AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Intelligent and Converged Networks Article
PDF (2 MB)
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Open Access

Intelligent throughput stabilizer for UDP-based rate-control communication system

Michiko Harayama1( ), Noboru Miyagawa2
Department of Electric Electronics and Informatics, Faculty of Engineering, Gifu University, Gifu 501-1193, Japan
Department of Intelligence Science and Engineering, Graduate School of Natural Science and Technology, Gifu University, Gifu 501-1193, Japan
Show Author Information

Abstract

In view of the successful application of deep learning, mainly in the field of image recognition, deep learning applications are now being explored in the fields of communication and computer networks. In these fields, systems have been developed by use of proper theoretical calculations and procedures. However, due to the large amount of data to be processed, proper processing takes time and deviations from the theory sometimes occur due to the inclusion of uncertain disturbances. Therefore, deep learning or nonlinear approximation by neural networks may be useful in some cases. We have studied a user datagram protocol (UDP) based rate-control communication system called the simultaneous multipath communication system (SMPC), which measures throughput by a group of packets at the destination node and feeds it back to the source node continuously. By comparing the throughput with the recorded transmission rate, the source node detects congestion on the transmission route and adjusts the packet transmission interval. However, the throughput fluctuates as packets pass through the route, and if it is fed back directly, the transmission rate fluctuates greatly, causing the fluctuation of the throughput to become even larger. In addition, the average throughput becomes even lower. In this study, we tried to stabilize the transmission rate by incorporating prediction and learning performed by a neural network. The prediction is performed using the throughput measured by the destination node, and the result is learned so as to generate a stabilizer. A simple moving average method and a stabilizer using three types of neural networks, namely multilayer perceptrons, recurrent neural networks, and long short-term memory, were built into the transmission controller of the SMPC. The results showed that not only fluctuation reduced but also the average throughput improved. Together, the results demonstrated that deep learning can be used to predict and output stable values from data with complicated time fluctuations that are difficultly analyzed.

Keywords

neural networkthroughput stabilizerrate control communicationcongestion control

References

1
M. Masirap, M. H. Amaran, Y. M. Yussoff, R. Ab Rahman, and H. Hashim, Evaluation of reliable UDP-based transport protocols for Internet of Things (IoT), presented at 2016 IEEE Symp. Computer Applications & Industrial Electronics (ISCAIE), Penang, Malaysia, 2016, pp. 200–205.https://doi.org/10.1109/ISCAIE.2016.7575063
Crossref
2

M. H. Wang, L. W. Chen, P. W. Chi, and C. L. Lei, SDUDP: A reliable UDP-based transmission protocol over SDN, IEEE Access, vol. 5, pp. 5904–5916, 2017.
Crossref Google Scholar
3
D. Syzov, D. Kachan, K. Karpov, N. Mareev, and E. Siemens, Custom UDP-based transport protocol implementation over DPDK, in Proc. 7th Int. Conf. Applied Innovation in IT, Köthen, Germany, 2019, pp. 13–17.
4
T. Viernickel, A. Froemmgen, A. Rizk, B. Koldehofe, and R. Steinmetz, Multipath QUIC: A deployable multipath transport protocol, presented at 2018 IEEE Int. Conf. Communications (ICC), Kansas City, MO, USA, 2018, pp. 1–7.https://doi.org/10.1109/ICC.2018.8422951
Crossref
5
M. J. Anjum, I. Raza, and S. A. Hussain, Real-time multipath transmission protocol (RMTP): A software defined networks (SDN) based routing protocol for data centric networks, presented at 2019 Int. Conf. Electrical, Communication, and Computer Engineering (ICECCE), Swat, Pakistan, 2019, pp. 1–6.https://doi.org/10.1109/ICECCE47252.2019.8940652
Crossref
6

A. Tanaka and M. Harayama, Path priority control method for simultaneous multi-path communication, (in Japanese), IEICE Tech. Rep., vol. 113, no. 472, pp. 143–148, 2014.
Google Scholar
7

W. Mano and M. Harayama, Improved communication fairness of SMPC, (in Japanese), IEICE Tech. Rep., pp. 2018–2134, 2019.
Google Scholar
8

A. Tealab, Time series forecasting using artificial neural networks methodologies: A systematic review, Future Comput. Inform. J., vol. 3, no. 2, pp. 334–340, 2018.
Crossref Google Scholar
9

E. Chong, C. Han, and F. C. Park, Deep learning networks for stock market analysis and prediction: Methodology, data representations, and case studies, Expert Syst. Appl., vol. 83, pp. 187–205, 2017.
Crossref Google Scholar
10

K. Miyazaki and Y. Matsuo, Stock prediction analysis using deep learning technique, (in Japanese), JSAI, p. 2017 2D3-OS-19a-3, 2017.
Google Scholar
11

T. Matsui and T. Shiotsuki, Stock market prediction using LSTMs, (in Japanese), JSAI, p. 2017 2D3-OS-19a-2, 2017.
Google Scholar
12

