D2IA: User-defined interval analytics on distributed streams

作者：

Highlights：

• A family of operators to generate interval events from instantaneous events.

• Operators are defined as DSL to expressively generate data-driven intervals.

• Operators fill a gap in the expressiveness of large-scale stream processing engines.

• Two alternative implementations based on Apache Flink and Esper.

• A systematic perfromance evaluation using the linear road benchmark.

摘要

•A family of operators to generate interval events from instantaneous events.•Operators are defined as DSL to expressively generate data-driven intervals.•Operators fill a gap in the expressiveness of large-scale stream processing engines.•Two alternative implementations based on Apache Flink and Esper.•A systematic perfromance evaluation using the linear road benchmark.

论文关键词：Big Stream Processing,Complex Event Processing,User-defined event intervals

论文评审过程：Received 29 November 2019, Revised 29 August 2020, Accepted 5 November 2020, Available online 13 November 2020, Version of Record 23 November 2021.

论文官网地址：https://doi.org/10.1016/j.is.2020.101679