Prof. Kaustubh Beedkar has been honored with the prestigious Best Paper Award at the 41st IEEE International Conference on Data Engineering (ICDE), held in Hong Kong. ICDE is one of the premier international conferences in the field of data management.
The award-winning paper, titled “Incremental Stream Query Placement in Massively Distributed and Volatile Infrastructures“, was co-authored in collaboration with researchers from TU Berlin and BIFOLD. It addresses a critical challenge in modern data management: efficiently processing continuous data streams in highly distributed and dynamic edge-cloud environments. As more data is generated by edge devices equipped with basic processing capabilities, traditional cloud-centric systems face increasing difficulties due to frequent infrastructure changes and evolving query workloads.
To address this, the authors propose ISQP, a novel framework that maintains valid operator placements despite infrastructure volatility and query churn. Unlike traditional methods that rely on costly full re-optimizations, ISQP incrementally adjusts operator placements with fine-grained updates, significantly reducing computational overhead. Importantly, ISQP is agnostic to the underlying placement strategy, making it a versatile, general-purpose solution for a wide range of stream processing scenarios.
