Читать книгу The Smart Cyber Ecosystem for Sustainable Development - Группа авторов - Страница 58

The process of analyzing traffic in networks is normally performed through examining messages and extracting information from them. This helps in developing effective assessment strategy of how network users behave and identifying their goals from using networks, as well as knowing the data paths and communication patterns. All of this can be used to provide information for network management algorithms and to optimize the use of network resources.

Traffic engineering is related to two processes: Prediction and Classification. Traffic prediction is a process for anticipating the traffic volume based on previously observed traffic volume; while traffic classification is a process of identifying the type of traffic. The process of traffic classification is based on collecting large number of traffic flows and analyzing those using ML techniques. Classifying traffic would help in improving security, QoS, capacity planning, and service differentiation. Classes could be: HTTP, FTP, WWW, DNS, P2P, Skype, and YouTube. Classification can be based on one or more traffic parameters, such as port number, packet payload, host behavior, or flow features [26].

ML is considered as an efficient tool in [27] for applying traffic engineering concepts. The authors use naïve Bayes classification, which uses supervised learning to construct a learning model for traffic analysis and classification. They developed a new weight-based kernel bandwidth selection algorithm to improve the constructed kernel probability density and ML model. The authors of [28] developed and SDN-based intelligent streaming architecture which exploits the power of time series forecasting for identifying users’ data rate levels in wireless networks, trying to improve the QoS of delivering video traffic. The SDN architecture is comprised of Data Plane (Switching devices), QoE management plane (management, bandwidth estimator, monitor, policy enforcer, and bandwidth forecaster), and CP aims to support the delivery of video services and to provide the QoE-based resource allocation per user.

The paper of [29] compares the performance of several supervised and unsupervised ML algorithms to classify traffic as normal or abnormal. In [30], the authors propose a traffic classification algorithm based on flow analysis. The algorithm is designed for SDN platforms.

The work in [31] uses traffic classification as part of a traffic scheduling solution for a data center network managed by SDN. ML techniques are used to classify elephant traffic flows, which require high bandwidth. Then, the SDN controller uses classification results and implements optimization of traffic scheduling. The authors of [32] use two phases for detection of elephant flows using ML techniques in SDN-based networks. In the first phase, packet headers are used to distinguish between elephant flows from mice flows, low bandwidth flows. A decision tree ML algorithm is then used to detect and classify traffic flows. Also, the authors of [33] developed an OpenFlow-based SDN system for enterprise networks. Several classification algorithms were compared.

An application of ML for improving the quality and latency of real time video streaming is proposed in [34]. The video quality is achieved through rate control, employing a DL-based adaptive rate control scheme. Two RL models are used. The first one is for prediction of video quality model, while the second is video quality RL. The predictor uses previous video frames to predict quality of future frames. The RL algorithm adopts and trains the neural network based on historic network status and video quality predictions to decide rate control actions.

In their research published in [35], the authors developed a method for traffic prediction based on the SDN architecture, where the controller gathers data and uses it to classify data flows into categories. Neural network algorithm is used to predict the expected traffic, leading to a system that can act to avoid traffic imbalance before it occurs.