Satellite-ground fusion intelligent networking: vision and key technologies. Journal of Beijing University of Posts and Telecommunications, 2021, 44 (6): 1- 12.
7	GUTIERREZ-ESTEVEZ D M, GRAMAGLIA M, DOMENICO A D, et al Artificial intelligence for elastic management and orchestration of 5G networks. IEEE Wireless Communications, 2019, 26 (5): 134- 141. doi: 10.1109/MWC.2019.1800498
8	HAN S, MA H B, ZHANG P, et al Improved MPEG-4 high-efficiency AAC with variable-length soft-decision decoding of the quantized spectral coefficients. China Communications, 2019, 16 (10): 65- 82. doi: 10.23919/JCC.2019.10.005
9	CHEN M Z, WEI X, GAO Y, et al. Deep-broad learning system for traffic flow prediction toward 5G cellular wireless network. Proc. of International Wireless Communications and Mobile Computing, 2020: 940−945.
10	HAN S, WANG Z L, WANG G Q, et al. Automatic association of cross-domain network topology. Proc. of the IEEE International Conference on Trust, Security and Privacy in Computing and Communications, 2022: 1173−1178.
11	NIE L S, NING Z L, OBAIDAT M S, et al A reinforcement learning-based network traffic prediction mechanism in intelligent internet of things. IEEE Trans. on Industrial Informatics, 2021, 17 (3): 2169- 2180. doi: 10.1109/TII.2020.3004232
12	SELVAMANJU E, SHALINI V B. Machine learning based mobile data traffic prediction in 5G cellular networks. Proc. of the 5th International Conference on Electronics, Communication and Aerospace Technology, 2021: 1318−1324.
13	HAN S, MA H B, CHEN D, et al. Streaming video optimization in mobile communications. Proc. of the IEEE/CIC International Conference on Communications in China, 2018: 495−499.
14	BARADIE S, REDDY R, LIPPS C, et al. Managing the fifth generation (5G) wireless mobile communication: a machine learning approach for network traffic prediction. Proc. of the IEEE 26th International Symposium on Mobile Communication Technologies and Applications, 2022. https://ieeexplore.ieee.org/abstract/document/9861870.
15	ALAWE I, KSENTINI A, HADJADJ-AOUL Y, et al Improving traffic forecasting for 5G core network scalability: a machine learning approach. IEEE Network, 2018, 32 (6): 42- 49. doi: 10.1109/MNET.2018.1800104
16	DENG D S. Research on Anomaly Detection method based on DBSCAN clustering algorithm. Proc. of the 5th International Conference on Information Science, Computer Technology and Transportation, 2020: 439−442.
17	HIRAI S, BABA H, MATSUMOTO M, et al. Machine learning based performance prediction for cloud-native 5G mobile core network. Proc. of the IEEE Wireless Communications and Networking Conference, 2022: 1230−1235.
18	CHAKRABORTY P, CORICI M, MAGEDANZ T. A comparative study for time series forecasting within software 5G networks. Prof. of the 14th International Conference on Signal Processing and Communication Systems, 2020. DOI: 10.1109/ICSPCS50536.2020.9310033.
19	CHAKRABORTY P, CORICI M, MAGEDANZ T. System failure prediction within software 5G core networks using time series forecasting. Proc. of the IEEE International Conference on Communications Workshops, 2021. DOI: 10.1109/ICCWorkshops50388.2021.9473530.
20	KURANAGE M P J, NUAYMI L, BOUABDALLAH A, et al. Deep learning based resource forecasting for 5G core network scaling in kubernetes environment. Proc. of the 8th International Conference on Network Softwarization, 2022: 139−144.
21	NGUYEN H T, DO T V, ROTTER C Scaling UPF instances in 5G/6G core with deep reinforcement learning. IEEE Access, 2021, 9, 165892- 165906. doi: 10.1109/ACCESS.2021.3135315
22	YAO H P, WANG L Y, WANG X D, et al The space-terrestrial integrated network: an overview. IEEE Communications Magazine, 2018, 56 (9): 178- 185. doi: 10.1109/MCOM.2018.1700038
23	CHEN L, TANG F L, LI Z T, et al. Time-varying resource graph based resource model for space-terrestrial integrated networks. Proc. of the Conference on Computer Communications, 2021. DOI: 10.1109/INFOCOM42981.2021.9488855.
24	ZHANG N, ZHANG S, YANG P, et al Software defined space-air-ground integrated vehicular networks: challenges and solutions. IEEE Communications Magazine, 2017, 55 (7): 101- 109. doi: 10.1109/MCOM.2017.1601156
25	LIU J J, SHI Y P, FADLULLAH Z M, et al Space-air-ground integrated network: a survey. IEEE Communications Surveys and Tutorials, 2018, 20 (4): 2714- 2741. doi: 10.1109/COMST.2018.2841996
