complex. In a dynamic environment of wireless networks, understanding the behavior of network users and learning from previous data is expected to be a good approach for improving channel assignment mechanisms.
The paper of [21] uses ML approach to tackle the channel assignment problem and developed a computationally efficient solution for this problem. The objective is to maximize the total data rate experienced by all users assuming limited resources and large number of network users. The convex optimization problem is converted to a regression problem. Ensemble learning is utilized to combine different machine learning models and improve the prediction performance.
2.7.1.3 User Association and Load Balancing
User association and load balancing is a challenge that has been attracting researchers of wireless networks. The question is how to optimally assign users to base stations and distribute the load in a balanced way among network base stations. The aim is to achieve high QoS to all users and at the same time efficiently utilize network resources.
The authors of [22] investigated the use of deep learning to perform user-cell association to maximize the total data rate in massive multiple input multiple output (MIMO) networks. The authors show how a deep neural network; that gets the geographical positions of users as input; can be trained to approach optimal association rule with low computational complexity. Association rule is updated in real-time considering mobility pattern of network users.
A method for cell outage detection was proposed in [23] using neural networks and unsupervised learning. The main feature of the method is the training of the network which can be performed in advance even when the cell outage data is not available. Moreover, the developed method could work in time-varying wireless environments. The machine learns from measurement reports of signal power which are collected by mobile devices.
The research work in [24] proposes a distributed, user-centric ML-based association scheme. The algorithm is based on fuzzy Q-learning, where each cell tries to maximize its throughput under infrastructure capacity and QoE constraints. With this scheme, cells broadcast data values to guide users to associate with best cells. The values reflect the possibility of a cell to satisfy a throughput performance level. Each cell tries to learn the optimal values through iterative interaction with the environment. In [25], the authors used realistic mobile network data and investigated methods for failure prediction. They compared the performance of the SVM and several neural networks.
2.7.1.4 Traffic Engineering
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.
2.7.1.5 QoS/QoE Prediction
QoS parameters are normally used by network administrators to assess the network performance. The parameters include throughput, loss rate, delay, and jitter. However, QoE is a parameter used to represent the user perception and satisfaction of the services. Developing prediction methods for QoS and QoE parameters helps network operators and service providers to offer high quality services [13]. SDN has been used to facilitate the implementation of different algorithms for QoS/QoE prediction [36–39].
The authors of [36] propose a linear regression ML algorithm for QoS prediction in SDN-based networks. A decision tree approach is used to detect relations between KPIs and QoS parameters. The authors show that the method can predict congestion and thus provide recommendations on QoS improvement. The researchers in [37] utilize two ML techniques for estimating QoS parameters for video on demand applications.
QoE prediction was addressed in [38–39]. The method of [38] was designed for video streaming in an SDN-based network, where QoS parameters are employed to estimate the mean opinion score. The SDN controller is used to adjust video parameters to improve QoE. In [39], the authors use neural network and KNN algorithms for predicting QoE parameters using video quality parameters.
2.7.1.6 Security
Users only use secure networks. One major issue in networking is the attacks by intrusions. Detecting intrusion and responding to attacks is a real challenge, especially in wireless networks
