The 2006 IEEE International Joint Conference on Neural Network Proceedings 2006
DOI: 10.1109/ijcnn.2006.247142
|View full text |Cite
|
Sign up to set email alerts
|

Internet Traffic Forecasting using Neural Networks

Abstract: Abstract-The forecast of Internet traffic is an important issue that has received few attention from the computer networks field. By improving this task, efficient traffic engineering and anomaly detection tools can be created, resulting in economic gains from better resource management. This paper presents a Neural Network Ensemble (NNE) for the prediction of TCP/IP traffic using a Time Series Forecasting (TSF) point of view. Several experiments were devised by considering real-world data from two large Inter… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
23
0

Year Published

2009
2009
2022
2022

Publication Types

Select...
4
3
1

Relationship

0
8

Authors

Journals

citations
Cited by 49 publications
(23 citation statements)
references
References 19 publications
0
23
0
Order By: Relevance
“…They observed that their mode is giving prediction efficiency and the accuracy. Daniel et al [8] proposed Simple Moving Average (SMA) and Exponential Moving Average (EMA) for prediction network traffic. They collected real network traffic from web services to test their model.…”
Section: Related Workmentioning
confidence: 99%
“…They observed that their mode is giving prediction efficiency and the accuracy. Daniel et al [8] proposed Simple Moving Average (SMA) and Exponential Moving Average (EMA) for prediction network traffic. They collected real network traffic from web services to test their model.…”
Section: Related Workmentioning
confidence: 99%
“…A time series is a sequence of data points or time ordered observations (y 1 , y 2 , ..., y t ) in which each period recorded at a specific time t. A time series forecasting is the use of a model to predict future values based on previously observed values [29,46]. For time series feature extraction, a trace (set of events) should be converted into time series with the regular time intervals.…”
Section: Time Series Analysismentioning
confidence: 99%
“…The choice of the input time intervals has a crucial effect in the PIT entries forecasting performance. A small number of time intervals will provide insufficient information, while a high number of intervals will increase the probability of irrelevant input features [29]. Several configurations based on our observations of PIT entries fluctuation in considered network topologies were set.…”
Section: Phase 1: Adaptive Trainingmentioning
confidence: 99%
See 1 more Smart Citation
“…One addresses the forecasting of hourly traffic of the next day based on past observations, and the other focuses on the peak load prediction of the next day. Based on Time Series Forecasting (TSF), (Cortez et al, 2006) uses a Neural Network Ensemble (NNE) to predict the TCP/IP traffic. Neural network based traffic prediction approach is complicated to implement.…”
Section: Application Of Neural Network In Traffic Forecastingmentioning
confidence: 99%