An Artificial Intelligence System for QoS and QoE Guarantee in IoT using Software Defined Networks

ABSTRACT

Multimedia traffic has drastically grown in the last few years. In addition, some of the last paradigms proposed, like the Internet of Things (IoT), adds new types of traffic and applications. Software Defined Networks (SDNs) improve the capability of network management. Combined with SDN, artificial intelligence (AI) can provide solutions to network problems based on classification and estimation techniques. In this paper, we propose an artificial intelligence system for detecting and correcting errors in multimedia transmission in a surveillance IoT environment connected through a SDN. The architecture, algorithm and messages of the SDN are detailed. The AI system design is described and the test-bed and the dataset are explained. The AI module consists of two different parts. The first one is a classifying part, which detects the type of traffic that is sent through the network. The second part is an estimator that informs the SDN controller on which kind of action should be executed to guarantee the Quality of Service (QoS) and Quality of Experience (QoE). Results show that with the actions performed by the network, problems like jitter and losses can be reduced.

 EXISTING SYSTEM :

Existing work as SDN-based TCP throughput management algorithm to provide fairness to competing users over a wireless network. It provides fairness a clients in order to avoid oscillation of the video quality and stable buffer length. Real measurements show an improvement of 39% of fairness a users for two competing clients, 43% for three competing clients and 46% for four.

PROPOSED SYSTEM :

In this paper, we propose an algorithm model based on the level of TCP throughput management throughout using Software Defined Network (SDN) for wireless network devices. It provides a better allocation of the available bandwidth to heterogeneous adaptive video streaming applications. This is done in order to provide stability and network resource utilization for users that watch adaptive video streaming content in shared wireless networks.

COCLUSION :

We have proposed an artificial intelligence system to detect problems and correct errors in multimedia transmission in surveillance IoT environments connected through a SDN. The system performs some actions to guarantee the Quality of Service (QoS) and Quality of Experience (QoE). The system has been tested in several scenarios.  With the proposed system, the QoS can be improved in different cases when the network suffers problems like congestion or high loss rates. Some QoS parameters are improved in the test performed, like bandwidth and jitter, and then, the QoE increases. Moreover, the presented AI module is able to detect critical traffic with 77% accuracy.

As future work, we can improve the system accuracy by using the end users’ interaction. So, during the transmission, can interact with the software from the destination. This interaction can be implemented through a checkbox or through some command. This would be detected by the system and marked as a FN. Another possible improvement would be to enhance the estimation model to a node-level one. This would allow us to select the best resource or action (depending on the network status) for each link in the path, not only for the entire network.

Moreover, in future works, we will analyze the correlation between the objective QoE metrics and MOS or DMOS. Thereby, this study could be applied to future research in order to improve the performance. Furthermore, some other statistical methods will be studied in order to improve the results in the estimation process for network resources selection.