A comprehensive survey on machine learning for networking: evolution, applications and research opportunities

Abstract

Machine Learning (ML) has been enjoying an unprecedented surge in applications that solve problems and enable automation in diverse domains. Primarily, this is due to the explosion in the availability of data, significant improvements in ML techniques, and advancement in computing capabilities. Undoubtedly, ML has been applied to various mundane and complex problems arising in network operation and management. There are various surveys on ML for specific areas in networking or for specific network technologies. This survey is original, since it jointly presents the application of diverse ML techniques in various key areas of networking across different network technologies. In this way, readers will benefit from a comprehensive discussion on the different learning paradigms and ML techniques applied to fundamental problems in networking, including traffic prediction, routing and classification, congestion control, resource and fault management, QoS and QoE management, and network security. Furthermore, this survey delineates the limitations, give insights, research challenges and future opportunities to advance ML in networking. Therefore, this is a timely contribution of the implications of ML for networking, that is pushing the barriers of autonomic network operation and management.

A Survey on Big Data for Network Traffic Monitoring and Analysis

“…We rely on a subset of the taxonomy of network management applications found in [15] to categorize papers handling NTMA with big data approaches. The previous work lists eight categories, which are defined according to the final purpose of the management application, namely: (i) traffic prediction, (ii) traffic classification, (iii) fault management, (iv) network security, (v) congestion control, (vi) traffic routing, (vii) resource management, and (viii) QoS/QoE management.…”

“…We only survey works that fit on the first four categories for two reasons. First, whereas the taxonomy in [15] is appropriate for describing network management applications, the level of dependence of such applications on NTMA varies considerably. Traffic routing and resource management seem less dependent on large-scale measurements than traffic prediction and security, for example.…”

“…Fault management can be proactive, e.g., when analytics predict faults based on measurements to avoid disruptions, or reactive, e.g., when traffic and system logs are evaluated to understand ongoing problems. In either case, a key step in fault management is the localization of the root-cause of problems [15].…”

WBQoEMS: Web browsing QoE monitoring system based on prediction algorithms

“…Academic research works done in Qian et al are based on SVM to deal with QoE prediction. Some relevant research works done in Paudel et al, Menkovski et al, and Rodr'ıguez et al to make QoE estimation are based on SVM, discriminate analysis, decision tree, neural network, Bayesian, and random neural networks (RNN), while Machado et al based their study on artificial neural network (ANN) to estimate QoE metrics in WiMAX networks or on KNN in Kang et al…”

“…At first, we distinguish the relationship between QoS and QoE like it was studied in Fiedler et al and Khan et al 23,24 Several research works discussed different approaches based on ML for predicting QoE. 25 So, Le Callet et al 26 [33][34][35] to make QoE estimation are based on SVM, discriminate analysis, [36][37][38][39] decision tree, neural network, 36,40,[43][44][45][46] Bayesian, and random neural networks (RNN), while Machado et al 41 based their study on artificial neural network (ANN) to estimate QoE metrics in WiMAX networks or on KNN in Kang et al 42 ML algorithms help to deduce knowledge from stocked data and enable automation in the area of QoS and QoE management for operators and services providers. Different learning paradigms and ML techniques are applied to solve prediction problem in the QoE context by predicting MOS or estimating the user expectation before serving them (video or web pages).…”