Intelligent systems for multimedia delivery in Software Defined Networks

• Published in: 2018 Fifth International Conference on Software Defined Systems (SDS) pp. 5 - 6
• Main Author: Lloret, Jaime
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.04.2018
• Subjects: Intelligent systems; Multimedia communication; Protocols; Software; Software defined networking; Traffic control
• DOI: 10.1109/SDS.2018.8370414

The rigidity of static configurations in the network devices, given by a list of commands or static scripts, is limiting current networks. They do not provide automatic resource provisioning and affects directly to the decrease of the efficiency. Furthermore, data centers have different traffic patterns because of the implementation of network virtualization and cloud computing technologies. Now the applications are executed in many virtual machines that must communicate, thus increasing the communication between servers. Software Defined Networks (SDNs) technology has appeared to allow higher programmable, automatic and flexible networks. They are able to divide the control plane from the data plane. In SDNs, the code is programmed centrally instead of programming node by node. The implementation can be done independently of the trademark or the model as long as it supports the communication protocol. SDN allows including new functions in the network devices. Moreover, it can easily include certain intelligent functions, in order to provide intelligence to the network. These features allow the system to self-adapt with the goal of improving it performance. The speech is focused on detailing and discussing some published Intelligent Systems for Multimedia delivery in SDN. Moreover, we will revise the most well-known artificial intelligence techniques that can be used in network data and communication networks. We will also revise the main network parameters and how they affect to the multimedia delivery. First we will detail the network architecture and the communication protocol design and development. We will also show how the information taken from the data frames, the users and servers behavior, and the traffic patterns (traffic changes, quality of service parameters, state of the frames, etc.) can be used to improve the multimedia delivery performance. It will self-adapt according to the state of the network. Network parameters and patterns are used by an intelligent network algorithm to estimate the behavior using the empirical data. Intelligent Systems for Multimedia delivery can be implemented in a wide range of multimedia applications.