A Framework for Distributed Data Processing

摘要

Nowadays, the data generated in the telecommunications networks tend to grow exponentially leading to a Big Data challenges, which makes it necessary to discover different ways to safely process this data. The reported strategies aim to provide reliable and flexible services for asynchronous data exchange. The parallel and distributed processing of large volumes of data plays a fundamental role in scenarios that require a response as soon as possible, such as detecting fraud in telecommunications services or carrying out security controls. In this paper, we present a strategy that allows to distribute data and manage several instances of the same application, which are executed in a distributed way. An aspect to be highlighted is that heterogeneity is not required in the computational units, that is, both conventional PCs and blade clusters can participate. Another important advantages of this tool are its flexibility and its adaptability. The data are distributed depending on the workload of the different application instances. Finally, a case study is presented for the distributed processing of the Windows Operating System logs.