A service‐agnostic method for predicting service metrics in real time

Summary We predict performance metrics of cloud services using statistical learning, whereby the behaviour of a system is learned from observations. Specifically, we collect device and network statistics from a cloud testbed and apply regression methods to predict, in real‐time, client‐side service...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	International journal of network management Ročník 28; číslo 2
Hlavní autoři:	Yanggratoke, Rerngvit, Ahmed, Jawwad, Ardelius, John, Flinta, Christofer, Johnsson, Andreas, Gillblad, Daniel, Stadler, Rolf
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Chichester Wiley Subscription Services, Inc 01.03.2018
Témata:	Accuracy Cloud computing Design and implementations Distance learning Distributed computer systems Forecasting Learning systems machine learning Mean absolute error Network statistics Operating systems Performance measurement Performance metrics Prediction accuracy Predictions quality of service Real time Real time network Real-time analytics real-time network analytics Regression analysis Statistical analysis statistical learning Statistics Testbeds Video streaming Video transmission
ISSN:	1055-7148, 1099-1190, 1099-1190
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Summary We predict performance metrics of cloud services using statistical learning, whereby the behaviour of a system is learned from observations. Specifically, we collect device and network statistics from a cloud testbed and apply regression methods to predict, in real‐time, client‐side service metrics for video streaming and key‐value store services. Results from intensive evaluation on our testbed indicate that our method accurately predicts service metrics in real time (mean absolute error below 16% for video frame rate and read latency, for instance). Further, our method is service agnostic in the sense that it takes as input operating systems and network statistics instead of service‐specific metrics. We show that feature set reduction significantly improves the prediction accuracy in our case, while simultaneously reducing model computation time. We find that the prediction accuracy decreases when, instead of a single service, both services run on the same testbed simultaneously or when the network quality on the path between the server cluster and the client deteriorates. Finally, we discuss the design and implementation of a real‐time analytics engine, which processes streams of device statistics and service metrics from testbed sensors and produces model predictions through online learning. We collect device and network statistics from a cloud testbed and use statistical learning to predict client‐side service metrics for video streaming and key‐value store services. Our method predicts service metrics in real time, with mean absolute error below 16% for video frame rate and read latency. The method is service agnostic as it does not rely on service‐specific metrics on the server side. We find that feature set reduction can improve prediction accuracy, while significantly reducing model computation time.
Bibliografie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ISSN:	1055-7148 1099-1190 1099-1190
DOI:	10.1002/nem.1991