M. Tahir Riaz

A method for classification of network traffic based on C5.0 Machine Learning Algorithm

Monitoring of the network performance in highspeed Internet infrastructure is a challenging task, as the requirements for the given quality level are service-dependent. Backbone QoS monitoring and analysis in Multi-hop Networks requires therefore knowledge about types of applications forming current network traffic. To overcome the drawbacks of existing methods for traffic classification, usage of C5.0 Machine Learning Algorithm (MLA) was proposed. On the basis of statistical traffic information received from volunteers and C5.0 algorithm we constructed a boosted classifier, which was shown to have ability to distinguish between 7 different applications in test set of 76,632-1,622,710 unknown cases with average accuracy of 99.3-99.9%. This high accuracy was achieved by using high quality training data collected by our system, a unique set of parameters used for both training and classification, an algorithm for recognizing flow direction and the C5.0 itself. Classified applications include Skype, FTP, torrent, web browser traffic, web radio, interactive gaming and SSH. We performed subsequent tries using different sets of parameters and both training and classification options. This paper shows how we collected accurate traffic data, presents arguments used in classification process, introduces the C5.0 classifier and its options, and finally evaluates and compares the obtained results.

Volunteer-based system for classification of traffic in computer networks

To overcome the drawbacks of existing methods for traffic classification (by ports, Deep Packet Inspection, statistical classification) a new system was developed, in which the data are collected from client machines. This paper presents design of the system, implementation, initial runs and obtained results. Furthermore, it proves that the system is feasible in terms of uptime and resource usage, assesses its performance and proposes future enhancements.

Strategies for the next generation green ICT infrastructure

Today, the global society is facing serious challenges in improving environmental performance, particularly with global warming, and resource management. Where the information and communication technology (ICT) industry is contributing to the global economy coupling with innovation and development of almost all the aspect of human life, but it also responsible for global CO2 emissions. In this paper, we provide a short survey of the challenges faced today of global warming by C02 emission related to global ICT infrastructure. The paper provides a number of strategies for greening ICT lead by the discussion and overall analysis.

Assessing Measurements of QoS for Global Cloud Computing Services

Many global distributed cloud computing applications and services running over the Internet, between globally dispersed clients and servers, will require certain levels of Quality of Service (QoS) in order to deliver and give a sufficiently smooth user experience. This would be essential for real-time streaming multimedia applications like online gaming and watching movies on a pay as you use basis hosted in a cloud computing environment. However, guaranteeing or even predicting QoS in global and diverse networks supporting complex hosting of application services is a very challenging issue that needs a stepwise refinement approach to be solved as the technology of cloud computing matures. In this paper, we investigate if latency in terms of simple Ping measurements can be used as an indicator for other QoS parameters such as jitter and throughput. The experiments were carried out on a global scale, between servers placed in universities in Denmark, Poland, Brazil and Malaysia. The results show some correlation between latency and throughput, and between latency and jitter, even though the results are not completely consistent. As a side result, we were able to monitor the changes in QoS parameters during a number of 24-hour periods. This is also a first step towards defining QoS parameters to be included in Service Level Agreements for cloud computing in the foreseeable future.

Using latency as a QoS indicator for global cloud computing services

Many globally distributed cloud computing (CC) applications and services running over the Internet, between globally dispersed clients and servers, will require certain levels of QoS in order to deliver and give a sufficiently smooth user experience. This would be essential for real‐time streaming multimedia applications such as online gaming and watching movies on a pay as you use basis hosted in a CC environment. However, guaranteeing or even predicting QoS in global and diverse networks that are supporting complex hosting of application services is a very challenging issue that needs a stepwise refinement approach to be solved as the technology of CC matures. In this paper, we investigate if latency in terms of simple ping measurements can be used as an indicator for other QoS parameters such as jitter and throughput. The experiments were carried out on a global scale, between servers placed in universities in Denmark, Poland, Brazil, and Malaysia. The results show the correlation between latency and throughput, and between latency and jitter, even though the results are not completely consistent. As a side result, we were able to monitor the changes in QoS parameters during a number of 24‐hour periods. This is also a first step toward defining QoS parameters to be included in service level agreements for CC at the global scale in the foreseeable future. Concurrency and Computation: Practice and Experience, 2013.© 2013 Wiley Periodicals, Inc.

