Data transfer is one of the most pressing problems for companies in the telecom industry today. As data requirements grow from month to month, cost for dealing the mass also goes extremely high. To a certain point, huge data processing has been sufficient for SKT. Increase in requirements due to use of more sophisticated smartphones brought serious business bottlenecks to the company with the need for near real-time analytics on the Hadoop to load petabytes of data. In this presentation, Yousun Jeong will detail how SKT dealt with this problem; how to provide network quality analytics platform for data scientists and network operators with Spark; how to process real-time network data more efficiently; and how Spark Streaming and Spark SQL, MLib are used for high-speed large enterprise data processing and analytics. SK telecom network quality analysis has proceeded to provide reliable wireless network and network optimization. For network traffic suddenly increases rapidly and accurately various attempts to resolve the problem have been conducted. Using Spark Streaming, Mllib, Spark-SQL let move the real-time processing from base station quality data based on statistics and set active analysis basis up. Yousun Jeong will try to introduce an analytics platform that combines Spark which is a major technology around real-time network analysis and variety of techniques. And she would love to share how to solve immediate problems in building a real-time analysis.
Yousun Jeong is an Senior Engineer of SKT(SK Telecom) which is a No.1 communications service provider in South Korea. She contributes to the Apache as a committer and deliver Spark to big data analytic cluster in SKT. Big data analysis of SKT mainly focuses on the various machine logs in diverse data types (ie formatted/unformatted). It essentially needs real-time processing and real-time analysis such as network quality analysis platform. She is really hoping to share her experience with the conference attendees.