Predicting the network service quality via the log of hardware usage

Мұқаба

Дәйексөз келтіру

Толық мәтін

Ашық рұқсат Ашық рұқсат
Рұқсат жабық Рұқсат берілді
Рұқсат жабық Рұқсат ақылы немесе тек жазылушылар үшін

Аннотация

The costs of using a cloud computing infrastructure depend on its optimal configuration. The task is to reduce these costs and to support service quality at agreed level at the same time. To solve these tasks, we need methods for predicting the quality of the network service provided. Such predictions based on the logs of computing infrastructure usage, machine learning and methods for estimating service execution times are the subject of these work. These logs data are obtained through measurements and previously collected data on the operation of the telecommunications infrastructure. Measurements of infrastructure performance and service performance generate large amounts of data. The article discusses various methods for reducing dimensions and isolating significant variables in order to estimate discrepancies between target and predicted characteristics. In experiments, combining the model of a random forest with the method of reducing the dimensions via the principal component analysis has shown the best way.

Толық мәтін

Рұқсат жабық

Авторлар туралы

A. Grusho

Federal Research Center “Informatics and Management” RAS

Хат алмасуға жауапты Автор.
Email: grusho@yandex.ru
Ресей, Moscow

M. Zabezhailo

Federal Research Center “Informatics and Management” RAS

Email: m.zabezhailo@yandex.ru
Ресей, Moscow

V. Piskovski

Federal Research Center “Informatics and Management” RAS; Lomonosov Moscow State University

Email: vpiskovski@lvk.cs.msu.ru

Faculty of Computational Mathematics and Cybernetics

Ресей, Moscow; Moscow

E. Timonina

Federal Research Center “Informatics and Management” RAS

Email: eltimon@yandex.ru
Ресей, Moscow

Әдебиет тізімі

  1. Френкель С.Л., Захаров В.Н. Модель прогнозирования интернет-трафика // Искусственный интеллект и принятие решений. 2022. № 4. С. 66–77. https://doi.org/10.14357/20718594220407
  2. Лычева Е.О., Писковский В.О., Могиленец В.М. Прогнозирование временных характеристик прикладных сетевых сервисов // Тр. 5-й Междунар. конф. MODERN NETWORK TECHNOLOGIES (MONETEC-2024). М., Изд-во МГУ им. М.В. Ломоносова, 2024. С. 25–33.
  3. Lan X., Taghia J., Moradi F., Khoshkholghi M.A., Zec E., Mogren O., Mahmoodi T., Johnsson A. Federated Learning for Performance Prediction in Multi-operator Environments // ITU Journal on Future and Evolving Technologies. 2023. V.4. P. 166–177.
  4. Hu C.-H., Chen Z., Larsson E.G. Device Scheduling and Update Aggregation Policies for Asynchronous Federated Learning // IEEE 22nd International Workshop on Signal Processing Advances in Wireless Communications (SPAWC). Lucca, Italy, 2021. P. 281–285.
  5. Lee H.-S., Lee J.-W. Adaptive Transmission Scheduling in Wireless Networks for Asynchronous Federated Learning // IEEE Journal on Selected Areas in Communications. 2021. V. 39. № 12. P. 3673–3687.
  6. Almanifi O.R.A., Chow C.-O., Tham M.-L., Chuah J.H., Kanesan J. Communication and Computation Efficiency in Federated Learning: A survey // Internet of Things. 2023. V. 22.
  7. Lu R., Zhang W., Li Q., He H., Zhong X., Yang H. et al. Adaptive Asynchronous Federated Learning // Future Generation Computer Systems. 2024. V. 152. P. 193–206.
  8. Басок Б.М., Захаров В.Н., Френкель С.Л. Использование вероятностной модели вычислений для тестирования одного класса готовых к использованию программных компонентов локальных и сетевых систем // Информатика и ее применения. 2018. Т. 12. Вып. 4. С. 44–51. https://doi.org/10.14357/19922264180407
  9. Data Traces from a Data Center Testbed – Kaggle [электронный ресурс]. URL: www.kaggle.com/datasets/jaliltaghia/data-traces-from-a-data-center-testbed (дата обращения: 11.09.2023).
  10. Yanggratoke R., Ahmed J., Ardelius J., Flinta C., Johnsson A., Gillblad D., Stadler R.A. Service-agnostic Method for Predicting Service Metrics in Real Time // Intern. J. of Network Management. 2017. V. 28. № 2.
  11. Bishop C.M. Pattern Recognition and Machine Learning. N.Y.: Springer, 2006.
  12. Сайфутдинов Р.А. Исследование алгоритмов уменьшения размерности данных для задачи классификации. СПб.: СПбГУ, 2014.
  13. Hyperparameter Tuning: GridSearchCV and RandomizedSearchCV, Explained [электронный ресурс]. URL: www.kdnuggets.com/hyperparameter-tuning-gridsearchcv-and-randomizedsearchcv-explained (дата обращения: 24.12.2024).
  14. Grusho A., Grusho N., Zabezhailo M., Timonina E. On Some Possibilities of Using AI Methods in the Search for Cause-and-effect Relationships in Accumulated Empirical Data // Proc. 8th Intern. Scientific Conf. “Intelligent Information Technologies for Industry” (IITI 2024, Harbin, China, Nov. 1–7, 2024), Lecture Notes in Networks and Systems (LNNS) 1210. 2024. V. 2. Chap. 25. P. 280–290.

Қосымша файлдар

Қосымша файлдар
Әрекет
1. JATS XML
Жүктеу

© Russian Academy of Sciences, 2025