Evaluation of modified degree 5 chordal rings for network topologies

In this paper an analysis of modified degree 5 chordal rings is presented. First modified graphs and reference graphs (ideal and optimal) have been defined, and it is shown that the reference graphs are useful for estimation of average path length and diameter in both original and modified graphs. Then the comparison of basic graph parameters, diameter and average path length, is given for original and modified graphs. Our finding shows that the modified graphs contain shorter distances than the original graphs, and thus can be good candidates for network topologies.

A Framework for Planning a Unified Wired and Wireless ICT Infrastructure

The increase in the use of information and communication technology (ICT) has pushed the existing access networks to their limits. Whole new access networks are currently being deployed and are expected to fully support the already started synergy of services converging on to one network. Through a brief survey of synergy and technology trends, it is concluded that a future network will use wired and wireless as complementary technologies. In this context the paper proposes a framework for planning of unified wired and wireless ICT infrastructures. The framework includes different input parameters of relevance for the planning and implementation, which also include a step-wise implementation plan. Planning methods for wired and wireless planning is presented and a simplified large-scale case study is conducted to verify and illustrate the use of the framework. The framework is concluded to be useful and the discussion lists some areas for further consideration.

On radio over fiber for heterogeneous wireless networks

The paper provides an overview of the Radio of Fiber (RoF) technology and its potential use in heterogeneous wireless networks. Wireless communications have seen a huge growth in the last decade. It has been estimated that five in every six people in the entire world will have a mobile phone in 2010. The vast growing use of Internet on the mobile devices has also been increased significantly. In order to provide a broadband access for mobile communications, a new wireless infrastructure (Fiber Optic Networks for Distributed, Extendible Heterogeneous Radio Architectures and Service Provisioning - FUTON) based on RoF technology has been introduced. The project adopts centralized processing of radio signals for number of wireless base stations can enhance the network performance in terms of bandwidth, and QoS parameters. The simplified Remote Access Units (RAU) are expected to not only increase the performance but also help to reduce the overall coast of the infrastructure.

Bringing fiber to the home to rural areas in Denmark

In order to support development of rural areas, and avoid that these areas are being depopulated, access to fast broadband networks can contribute by facilitating tele working, distance learning, ICT for industries and farming etc. In this paper we show how broadband and Fiber To The Home (FTTH) is developing in Denmark, and that FTTH is also being deployed in rural areas. A main reason for this is that consumer-owed utility companies have decided to invest heavily in the field, to a large extent with the philosophy that, since all consumers are a part of the investment, everybody should also benefit from it. As a result of these investments, FTTH availability and penetration has increased significantly over the last years. In the end of the paper, we highlight the importance of studying the actual impact of bringing FTTH to these areas.

On the use of the universal Okumura-Hata model for defining different ICT areas

The main goal of this paper is to observe QoS behavioural pattern for different ICT areas. Use these patterns to define rural and poor ICT areas from an ICT point of view. Okumura Hatta model shows the intensity pattern for defining an area. In the same way QoS parameters behavioural patterns, also have to be taken into consideration for complete definition of an ICT area. Okumura Hatta model is not sufficient to define the area, but QoS model is also required. A better example is we can define rural area with Okumura Hata model, but we cannot define poor area with it. After getting sufficient field strength also, Quality of Service (QoS) depends upon number of nodes or on resources available in any networks. In this paper we assume that sufficient field strength or required propagation pattern is there as per area for communication. Topology is generated using NS2 with different resources and have tried to plot the behavioural graphs for urban, rural and poor area scenarios.For studying area, properties generated and received packets are of prime importance. QoS features like end to end delay, throughput, and bandwidth utilization for 82 nodes have been experimented. Other parameters like number of paths, number of base stations will indirectly contribute in above QoS parameters. The generated topology model is hypothetical.