Quality of Service Forecasting with LSTM Neural Network
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14610%2F19%3A00108335" target="_blank" >RIV/00216224:14610/19:00108335 - isvavai.cz</a>
Result on the web
<a href="http://dl.ifip.org/db/conf/im/im2019/188793.pdf" target="_blank" >http://dl.ifip.org/db/conf/im/im2019/188793.pdf</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Quality of Service Forecasting with LSTM Neural Network
Original language description
A robust and accurate forecast of the Quality of Service (QoS) attributes is essential for effective web service recommendation, enhanced user experience, and service management. Deep learning methods, especially Long Short-Term Memory Neural Networks (LSTM NN), have proven to be worthy for sequence forecasting in various domains recently. In this paper, we pilot an experimental application of LSTM NN in the domain of QoS forecasting. We develop a LSTM NN model for QoS prediction and compare its forecast performance with existing approaches for QoS attribute forecasting -- ARIMA and Holt-Winters models. The approaches are compared on two real-world QoS attribute datasets created using centralized passive QoS attribute collection technique. Our results show that LSTM NN improves the accuracy of QoS forecast for attributes collected with high granularity while maintaining a reasonable computation time.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
2019 IFIP/IEEE Symposium on Integrated Network and Service Management (IM)
ISBN
9781728106182
ISSN
1573-0077
e-ISSN
—
Number of pages
10
Pages from-to
251-260
Publisher name
IEEE
Place of publication
Washington DC, USA
Event location
Washington DC, USA
Event date
Jan 1, 2019
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000469937200056