Page 205 - Big data - Concept and application for telecommunications

Big data - Concept and application for telecommunications 5

Appendix I

The concept of close-loop bDDN-ADN-NI
(This appendix does not form an integral part of this Recommendation.)

As the Internet becomes ubiquitous in its role as a social infrastructure, various Internet applications have
emerged, and the complexity of traffic carried over the telecommunication networks continues to increase.
One of the reason for a low quality of experience and low network efficiency lies in diverse and uncertain
Internet applications being transported by a unique and rigid IP network. The diversity of service models
requires that the network models dynamically match the service models on demand. Firstly, it requires the
network and application to be aware of the status of each other. For the awareness problem, deep packet
inspection is one of the key technologies which can enable the network to be aware of the application status.
While the big data capability is one of the key technologies which can enable the application to be aware of
the network status. This is the concept of big-data-driven networking. Secondly, it is required that the
network can be programmed by the application flexibly. Dynamic programmability is one of the key
technologies that enables the application to program the network flexibly; this is the concept of application-
driven networking (ADN).

Figure I.1 – The concept of close-loop bDDN-ADN-NI

The concept of close-loop big-data-driven networking (bDDN) is illustrated as Figure I.1. We can obtain large
amounts of traffic data based on deep packet inspection and operation data from the telecommunication
network management or operation entity. Based on big data capabilities we can use the knowledge
discovered by big data analysis to service the applications (e.g., network management, resource) to program
the network to improve network and traffic efficiency.

Network and infrastructure 197