Search: onr:"swepub:oai:DiVA.org:umu-182918" >
Multivariate Time S...
Multivariate Time Series Synthesis Using Generative Adversarial Networks
-
- Leznik, Mark (author)
- Ulm University, Ulm, Germany
-
- Michalsky, Patrick (author)
- Ulm University, Ulm, Germany
-
- Willis, Peter (author)
- BT Applied Research, Ipswich, United Kingdom
-
show more...
-
- Schanzel, Benjamin (author)
- Ulm University, Ulm, Germany
-
- Östberg, Per-Olov (author)
- Umeå universitet,Institutionen för datavetenskap
-
- Domaschka, Jörg (author)
- Ulm University, Ulm, Germany
-
show less...
-
(creator_code:org_t)
- 2021-04-09
- 2021
- English.
-
In: ICPE 2021. - New York, NY, USA : Association for Computing Machinery, Inc. - 9781450381949 ; , s. 43-50
- Related links:
-
https://doi.org/10.1...
-
show more...
-
https://umu.diva-por... (primary) (Raw object)
-
http://umu.diva-port...
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- Collection and analysis of distributed (cloud) computing workloads allows for a deeper understanding of user and system behavior and is necessary for efficient operation of infrastructures and applications. The availability of such workload data is however often limited as most cloud infrastructures are commercially operated and monitoring data is considered proprietary or falls under GPDR regulations. This work investigates the generation of synthetic workloads using Generative Adversarial Networks and addresses a current need for more data and better tools for workload generation. Resource utilization measurements such as the utilization rates of Content Delivery Network (CDN) caches are generated and a comparative evaluation pipeline using descriptive statistics and time-series analysis is developed to assess the statistical similarity of generated and measured workloads. We use CDN data open sourced by us in a data generation pipeline as well as back-end ISP workload data to demonstrate the multivariate synthesis capability of our approach. The work contributes a generation method for multivariate time series workload generation that can provide arbitrary amounts of statistically similar data sets based on small subsets of real data. The presented technique shows promising results, in particular for heterogeneous workloads not too irregular in temporal behavior.
Subject headings
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Datorsystem (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Computer Systems (hsv//eng)
Keyword
- generative adversarial networks
- server workload
- synthetic data
- time series synthesis
- workload generation
Publication and Content Type
- ref (subject category)
- kon (subject category)
Find in a library
-
ICPE 2021
(Search for host publication in LIBRIS)
To the university's database