Predicting Throughput of Cloud Network Infrastructure Using Neural Networks
Authors:
- 10 May 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
Throughput prediction of network infrastructures is an important aspect of capacity planning, scheduling, resource management, route selection and other network functions. In this paper, we describe throughput measurements collected over a network infrastructure that supports cloud computing spanning the globe. We train deep learning models to predict TCP throughput using these measurements, which show performance improvements with buffer tuning and parallel streams. We also compare the accuracy of machine learning and conventional methods in predicting both single thread and mutli-stream throughput in a public cloud environment.Keywords
This publication has 17 references indexed in Scilit:
- A History-Based TCP Throughput Prediction Incorporating Communication Quality Features by Support Vector Regression for Mobile Network2017
- Throughput Estimation for Short Lived TCP Cubic Flows2016
- On the Properties of Neural Machine Translation: Encoder–Decoder Approaches2014
- Dynamic bandwidth provisioning using ARIMA-based traffic forecasting for Mobile WiMAXComputer Communications, 2011
- Formula-based TCP throughput prediction with available bandwidthIEEE Communications Letters, 2010
- On the predictability of large transfer TCP throughput2005
- Modeling TCP throughputACM SIGCOMM Computer Communication Review, 1998
- Long Short-Term MemoryNeural Computation, 1997
- High performance TCP in ANSNETACM SIGCOMM Computer Communication Review, 1994
- Learning long-term dependencies with gradient descent is difficultIEEE Transactions on Neural Networks, 1994