26	ARANI A H, HU P, ZHU Y Y Fairness-aware link optimization for space-terrestrial integrated networks: a reinforcement learning framework. IEEE Access, 2021, 9, 77624- 77636. doi: 10.1109/ACCESS.2021.3082862
27	WEI L H, SHUAI J C, LIU Y, et al Service customized space-air-ground integrated network for immersive media: architecture, key technologies, and prospects. China Communications, 2022, 19 (1): 1- 13. doi: 10.23919/JCC.2022.9693488
28	WANG X Y, SUN T, DUAN X D, et al Holistic service-based architecture for space-air-ground integrated network for 5G-advanced and beyond. China Communications, 2022, 19 (1): 14- 28. doi: 10.23919/JCC.2022.01.002
29	ZHOU Z H, MA J X, WAN G N, et al. Research on 6G satellite-terrestrial integrated network architecture. Proc. of the 7th International Conference on Cyber Security and Information Engineering, 2022: 1057−1062.
30	DONG G, PAN L, ZHANG Y, et al. Air-space-ground integrated information network: technology, development and prospect. Proc. of the 8th International Conference on Signal and Information Processing, Networking and Computers, 2022: 883−891.
31	SHENG J, CAI X Q, LI Q Y, et al Space-air-ground integrated network development and applications in high-speed railways: a survey. IEEE Trans. on Intelligent Transportation Systems, 2021, 23 (8): 10066- 10085.
32	PEI Y S, MIAO S Y, LI F C. Challenges and opportunities for terrestrial network operators in the air-space-ground integrated network. Proc. of the International Conference on Parallel and Distributed Processing with Applications, Big Data and Cloud Computing, Sustainable Computing and Communications, Social Computing and Networking, 2020: 1400−1404.
33	CHI L H, LIN C W, LIN W H, et al. Research on development of space-ground integration information network. Proc. of the International Conference on Urban Engineering and Management Science, 2020: 29−32.
34	PEI Y, ZHANG Z, WANG T Development vision and challenge of air-space-ground integrated network. Designing Techniques of Posts and Telecommunications, 2020, 63 (4): 15- 20.
35	TAYLOR S J, LETHAM B Forecasting at scale. The American Statistician, 2018, 72 (1): 37- 45. doi: 10.1080/00031305.2017.1380080
36	CHAKRABORTY P, CORICI M, MAGEDANZ T. A comparative study for time series forecasting within software 5G networks. Proc. of the 14th International Conference on Signal Processing and Communication Systems, 2020. DOI: 10.1109/ICSPCS50536.2020.9310033.
37	RANGAPURAM S S, SEEGER M W, GASTHAUS J, et al. Deep state space models for time series forecasting. Proc. of the 32nd Conference on Neural Information Processing Systems, 2018: 7796–7805.
38	LIU Z X, FENG Y, YIN Y N, et al. DeepState: selecting test suites to enhance the robustness of recurrent neural networks. Proc. of the 44th International Conference on Software Engineering, 2022: 598−609.
39	ZHANG D B A coefficient of determination for generalized linear models. The American Statistician, 2017, 71 (4): 310- 316. doi: 10.1080/00031305.2016.1256839
40	ALMOHAMMEDI A M, ZERGUINE A, DERICHE M, et al. Artificial bee colony DLMS beyond mean square error boundary in ad-hoc WSN. Proc. of the 14th International Conference on Computational Intelligence and Communication Networks, 2022: 572−576.
41	YAMAKI S, SEKI S, SUGITA N, et al. Performance evaluation of cross correlation functions based on correlation filters. Proc. of the 20th International Symposium on Communications and Information Technologies, 2021: 145−149.

Feature	AMF/Ten thousand users	UDM/Ten thousand users	SMF/ Ten thousands sessions
NU/Ten thousand users	0.876026	0.985335	0.847536
NT/Ten thousand users	0.871045	0.968826	0.833428
Holiday	−0.264972	−0.027671	−0.299663
Workday	−0.143109	−0.008093	−0.180952
Weekend	−0.00803	0.000481	−0.028388

Parameter	Prophet	DeepState
MSE	0.000029	0.008465
R²	0.944	0.83

Parameter	Prophet	DeepState
MSE	0.000068	0.048908
R²	0.893	0.36

Parameter	Prophet	DeepState
MSE	0.000014	0.002061
R²	0.954	0.98

Early warning of core network capacity in space-terrestrial integrated networks

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

Share this article

Figures/Tables 12

References 41

Related Articles 0

Recommended Articles

Metrics

Comments