Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This lecture discusses the challenges in scalable analytics over heterogeneous Big Data and the limitations of existing platforms like Spark. It introduces SmartDataLake, a platform aiming to handle raw, heterogeneous data efficiently by leveraging existing platforms and extending them to support native handling and distributed analytics. The lecture covers topics such as data distribution, adaptive scheduling, data prefetching, and automated storage tiering. SmartDataLake's design focuses on optimizing task distribution, resource allocation, and query execution to improve performance and reduce latency. The lecture also highlights the importance of storage tiering, approximate analytics, and the potential for cost-effective scalability. Various industry-standard benchmarks will be used to validate SmartDataLake's capabilities.
This video is available exclusively on Mediaspace for a restricted audience. Please log in to MediaSpace to access it if you have the necessary permissions.
Watch on Mediaspace