Search

Traffic control in data networks has recently become very important due to the massive use of computer networks in different areas of society. Different techniques are usually used to carry out effective traffic control, allowing, among other things, to classify, predict and monitor network traffic. These techniques have evolved and are currently supported by artificial intelligence tools, which have made it possible to improve the results obtained with conventional techniques. This paper collects the different contributions made by the field of artificial intelligence to the improvement of these techniques and network management in general. The article describes the contributions made in aspects such as security, prediction, and classification of data traffic, as well as the optimization of routing in a computer network. [ABSTRACT FROM AUTHOR]

Traffic engineering in the Internet is responsible for the optimization and evaluation of the performance of IP networks to avoid congestion. One of the most accepted proposals is MPLS (Multiprotocol Label Switching), which provides an efficient paradigm for traffic optimization. Other proposals include the adjustment of link weights of interior gateway protocols (IGPs), the LISP protocol (Locator/ID Separation Protocol), and segment routing (SR). Currently, work is still being done on the topic and updates to existing recommendations are being proposed. [Extracted from the article]

Internet routing is based on the destination address and a shortest path algorithm, this leads to some links are congested because the same paths are selected for many communications. On the other hand, constraint based algorithms select the path based on a set of requirements that allows choosing the most optimal path for a specific set of constraints, solving the problem of the shortest path routing and providing additional benefits such as support QoS and traffic engineering. In the literature, it has been shown that the processes with traffic engineering objectives are NP-hard, and for quality of service are NP-complete, it allows making heuristic algorithms proposals because this is an open issue. Therefore, this article provides an overview of the constraint based algorithms proposed as a solution to the problem of conventional Internet routing in the last 15 years. This study has been organized into three categories according to the goals for each proposal. These categories were targeted in Internet current issues that are Traffic Engineering and Quality of Service support. A brief description of each algorithm is presented, highlighting their objectives and constraints. It is very important to highlight that to propose solutions to these issues remains a challenge and is an open issue, for this reason to have a knowledge of the taxonomy of these algorithms and objectives allows us to propose new alternatives to routing for next generation networks, with new demands on their services. [ABSTRACT FROM AUTHOR]

Traffic engineering is an important process for the evaluation and performance in the optimization of operational IP networks. This article provides a rigorous study of several recommendations made by the IETF and other approaches proposed by researchers in the last decade; they are related to specify and support the process of Internet traffic engineering. This study provides a contextualization of a traffic engineering system, the taxonomy and several problems that have been studied in order to improve performance in these networks. This information will be a valuable input to generate a new proposal in order to support Internet traffic engineering. [ABSTRACT FROM AUTHOR]