Z. Md. Fadlullah, F. X. Tang, B. M. Mao, N. Kato, O. Akashi, T. Inoue, and K. Mizutani, State-of-the-Art deep learning: evolving machine intelligence toward tomorrow’s, intelligent network traffic control system, IEEE Commun. Surv. Tut., vol. 19, no. 4, pp. 2432–2455, 2017.
Crossref Google Scholar
13

H. Osanai, A. Nakao, Y. Week, M. Yamaguchi, and M. Oguchi, RNN prediction of network traffic fluctuation, (in Japanese), DEIM Forum, p. F1-6, 2018.
Google Scholar
14

K. Cheon, J. Kim, M. Hamadache, and D. Lee, On replacing PID controller with deep learning controller for DC motor system, J. Automat. Control Eng., vol. 3, no. 6, pp. 452–456, 2015.
Crossref Google Scholar
15

Q. X. Wu, C. M. Lin, W. B. Fang, F. Chao, L. Z. Yang, C. J. Shang, and C. L. Zhou, Self-organizing brain emotional learning controller network for intelligent control system of mobile robots, IEEE Access, vol. 6, pp. 59096–59108, 2018.
Crossref Google Scholar
16

V. T. Yen, W. Y. Nan, and P. Van Cuong, Recurrent fuzzy wavelet neural networks based on robust adaptive sliding mode control for industrial robot manipulators, Neural Comput. Appl., vol. 31, no. 11, pp. 6945–6958, 2019.
Crossref Google Scholar
17

G. Z. Zhang, W. H. Hu, D. Cao, Q. Huang, J. B. Yi, Z. Chen, and F. Blaabjerg, Deep reinforcement learning-based approach for proportional resonance power system stabilizer to prevent ultra-low-frequency oscillations, IEEE Trans. Smart Grid, vol. 11, no. 6, pp. 5260–5272, 2020.
Crossref Google Scholar
18
A. M. A. Aela, J. P. Kenne, and H. A. Mintsa, Adaptive neural network and nonlinear electrohydraulic active suspension control system, J. Vibrat. Control, doi: 10.1177/1077546320975979.https://doi.org/10.1177/1077546320975979
Crossref
19

Y. G. Sun, J. Q. Xu, G. B. Lin, and N. Sun, Adaptive neural network control for maglev vehicle systems with time-varying mass and external disturbance, Neural Comput. Appl., pp. 1–12, 2021.
Crossref Google Scholar
20
A. Langley, A. Riddoch, A. Wilk, A. Vicente, C. Krasic, D. Zhang, F. Yang, F. Kouranov, I. Swett, J. Iyengar, et al., The QUIC transport protocol: Design and internet-scale deployment, in Proc. Conf. ACM Special Interest Group on Data Communication, New York, NY, USA, 2017, pp. 183–196.https://doi.org/10.1145/3098822.3098842
Crossref
21
B. Montazeri, Y. L. Li, M. Alizadeh, and J. Ousterhout, Homa: A receiver-driven low-latency transport protocol using network priorities, in Proc. 2018 Conf. ACM Special Interest Group on Data Communication, New York, NY, USA, 2018, pp. 221–235.https://doi.org/10.1145/3230543.3230564
Crossref
22

A. Briones, A. Mallorquí, A. Zaballos, and R. M. de Pozuelo, Adaptive and aggressive transport protocol to provide QoS in cloud data exchange over Long Fat Networks, Future Generat. Comput. Syst., vol. 115, pp. 34–44, 2021.
Crossref Google Scholar
23

B. J. Zhou, J. Li, X. Y. Wang, Y. Gu, L. Xu, Y. Q. Hu, and L. H. Zhu, Online internet traffic monitoring system using spark streaming, Big Data Mining and Analytics, vol. 1, no. 1, pp. 47–56, 2018.
Crossref Google Scholar
24

A. D’Alconzo, I. Drago, A. Morichetta, M. Mellia, and P. Casas, A survey on big data for network traffic monitoring and analysis, IEEE Trans. Netw. Serv. Manage., vol. 16, no. 3, pp. 800–813, 2019.
Crossref Google Scholar
25

S. Dhingra, R. B. Madda, R. Patan, P. C. Jiao, K. Barri, and A. H. Alavi, Internet of things-based fog and cloud computing technology for smart traffic monitoring, Int. Things, vol. 14, p. 100175, 2020.
Crossref Google Scholar
Intelligent and Converged Networks
Volume 2 Issue 3,
September 2021
Pages 205-212
DOI: 10.23919/ICN.2021.0014
Cite this article:
Harayama M, Miyagawa N. Intelligent throughput stabilizer for UDP-based rate-control communication system. Intelligent and Converged Networks, 2021, 2(3): 205-212. https://doi.org/10.23919/ICN.2021.0014

719

Views

38

Downloads

1

Crossref

2

Scopus

Altmetrics
Received: 03 May 2020
Revised: 17 April 2021
Accepted: 09 June 2021
Published: 01 September 2021
© All articles included in the journal are copyrighted to the ITU and TUP.

This work is available under the CC BY-NC-ND 3.0 IGO license: https://creativecommons.org/licenses/by-nc-nd/3.0/igo/

Return