@inproceedings{
 title = {Big provenance stream processing for data intensive computations},
 type = {inproceedings},
 year = {2018},
 keywords = {Big Data,Big Provenance,Stream Processing},
 pages = {245-255},
 month = {12},
 publisher = {Institute of Electrical and Electronics Engineers Inc.},
 day = {24},
 id = {02faffe9-74a8-370f-9c62-67aef6795cd5},
 created = {2020-04-22T21:44:56.973Z},
 accessed = {2020-04-21},
 file_attached = {false},
 profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d},
 last_modified = {2020-05-11T14:43:32.831Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {false},
 hidden = {false},
 citation_key = {Suriarachchi2018},
 private_publication = {false},
 abstract = {In the business and research landscape of today, data analysis consumes public and proprietary data from numerous sources, and utilizes any one or more of popular data-parallel frameworks such as Hadoop, Spark and Flink. In the Data Lake setting these frameworks co-exist. Our earlier work has shown that data provenance in Data Lakes can aid with both traceability and management. The sheer volume of fine-grained provenance generated in a multi-framework application motivates the need for on-the-fly provenance processing. We introduce a new parallel stream processing algorithm that reduces fine-grained provenance while preserving backward and forward provenance. The algorithm is resilient to provenance events arriving out-of-order. It is evaluated using several strategies for partitioning a provenance stream. The evaluation shows that the parallel algorithm performs well in processing out-of-order provenance streams, with good scalability and accuracy.},
 bibtype = {inproceedings},
 author = {Suriarachchi, Isuru and Withana, Sachith and Plale, Beth},
 doi = {10.1109/eScience.2018.00039},
 booktitle = {Proceedings - IEEE 14th International Conference on eScience, e-Science 2018}
}

{"_id":"J7p5j7zsxsvJZ49B2","bibbaseid":"suriarachchi-withana-plale-bigprovenancestreamprocessingfordataintensivecomputations-2018","authorIDs":[],"author_short":["Suriarachchi, I.","Withana, S.","Plale, B."],"bibdata":{"title":"Big provenance stream processing for data intensive computations","type":"inproceedings","year":"2018","keywords":"Big Data,Big Provenance,Stream Processing","pages":"245-255","month":"12","publisher":"Institute of Electrical and Electronics Engineers Inc.","day":"24","id":"02faffe9-74a8-370f-9c62-67aef6795cd5","created":"2020-04-22T21:44:56.973Z","accessed":"2020-04-21","file_attached":false,"profile_id":"42d295c0-0737-38d6-8b43-508cab6ea85d","last_modified":"2020-05-11T14:43:32.831Z","read":false,"starred":false,"authored":"true","confirmed":false,"hidden":false,"citation_key":"Suriarachchi2018","private_publication":false,"abstract":"In the business and research landscape of today, data analysis consumes public and proprietary data from numerous sources, and utilizes any one or more of popular data-parallel frameworks such as Hadoop, Spark and Flink. In the Data Lake setting these frameworks co-exist. Our earlier work has shown that data provenance in Data Lakes can aid with both traceability and management. The sheer volume of fine-grained provenance generated in a multi-framework application motivates the need for on-the-fly provenance processing. We introduce a new parallel stream processing algorithm that reduces fine-grained provenance while preserving backward and forward provenance. The algorithm is resilient to provenance events arriving out-of-order. It is evaluated using several strategies for partitioning a provenance stream. The evaluation shows that the parallel algorithm performs well in processing out-of-order provenance streams, with good scalability and accuracy.","bibtype":"inproceedings","author":"Suriarachchi, Isuru and Withana, Sachith and Plale, Beth","doi":"10.1109/eScience.2018.00039","booktitle":"Proceedings - IEEE 14th International Conference on eScience, e-Science 2018","bibtex":"@inproceedings{\n title = {Big provenance stream processing for data intensive computations},\n type = {inproceedings},\n year = {2018},\n keywords = {Big Data,Big Provenance,Stream Processing},\n pages = {245-255},\n month = {12},\n publisher = {Institute of Electrical and Electronics Engineers Inc.},\n day = {24},\n id = {02faffe9-74a8-370f-9c62-67aef6795cd5},\n created = {2020-04-22T21:44:56.973Z},\n accessed = {2020-04-21},\n file_attached = {false},\n profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d},\n last_modified = {2020-05-11T14:43:32.831Z},\n read = {false},\n starred = {false},\n authored = {true},\n confirmed = {false},\n hidden = {false},\n citation_key = {Suriarachchi2018},\n private_publication = {false},\n abstract = {In the business and research landscape of today, data analysis consumes public and proprietary data from numerous sources, and utilizes any one or more of popular data-parallel frameworks such as Hadoop, Spark and Flink. In the Data Lake setting these frameworks co-exist. Our earlier work has shown that data provenance in Data Lakes can aid with both traceability and management. The sheer volume of fine-grained provenance generated in a multi-framework application motivates the need for on-the-fly provenance processing. We introduce a new parallel stream processing algorithm that reduces fine-grained provenance while preserving backward and forward provenance. The algorithm is resilient to provenance events arriving out-of-order. It is evaluated using several strategies for partitioning a provenance stream. The evaluation shows that the parallel algorithm performs well in processing out-of-order provenance streams, with good scalability and accuracy.},\n bibtype = {inproceedings},\n author = {Suriarachchi, Isuru and Withana, Sachith and Plale, Beth},\n doi = {10.1109/eScience.2018.00039},\n booktitle = {Proceedings - IEEE 14th International Conference on eScience, e-Science 2018}\n}","author_short":["Suriarachchi, I.","Withana, S.","Plale, B."],"biburl":"https://bibbase.org/service/mendeley/42d295c0-0737-38d6-8b43-508cab6ea85d","bibbaseid":"suriarachchi-withana-plale-bigprovenancestreamprocessingfordataintensivecomputations-2018","role":"author","urls":{},"keyword":["Big Data","Big Provenance","Stream Processing"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"inproceedings","creationDate":"2020-04-22T23:10:24.482Z","downloads":0,"keywords":["big data","big provenance","stream processing"],"search_terms":["big","provenance","stream","processing","data","intensive","computations","suriarachchi","withana","plale"],"title":"Big provenance stream processing for data intensive computations","year":2018,"biburl":"https://bibbase.org/service/mendeley/42d295c0-0737-38d6-8b43-508cab6ea85d","dataSources":["zgahneP4uAjKbudrQ","ya2CyA73rpZseyrZ8","2252seNhipfTmjEBQ"]}