Page 235 - Big data - Concept and application for telecommunications

Big data - Concept and application for telecommunications 5

Figure 6-1 – Big-data-driven network management

6.2 Big-data-driven network active maintenance

The traditional network maintenance system that focuses on fault alarm has been unable to achieve
end-to-end full coverage, whole process, real-time monitoring and analysis.

The traditional operation model is based on a customer complaint or network fault and alarm. The model
cannot pre-treat customer perception. It is difficult to fundamentally guarantee and improve customer
experience.
Active maintenance based on big data can quickly determine the performance of the network in the
imbalance between the nodes, abnormal trend of hidden problems etc., with active network analysis based
on network big data. According to such an analysis, engineers can target for exact optimization, reduce costs,
improve network quality and customer satisfaction before a failure occurs.

In order to realize active user perception, deep packet analysis by telecom operators has enabled mobile
communication network signalling data acquisition and analysis projects. However, the signalling data and
new deep packet inspection (DPI) data volume is far larger than that of traditional data. These characteristics
and data analysis can be used to promote big data thinking and technology.
Through signalling data collection and big-data analysis, user detail information can be obtained to improve
user-perceived end-to-end experience by realizing active maintenance and solving problems before the user
complains.

6.3 Big-data-driven network optimization
Big-data analytical techniques can provide the operator with deep insights into their networks to make
informed decisions. For example, these analytical techniques can help the operator to monitor and analyse
various types of data, as well as event messages, in networks.
Intelligence and important insights can be extracted from both instantaneous and historic data. Useful
information, such as the correlation between user behaviour and network traffic, can help the operator not
only to make decisions based on long-term strategies, but also to optimize resource allocation to minimize
deployment and operational costs.

Network and infrastructure 227