Currently, the network traffic control systems are mainly composed of the Internet core and wired/wireless heterogeneous backbone networks. Recently, these packet-switched systems are experiencing an explosive network traffic growth due to the rapid development of communication technologies. The existing network policies are not sophisticated enough to cope with the continually varying network conditions arising from the tremendous traffic growth. Deep learning, with the recent breakthrough in the machine learning/intelligence area, appears to be a viable approach for the network operators to configure and manage their networks in a more intelligent and autonomous fashion. While deep learning has received a significant research attention in a number of other domains such as computer vision, speech recognition, robotics, and so forth, its applications in network traffic control systems are relatively recent and garnered rather little attention. In this paper, we address this point and indicate the necessity of surveying the scattered works on deep learning applications for various network traffic control aspects. In this vein, we provide an overview of the state-of-the-art deep learning architectures and algorithms relevant to the network traffic control systems. Also, we discuss the deep learning enablers for network systems. In addition, we discuss, in detail, a new use case, i.e., deep learning based intelligent routing. We demonstrate the effectiveness of the deep learning-based routing approach in contrast with the conventional routing strategy. Furthermore, we discuss a number of open research issues, which researchers may find useful in the future.

State-of-the-Art Deep Learning: Evolving Machine Intelligence Toward Tomorrow’s Intelligent Network Traffic Control Systems

Service-centric communication network monitoring apparatus and methods are provided. Service traffic, associated with a third-party service provided by an external service provider that is controlled independently of a communication network, is identified in communication traffic that is being transferred through that communication network. The identified service traffic is monitored, for example, to compile service usage statistics, to police usage of the service, to generate billing records for usage of the service, and/or to mirror the identified service traffic. A registry in which the service is registered may interact with a monitoring system of the communication network so as to establish monitoring for the service traffic.

Service-centric communication network monitoring

Anonymization of network traces is widely viewed as a necessary condition for releasing such data for research purposes. For obvious privacy reasons, an important goal of trace anonymization is to suppress the recovery of web browsing activities. While several studies have examined the possibility of reconstructing web browsing activities from anonymized packet-level traces, we argue that these approaches fail to account for a number of challenges inherent in real-world network traffic, and more so, are unlikely to be successful on coarser Net-Flow logs. By contrast, we develop new approaches that identify target web pages within anonymized NetFlow data, and address many real-world challenges, such as browser caching and session parsing. We evaluate the effectiveness of our techniques in identifying front pages from the 50 most popular web sites on the Internet (as ranked by alexa.com), in both a closed-world experiment similar to that of earlier work and in tests with real network flow logs. Our results show that certain types of web pages with unique and complex structure remain identifiable despite the use of state-of-the-art anonymization techniques. The concerns raised herein pose a threat to web browsing privacy insofar as the attacker can approximate the web browsing conditions represented in the flow logs.

https://www.cs.jhu.edu/~fabian/papers/usenix07b.pdf

On web browsing privacy in anonymized NetFlows

Traditional traffic identification methods based on wellknown port numbers are not appropriate for the identification of new types of Internet applications. This paper proposes a new method to identify current Internet traffic, which is a preliminary but essential step toward traffic characterization. We categorized most current network-based applications into several classes according to their traffic patterns. Then, using this categorization, we developed a flow grouping method that determines the application name of traffic flows. We have incorporated our method into NG-MON, a traffic analysis system, to analyze Internet traffic between our enterprise network and the Internet, and characterized all the traffic according to their application types.

Application-Level Traffic Monitoring and an Analysis on IP Networks

http://dpnm.postech.ac.kr/papers/Comp-Communications/06/flow-based-traffic-analysis.pdf

Characteristic analysis of internet traffic from the perspective of flows

One of the main problems with today’s Internet traffic analysis is caused by the large number of network-based applications whose types and traffic patterns are more complicated than in the past. Today, peer-to-peer (P2P), streaming media, and game traffic are continuously increasing. The difficulty the traffic analysis is that this newly emerging traffic is not as simple as past well-known port based traffic. This paper focuses on analyzing P2P traffic, which is the most complicated traffic among newly emerging Internet traffic. We describe the properties of P2P traffic and explain why P2P traffic analysis is more difficult than other types of Internet traffic analysis. Next, we propose a new algorithm suitable for P2P traffic analysis. The main idea of our algorithm is that flow grouping based on their relationships will increase the accuracy of P2P traffic analysis.

/pdf/towards-peer-to-peer-traffic-analysis-using-flows-3uw7n34bpx.pdf

Towards Peer-to-Peer Traffic Analysis Using Flows

The use of multimedia service applications is growing rapidly on the Internet. These applications are generating a huge volume of network traffic, which has a great impact on network performance and planning. For various purposes, obtaining information on multimedia service traffic is important. However, traditional analysis methods based on well-known ports cannot be used to analyze such traffic. Because the majority of multimedia service applications use dynamically allocated port numbers, the traditional methods misidentify multimedia service traffic as unknown traffic. This paper presents a method for monitoring and analyzing multimedia service traffic. Our method detects transport protocol and port numbers for dynamically created sessions during a control session. We then use such information to analyze traffic generated by the most popular multimedia service applications, namely Windows Media, RealMedia, Quicktime, SIP and H.323. We also present a system architecture that uses our method to monitor and analyze multimedia service traffic.

/pdf/a-method-on-multimedia-service-traffic-monitoring-and-4wc0sn8c4y.pdf

A Method on Multimedia Service Traffic Monitoring and Analysis

This paper presents a method and architecture to analyze streaming media and multimedia conferencing traffic. Our method is based on detecting the transport protocol and port numbers that are dynamically assigned during the setup between communicating parties. We then apply such information to analyze traffic generated by the most popular streaming media and multimedia conferencing applications, namely, Windows Media, Real Networks, QuickTime, SIP and H.323. We also describe a prototype implementation of a traffic monitoring and analysis system that uses our method and architecture.

/pdf/streaming-media-and-multimedia-conferencing-traffic-analysis-4k0fv0x9he.pdf

Hun-Jeong Kang

Papers

Towards Peer-to-Peer Traffic Analysis Using Flows

A Method on Multimedia Service Traffic Monitoring and Analysis

Streaming Media and Multimedia Conferencing Traffic Analysis Using Payload Examination