Machine Learning Classification and Regression Approaches for Optical Network Traffic Prediction

Rapid growth of network traffic causes the need for the development of new network technologies. Artificial intelligence provides suitable tools to improve currently used network optimization methods. In this paper, we propose a procedure for network traffic prediction. Based on optical networks’ (and other network technologies) characteristics, we focus on the prediction of fixed bitrate levels called traffic levels. We develop and evaluate two approaches based on different supervised machine learning (ML) methods—classification and regression. We examine four different ML models with various selected features. The tested datasets are based on real traffic patterns provided by the Seattle Internet Exchange Point (SIX). Obtained results are analyzed using a new quality metric, which allows researchers to find the best forecasting algorithm in terms of network resources usage and operational costs. Our research shows that regression provides better results than classification in case of all analyzed datasets. Additionally, the final choice of the most appropriate ML algorithm and model should depend on the network operator expectations.

Download Full-text

Application of Machine Learning Algorithms for Traffic Forecasting in Dynamic Optical Networks with Service Function Chains

Foundations of Computing and Decision Sciences ◽

10.2478/fcds-2020-0012 ◽

2020 ◽

Vol 45 (3) ◽

pp. 217-232

Author(s):

Daniel Szostak ◽

Krzysztof Walkowiak

Keyword(s):

Machine Learning ◽

Optical Networks ◽

Network Traffic ◽

Optical Network ◽

Machine Learning Algorithms ◽

Network Function Virtualization ◽

Service Function ◽

Traffic Forecasting ◽

Network Function ◽

Traffic Characteristics

AbstractKnowledge about future optical network traffic can be beneficial for network operators in terms of decreasing an operational cost due to efficient resource management. Machine Learning (ML) algorithms can be employed for forecasting traffic with high accuracy. In this paper we describe a methodology for predicting traffic in a dynamic optical network with service function chains (SFC). We assume that SFC is based on the Network Function Virtualization (NFV) paradigm. Moreover, other type of traffic, i.e. regular traffic, can also occur in the network. As a proof of effectiveness of our methodology we present and discuss numerical results of experiments run on three benchmark networks. We examine six ML classifiers. Our research shows that it is possible to predict a future traffic in an optical network, where SFC can be distinguished. However, there is no one universal classifier that can be used for each network. Choice of an ML algorithm should be done based on a network traffic characteristics analysis.

Download Full-text

Machine Learning Ensemble Methods for Optical Network Traffic Prediction

10.1007/978-3-030-87872-6_11 ◽

2021 ◽

pp. 105-115

Author(s):

Daniel Szostak

Keyword(s):

Machine Learning ◽

Network Traffic ◽

Optical Network ◽

Ensemble Methods ◽

Traffic Prediction

Download Full-text

Source allocation of per- and polyfluoroalkyl substances (PFAS) with supervised machine learning: Classification performance and the role of feature selection in an expanded dataset

Chemosphere ◽

10.1016/j.chemosphere.2021.130124 ◽

2021 ◽

Vol 275 ◽

pp. 130124

Author(s):

Tohren C.G. Kibbey ◽

Rafal Jabrzemski ◽

Denis M. O’Carroll

Keyword(s):

Machine Learning ◽

Feature Selection ◽

Classification Performance ◽

Supervised Machine Learning ◽

Machine Learning Classification ◽

Polyfluoroalkyl Substances ◽

Source Allocation

Download Full-text

Evaluating disaster-related tweet credibility using content-based and user-based features

Information Discovery and Delivery ◽

10.1108/idd-04-2020-0044 ◽

2021 ◽

Vol ahead-of-print (ahead-of-print) ◽

Author(s):

Nasser Assery ◽

Yuan (Dorothy) Xiaohong ◽

Qu Xiuli ◽

Roy Kaushik ◽

Sultan Almalki

Keyword(s):

Machine Learning ◽

Unsupervised Learning ◽

Supervised Learning ◽

Emergency Response ◽

Learning Model ◽

Performance Comparison ◽

Supervised Machine Learning ◽

Learning Methods ◽

Content Type ◽

Machine Learning Classification

Purpose This study aims to propose an unsupervised learning model to evaluate the credibility of disaster-related Twitter data and present a performance comparison with commonly used supervised machine learning models. Design/methodology/approach First historical tweets on two recent hurricane events are collected via Twitter API. Then a credibility scoring system is implemented in which the tweet features are analyzed to give a credibility score and credibility label to the tweet. After that, supervised machine learning classification is implemented using various classification algorithms and their performances are compared. Findings The proposed unsupervised learning model could enhance the emergency response by providing a fast way to determine the credibility of disaster-related tweets. Additionally, the comparison of the supervised classification models reveals that the Random Forest classifier performs significantly better than the SVM and Logistic Regression classifiers in classifying the credibility of disaster-related tweets. Originality/value In this paper, an unsupervised 10-point scoring model is proposed to evaluate the tweets’ credibility based on the user-based and content-based features. This technique could be used to evaluate the credibility of disaster-related tweets on future hurricanes and would have the potential to enhance emergency response during critical events. The comparative study of different supervised learning methods has revealed effective supervised learning methods for evaluating the credibility of Tweeter data.

Download Full-text

Analysis of Decision Tree Induction Algorithms

Research Society and Development ◽

10.33448/rsd-v8i11.1473 ◽

2019 ◽

Vol 8 (11) ◽

pp. e298111473

Author(s):

Hugo Kenji Rodrigues Okada ◽

Andre Ricardo Nascimento das Neves ◽

Ricardo Shitsuka

Keyword(s):

Machine Learning ◽

Decision Tree ◽

Decision Trees ◽

Quantitative Study ◽

Data Structures ◽

Execution Time ◽

Supervised Machine Learning ◽

Decision Tree Induction ◽

Classification And Regression ◽

Cart Algorithm

Decision trees are data structures or computational methods that enable nonparametric supervised machine learning and are used in classification and regression tasks. The aim of this paper is to present a comparison between the decision tree induction algorithms C4.5 and CART. A quantitative study is performed in which the two methods are compared by analyzing the following aspects: operation and complexity. The experiments presented practically equal hit percentages in the execution time for tree induction, however, the CART algorithm was approximately 46.24% slower than C4.5 and was considered to be more effective.

Download Full-text