Abstract
Approximate query processing (AQP) is an effective way to provide approximate results for SQL queries, which relaxing accuracy in exchange for higher processing speed. In sampling-based AQP techniques, random sampling works well for uniformly distributed data but performs poorly on skewed data. To address this problem, we propose a distribution-aware approximation framework called AQapprox (aggregation queries approximation), to approximate queries more efficiently and accurately by extending Sapprox. We construct a probabilistic Map, which records the occurrences of sub-datasets on categorical columns and related statistics on numerical columns at each segment of the whole dataset. When a query arrives, AQapprox will combine Map and adaptively use different sampling methods based on the distribution. Experimental results on both real and synthetic datasets show that AQapprox can achieve a speedup by up to 5.9\(\times \) for skewed data, 64\(\times \) for uniform data over Sapprox, and has higher accuracy on multi-column queries.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Amazon review data. http://jmcauley.ucsd.edu/data/amazon/
Tpc-h benchmark. http://www.tpc.org/tpch/
Agarwal, S., Mozafari, B., Panda, A., Milner, H., Madden, S., Stoica, I.: BlinkDB: queries with bounded errors and bounded response times on very large data. In: Proceedings of the 8th ACM European Conference on Computer Systems, pp. 29–42 (2013)
Chaudhuri, S., Ding, B., Kandula, S.: Approximate query processing: no silver bullet. In: Proceedings of the 2017 ACM International Conference on Management of Data, pp. 511–519 (2017)
Ding, B., Huang, S., Chaudhuri, S., Chakrabarti, K., Wang, C.: Sample+seek: approximating aggregates with distribution precision guarantee. In: Proceedings of the 2016 International Conference on Management of Data, pp. 679–694 (2016)
Gan, Y., Meng, X., Shi, Y.: Processing online aggregation on skewed data in mapreduce. In: Proceedings of the Fifth International Workshop on Cloud Data Management, pp. 3–10 (2013)
Gemulla, R., Lehner, W., Haas, P.J.: Maintaining bounded-size sample synopses of evolving datasets. VLDB J. 17(2), 173–201 (2008)
Goiri, I., Bianchini, R., Nagarakatte, S., Nguyen, T.D.: ApproxHadoop: bringing approximations to mapreduce frameworks. In: Proceedings of the Twentieth International Conference on Architectural Support for Programming Languages and Operating Systems, pp. 383–397 (2015)
Gretton, A., Borgwardt, K.M., Rasch, M.J., Schölkopf, B., Smola, A.: A kernel two-sample test. J. Mach. Learn. Res. 13, 723–773 (2012)
Haas, P.J., König, C.: A bi-level bernoulli scheme for database sampling. In: Proceedings of the 2004 ACM SIGMOD International Conference on Management of Data, pp. 275–286 (2004)
Kandula, S., et al.: Quickr: lazily approximating complex AdHoc queries in bigdata clusters. In: Proceedings of the 2016 International Conference on Management of Data, pp. 631–646 (2016)
Li, K., Zhang, Y., Li, G., Tao, W., Yan, Y.: Bounded approximate query processing. IEEE Trans. Knowl. Data Eng. 12, 2262–2276 (2019). https://doi.org/10.1109/TKDE.2018.2877362
Lohr, S.L.: Sampling: Design and Analysis. Nelson Education (2009)
Marwick, B., Krishnamoorthy, K.: cvequality: tests for the equality of coefficients of variation from multiple groups. R software package version, vol. 1, p. 3 (2018)
Pansare, N., Borkar, V.R., Jermaine, C., Condie, T.: Online aggregation for large mapreduce jobs. Proc. VLDB Endowment 4(11), 1135–1145 (2011)
Park, Y., Mozafari, B., Sorenson, J., Wang, J.: VerdictDB: universalizing approximate query processing. In: Proceedings of the 2018 International Conference on Management of Data, pp. 1461–1476 (2018)
Wiegand, H.: Kish, l.: Survey Sampling. Wiley, New York (1965). ix + 643 s., 31 abb., 56 tab., preis 83 s. 10(1), 88–89 (2010)
Zhang, X., Wang, J., Yin, J.: Sapprox: enabling efficient and accurate approximations on sub-datasets with distribution-aware online sampling. Proc. VLDB Endowment 10(3), 109–120 (2016)
Acknowledgments
This work was supported by NSFC grants (No. 61532021 and 61972155), Shanghai Knowledge Service Platform Project (No. ZF1213).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Wu, H., Wang, X., Lu, X. (2020). AQapprox: Aggregation Queries Approximation with Distribution-Aware Online Sampling. In: Huang, Z., Beek, W., Wang, H., Zhou, R., Zhang, Y. (eds) Web Information Systems Engineering – WISE 2020. WISE 2020. Lecture Notes in Computer Science(), vol 12343. Springer, Cham. https://doi.org/10.1007/978-3-030-62008-0_28
Download citation
DOI: https://doi.org/10.1007/978-3-030-62008-0_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-62007-3
Online ISBN: 978-3-030-62008-0
eBook Packages: Computer ScienceComputer Science (R0)