Szczegóły publikacji
Opis bibliograficzny
Management of heterogeneous cloud resources with use of the PPO / Włodzimierz FUNIKA, Paweł Koperek, Jacek KITOWSKI // W: Euro-Par 2020: Parallel Processing Workshops : Euro-Par 2020 international workshops : Warsaw, Poland, August 24–25, 2020 : revised selected papers / eds. Bartosz Baliś, [et al.]. — Cham : Springer Nature Switzerland, cop. 2021. — (Lecture Notes in Computer Science ; ISSN 0302-9743 ; LNCS 12480. Theoretical Computer Science and General Issues ; ISSN 0302-9743). — ISBN: 978-3-030-71592-2; e-ISBN: 978-3-030-71593-9. — S. 148–159. — Bibliogr. s. 158–159, Abstr. — Publikacja dostępna online od: 2021-03-14. — J. Kitowski - dod. afiliacja: ACC CYFRONET AGH
Autorzy (3)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 133311 |
|---|---|
| Data dodania do BaDAP | 2021-04-09 |
| DOI | 10.1007/978-3-030-71593-9_12 |
| Rok publikacji | 2021 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Springer |
| Konferencja | International Conference on Parallel and Distributed Computing |
| Czasopisma/serie | Lecture Notes in Computer Science, Theoretical Computer Science and General Issues |
Abstract
Reinforcement learning has been recently a very active field of research. Thanks to combining it with Deep Learning, many newly designed algorithms improve the state of the art. In this paper we present the results of our attempt to use the recent advancements in Reinforcement Learning to automate the management of heterogeneous resources in an environment which hosts a compute-intensive evolutionary process. We describe the architecture of our system and present evaluation results. The experiments include autonomous management of a sample workload and a comparison of its performance to the traditional automatic management approach. We also provide the details of training of the management policy using the Proximal Policy Optimization algorithm. Finally, we discuss the feasibility to extend the presented approach to other scenarios.