Quality of Service Forecasting with LSTM Neural Network
| Authors | |
|---|---|
| Year of publication | 2019 |
| Type | Article in Proceedings |
| Conference | 2019 IFIP/IEEE Symposium on Integrated Network and Service Management (IM) |
| MU Faculty or unit | |
| Citation | |
| Web | |
| Keywords | quality of service; forecast; long short-term memory; neural network |
| Attached files | |
| 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. |
| Related projects: |