Use of sockets technology in the network system of a virtual laboratory based on machine learning algorithms

DOI: 10.31673/2412-4338.2022.023242

Abstract

The use of virtual laboratory systems has become a modern trend in many areas of human activity. Modern networked virtual laboratories use virtual reality technology to implement laboratory simulations and interactive environment technology to control simulations. The work examines the advantages, principles of building a virtual laboratory and existing problems in the communication mechanism. In particular, when exchanging data between node machines in a network virtual laboratory system, the network layer cannot ensure the same transmission of packet data. The article reviews modern methods of machine learning: supervised, unsupervised, semi-supervised and reinforcement learning. It was determined that the main characteristics of the virtual laboratory system architecture are openness, modularity and real-time communication. The communication mechanism of the virtual laboratory system does not meet the requirements of high bandwidth and real-time two-way communication. To solve the problem of technical requirements of high throughput and ultra-low delay of the virtual laboratory system, a communication planning technology based on a deep machine learning algorithm is proposed. The work uses the Socket mechanism to implement communication based on the TCP/IP protocol. In accordance with the technical requirements of high throughput and ultra-low latency of the network system of the virtual experiment, a technology of self-tuning and optimal planning of the communication network based on the deep machine learning algorithm is proposed. The proposed technology makes it possible to make the optimal decision regarding resource planning and implement optimization of the indirect selection of system parameters.

Keywords: network virtual laboratory, machine learning, sockets, TCP/IP protocol, planning technology.

References:

1. Budai T., Kuczmann M. Towards a Modern, Integrated Virtual Laboratory. Acta Polytechnica Hungarica. 2018. Vol. 15, No. 3, P. 191-204.
2. Zeng W.,  Hao F.. Study on Virtual Simulation Experiment System of Fire Escape and Emergency Evacuation. Proceedings of the 2021 International Conference on Diversified Education and Social Development (DESD 2021). 4 August 2021. P.68-72.
3. Caminero A. C., Ros S., Hernández R., Robles-Gómez A., Tobarra L. and Granjo P. J. T. Virtual remote laboratories management system (TUTORES): Using cloud computing to acquire University practical skills. IEEE Trans. Learn. Technol. 2016. Vol. 9, No 2, P. 133-145.
4. Hou W., Ning Z., Guo L., Chen Z., Obaidat M. S. Novel framework of risk-aware virtual network embedding in optical data center networks. IEEE Syst. J. 2018. Vol. 12, No 3.P. 2473-2482.
5. Torre L., Guinaldo M., Heradio R., Dormido S. The ball and beam system: A case study of virtual and remote lab enhancement with moodle. IEEE Trans. Ind. Informat. 2015. 11, No. 4. P. 934-945.
6. Buczak A. L., Guven E. A survey of data mining and machine learning methods for cyber security intrusion detection. IEEE Commun. Surveys Tuts. 2016. Vol. 18, No 2. P. 1153-1176.
7. Sun Y., Babu P., Palomar D. Majorization-minimization algorithms in signal processing communications and machine learning. IEEE Trans. Signal Process. Vol. 65, No 3. – P. 794-816.
8. Yarkoni T., Westfall J. Choosing prediction over explanation in psychology: Lessons from machine learning. Psychol. Sci. 2017. Vol. 12, No. 6. P. 1100-1122.
9. Parish E. J,. Duraisamy K. A paradigm for data-driven predictive modeling using field inversion and machine learning. Comput. Phys. 2016. Vol. 305. P. 758-774.
10. Fontana F. A., Mäntylä M. V., Zanoni M., Marino A. Comparing and experimenting machine learning techniques for code smell detection. Empirical Softw. Eng., 2016. Vol. 21, No 3, P. 1143-1191.
11. Pasolli E., Truong D. T., Malik F., Waldron L., Segata N. Machine learning meta-analysis of large metagenomic datasets: Tools and biological insights. PLoS Comput. Biol. 2016. Vol. 12, No 7.
12. .Deva Kumari A., Prem Kumar J., Prakash V. S., Divya K. S. Supervised Learning Algorithms: A Comparison. Kristu Jayanti Journal of Computational Sciences (KJCS). 2021. Vol.1, No 1, P. 01-12.
13. Grishkun E., Kravchenko S., Levchenko A., Lysogor Y. Machine learning methods. Znanstvena misel. 2020. Vol. 1, No 39. С.55-58Turhan K., Kayikcioglu T. Implementation of a virtual private network-based laboratory information system serving a rural area in Turkey. Lab. Med. 2006. Vol. 37. P. 527-531.
14. Engelen J.E., Hoos H.H. A survey on semi-supervised learning. Mach Learn. 2020.No109, P. 373–440.
15. Maltsev A. Yu. Review of the principles of deep learning as a dynamic theory of artificial intelligence. Academic notes of TNU named after V.I. Vernadskyi. Series: Technical Sciences 2021. Volume 32 (71) No. 6. P. 97-102.
16. Si H., Sun C., Chen B., Shi L., Qiao H. Analysis of Socket Communication Technology Based on Machine Learning Algorithms Under TCP/IP Protocol in Network Virtual Laboratory System. in IEEE Access. 2019. Vol. 7. P. 80453-80464
17. Phoemphon S., So-In C., Leelathakul N. Fuzzy weighted centroid localization with virtual node approximation in wireless sensor networks. IEEE Internet Things J. 2018. Vol. 5, No 6, P. 4728-4752.
18. Bai J., Wang W., Lu M., Wang H., J. Wang. TD-WS: A threat detection tool of WebSocket and Web storage in HTML5 websites. Secur. Commun. Netw. 2016. Vol. 9, No. 18, P. 5432-5443.
19. Samain J., Carofiglio G., Muscariello L., Papalini M., Sardara M., Tortelli M. Dynamic adaptive video streaming: Towards a systematic comparison of ICN and TCP/IP. IEEE Trans. Multimedia. 2017. Vol. 19, No. 10. P. 2166-2181.
20. Wang J.-S., Yang G.-H. Data-driven methods for stealthy attacks on TCP/IP-based networked control systems equipped with attack detectors. IEEE Trans. Cybern. 2019. Vol. 49, No 8, P. 3020-3031.
21. Quan L., Xu Z., Li Z. Implementation of hardware TCP/IP stack for DAQ systems with flexible data channel. Electron. Lett. 2017. Vol. 53, No. 8. P. 530-532.
22. Gomez-Sacristan A., Sempere-Paya V. M., Rodriguez-Hernandez M. A. Virtual laboratory for QoS study in next-generation networks with metro Ethernet access. IEEE Trans. Educ. 2016. Vol. 59, No 3. P. 187-193.