Development of New Models Using Machine Learning Methods Combined with Different Time Lags for Network Traffic Forecasting

Front Cover
Dissertation.com, Jun 25, 2017 - Computers - 112 pages

The purpose of this thesis is to forecast the amount of network traffic in Transmission Control Protocol/Internet Protocol (TCP/IP) -based networks by using different time lags and various machine learning methods including Support Vector Machines (SVM), Multilayer Perceptron (MLP), Radial Basis Function (RBF) Neural Network, M5P (a decision tree with linear regression functions at the nodes), Random Forest (RF), Random Tree (RT), and Reduced Error Prunning Error (REPTree), and statistical regression methods including Multiple Linear Regression (MLR) and Holt-Winters and compare the performance of statistical and machine learning methods. Two different Internet Service Providers' (ISPs) traffic data have been utilized to build traffic forecasting models. The first 66% of the data sets has been utilized as training sets and the rest has been used as test sets. The performance of the forecasting models for the data sets has been assessed using Mean Absulote Percentage Error (MAPE). The results show that SVM and M5P based models usually perform better than the ones obtained by the other methods. 

 

Selected pages

Contents

INTRODUCTION
1
OVERVIEW OF METHODS
15
DEVELOPMENT OF PREDICTION MODELS
36
RESULTS AND DISCUSSION
51
CONCLUSION
98
Copyright

Common terms and phrases

algorithm ANN category ANN SVM Decision ARMA attributes Auto-Regressive average MAPE’s based prediction models category DS1-5M category DS2-1H Cortez data set Decision Trees category develop Internet traffic DS2-5M data set Feed-Forward forecast Internet traffic hidden layer hyperplane Illustration of average input Internet traffic forecasting intervals for values linear regression lower MAPE’s M5 tree M5P RF RT machine learning methods MAPE values MAPE’s of M5P MLP and RBF MLP based prediction Models Figure Models M5P Models MLP RBF Moving Average Multilayer Perceptron network traffic Neural Network node output Percentage decrease rates prediction models give prediction models yield Radial Basis Function Random Forest rates in average rates in MAPE’s REPTree based models REPTree based prediction rest of forecasting RF RT REPTree SARIMA seasonal snear snew Statistical ANN SVM statistical category Support Vector Machine Support Vector Regression SVM based prediction SVM category SVM Decision Trees traffic forecasting models Trees Categories Figure

Bibliographic information

TitleDevelopment of New Models Using Machine Learning Methods Combined with Different Time Lags for Network Traffic Forecasting
AuthorDerman Akgol
PublisherDissertation.com, 2017
ISBN1612334601, 9781612334608
Length112 pages
Subjects › 

Computers / Neural Networks
  
Export CitationBiBTeX EndNote RefMan