Research

Today, we have in our hands massive amounts of data, but we are not able to process them efficiently and extract useful insights out of them. In the meanwhile, both the data sources and the workloads grow in size, variety, and heterogeneity. Internet of Things, genomics and bio-medical applications, high-energy physics, astronomy, and many more fields generate an unprecedented amount of data that often need to be combined in order to construct meaningful information. On top of that, data analysts require support for different types of queries, even if they are performed on top of the same data.

My research focuses on bridging the heterogeneity across different data sources, workloads and systems and on adapting the system resource allocation to the requirements of each application. Throughout my career so far, I have worked on standardising middleware frameworks in order to enable interoperability across applications, on bridging the network heterogeneity in order to enable device-to-device communication at extreme scale for the Internet of Things, and on elastic infrastructures to adapt resource scheduling to the workload requirements at runtime. My vision is to jointly optimise data processing algorithms execution with resource scheduling in order to build systems which are adaptive to underlying resource available in par with the workload requirements.