Preview

Advanced Engineering Research (Rostov-on-Don)

Advanced search

Artificial intelligence in data storage systems

https://doi.org/10.23947/1992-5980-2020-20-2-196-200

Abstract

Introduction. The artificial intelligence (AI) performance in data storage systems is considered. When working with data, the advantage of its use both in economic terms and for security is determined. The work objective is the introduction of artificial intelligence in data storage systems. The key tasks involve the description of methods for data separation, organization of itsstorage and counteraction to security threats.

Materials and Methods. The data that should be fed into the drives is divided into parts so that it can be restored without one of the parts. This is necessary to be able to access and recover information in the event of a software or hardware failure.

Results. The AI performance under detecting security threats is considered. Since the model implies the interaction of users with data, it was found out how the data access control is carried out and the keys are stored.

Discussion and Conclusions. The use of AI in organizing a data warehouse will speed up the system. Artificial intelligence with built-in machine-learning algorithms will provide responding to a situation that affects the state of the sys-tem. Analysis of the state of the drives will avoid a possible hardware or software failure. Minimization of the human factor in the system operation contributes to the improvement of its work.

About the Authors

V. V. Zhilin
Budenny Military Academy of Communication
Russian Federation
St. Petersburg.


O. A. Safar'yan
Don State Technical University
Russian Federation
Rostov-on-Don.


References

1. Mogilevskaya NS, Kul'bikayan RV, Zhuravlev LA. Porogovoe razdelenie failov na osnove bitovykh masok: ideya i vozmozhnoe primenenie [Threshold file sharing based on bit masks: concept and possible use]. Vestnik of DSTU. 2011;11(10):1749–1755. URL: https://vestnik.donstu.ru/jour/article/ view/912/907 (accessed 04.04.2020). (In Russ.)

2. Nikolenko SI, Kadurin AA, Arkhangel'skaya EV. Glubokoe obuchenie. Pogruzhenie v mir neironnykh setei [Deep learning. Immersion in the world of neural networks]. St. Petersburg: Piter; 2018. 481 p. (In Russ.)

3. Dubrova E. Fault-Tolerant Design. Springer; 2013. 185 p.

4. Flakh P. Mashinnoe obuchenie [Machine Learning]. Moscow: DMK Press; 2015. 400 p. (In Russ.)

5. Zhilin VV, Drozdova II, Cherkesova LV, et al. Trekhmernaya model' bezopasnosti komp'yuternykh sistem [Three-dimensional model of computer systems security]. Young Researcher of the Don. 2018;5:30‒37. URL: http://mid-journal. ru/upload/iblock/f81/6_620_ZHilin_30_37.pdf (accessed 04.05.2020). (In Russ.)

6. Parloff R. Why Deep Learning Is Suddenly Changing Your Life. Fortune. 2016. Retrieved 13 April, 2018.

7. Cormen Th, Leiserson Ch, Rivest R. Algoritmy: postroenie i analiz [Algorithms: construction and analysis]. Moscow: Vil'yams; 2006. 1296 p. (In Russ.)

8. Hutson M. Missing data hinder replication of artificial intelligence studies. Science. 15 February, 2018. doi:10.1126/science.aat3298.


Review

For citations:


Zhilin V.V., Safar'yan O.A. Artificial intelligence in data storage systems. Vestnik of Don State Technical University. 2020;20(2):196-200. https://doi.org/10.23947/1992-5980-2020-20-2-196-200

Views: 864


Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.


ISSN 2687-1653 (Online)