@Misc{Kimovski2021, author = {Dumitru, Roman and Nikolov, Nikolay and Elvesater, Brian and Soylu, Ahmet and Prodan, Radu and Kimovski, Dragi and Marrella, Andrea and Leotta, Francesco and Benvenuti, Dario and Matskin, Mihhail and Ledakis, Giannis and Simonet-Boulogne, Anthony and Perales, Fernando and Kharlamov, Evgeny and Ulisses, Alexandre and Solberg, Arnor and Ceccarelli, Raffaele}, howpublished = {RCIS '21 Proceedings of the 15th International Conference on Research Challenges in Information Science}, month = may, title = {{DataCloud: Enabling the Big Data Pipelines on the Computing Continuum}}, year = {2021}, abstract = {With the recent developments of Internet of Things (IoT) and cloud-based technologies, massive amounts of data are generated by heterogeneous sources and stored through dedicated cloud solutions. Often organizations generate much more data than they are able to interpret, and current Cloud Computing technologies cannot fully meet the requirements of the Big Data processing applications and their data transfer overheads. Many data are stored for compliance purposes only but not used and turned into value, thus becoming Dark Data, which are not only an untapped value, but also pose a risk for organizations. To guarantee a better exploitation of Dark Data, the DataCloud project aims to realize novel methods and tools for effective and efficient management of the Big Data Pipeline lifecycle encompassing the Computing Continuum. Big Data pipelines are composite pipelines for processing data with nontrivial properties, commonly referred to as the Vs of Big Data (e.g., volume, velocity, value, etc.). Tapping their potential is a key aspect to leverage Dark Data, although it requires to go beyond the current approaches and frameworks for Big Data processing. In this respect, the concept of Computing Continuum extends the traditional centralised Cloud Computing with Edge and Fog computing in order to ensure low latency pre-processing and filtering close to the data sources. This will prevent to overwhelm the centralised cloud data centres enabling new opportunities for supporting Big Data pipelines.}, doi = {http://dx.doi.org/10.1007/978-3-030-75018-3}, url = {https://link.springer.com/content/pdf/bbm:978-3-030-75018-3/1.pdf} }