Szczegóły publikacji
Opis bibliograficzny
Continuous self-adaptation of control policies in automatic cloud management / Włodzimierz FUNIKA, Paweł Koperek, Jacek KITOWSKI // Concurrency and Computation : Practice and Experience ; ISSN 1532-0626. — 2023 — vol. 35 iss. 20 spec. iss. art. no. e7371, s. 1–12. — Bibliogr. s. 11–12, Abstr. — Publikacja dostępna online od: 2022-11-01. — P2S2 2020 : 17.08.2020, online ; P2S2 2021 : 9.08.2021, online ; EAI MobiMedia 2021 : 23–25.07.2021, Guiyang, People's Republic of China ; HeteroPar 2021 : 31.08.2021, Lisbon, Portugal
Autorzy (3)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 148326 |
|---|---|
| Data dodania do BaDAP | 2023-09-27 |
| DOI | 10.1002/cpe.7371 |
| Rok publikacji | 2023 |
| Typ publikacji | referat w czasopiśmie |
| Otwarty dostęp |  |
| Czasopismo/seria | Concurrency and Computation : Practice & Experience |
Abstract
Deep reinforcement learning has been recently a very active field of research. The policies generated with the use of this class of training algorithms are flexible and thus have many practical applications. In this article we present the results of our attempt to use the recent advancements in reinforcement learning to automate the management of resources in a compute cloud environment. We describe a new approach to self-adaptation of autonomous management, which uses a digital clone of the managed infrastructure to continuously update the control policy. We present the architecture of our system and discuss the results of evaluation which includes autonomous management of a sample application deployed to Amazon Web Services cloud. We also provide the details of the training of the management policy using the Proximal Policy Optimization algorithm. Finally, we discuss the feasibility to extend the presented approach to further scenarios.