A BiLSTM cardinality estimator in complex database systems based on attention mechanism  

作　　者：Qiang Zhou Guoping Yang Haiquan Song Jin Guo Yadong Zhang Shengjie Wei Lulu Qu Louis Alberto Gutierrez Shaojie Qiao 

机构地区：[1]School of Information Science and Technology,Southwest Jiaotong University,Chengdu,China [2]School of Software Engineering,Chengdu University of Information Technology,Chengdu,China [3]School of Energy Power and Mechanical Engineering,North China Electric Power University,Baoding,China [4]Digital Media Art,Key Laboratory of Sichuan Province,Sichuan Conservatory of Music,Chengdu,China [5]Department of Computer Science,Rensselaer Polytechnic Institute,New York,New York,USA

出　　处：《CAAI Transactions on Intelligence Technology》2022年第3期537-546,共10页智能技术学报（英文）

基　　金：supported by the National Natural Science Foundation of China under grant nos.61772091,61802035,61962006,61962038,U1802271,U2001212,and 62072311;the Sichuan Science and Technology Program under grant nos.2021JDJQ0021 and 22ZDYF2680;the CCF‐Huawei Database System Innovation Research Plan under grant no.CCF‐HuaweiDBIR2020004A;Digital Media Art,Key Laboratory of Sichuan Province,Sichuan Conservatory of Music,Chengdu,China under grant no.21DMAKL02;the Chengdu Major Science and Technology Innovation Project under grant no.2021‐YF08‐00156‐GX;the Chengdu Technology Innovation and Research and Development Project under grant no.2021‐YF05‐00491‐SN;the Natural Science Foundation of Guangxi under grant no.2018GXNSFDA138005;the Guangdong Basic and Applied Basic Research Foundation under grant no.2020B1515120028;the Science and Technology Innovation Seedling Project of Sichuan Province under grant no 2021006;the College Student Innovation and Entrepreneurship Training Program of Chengdu University of Information Technology under grant nos.202110621179 and 202110621186.

摘　　要：An excellent cardinality estimation can make the query optimiser produce a good execution plan.Although there are some studies on cardinality estimation,the prediction results of existing cardinality estimators are inaccurate and the query efficiency cannot be guaranteed as well.In particular,they are difficult to accurately obtain the complex relationships between multiple tables in complex database systems.When dealing with complex queries,the existing cardinality estimators cannot achieve good results.In this study,a novel cardinality estimator is proposed.It uses the core techniques with the BiLSTM network structure and adds the attention mechanism.First,the columns involved in the query statements in the training set are sampled and compressed into bitmaps.Then,the Word2vec model is used to embed the word vectors about the query statements.Finally,the BiLSTM network and attention mechanism are employed to deal with word vectors.The proposed model takes into consideration not only the correlation between tables but also the processing of complex predicates.Extensive experiments and the evaluation of BiLSTM-Attention Cardinality Estimator(BACE)on the IMDB datasets are conducted.The results show that the deep learning model can significantly improve the quality of cardinality estimation,which is a vital role in query optimisation for complex databases.

关 键 词：ATTENTION BiLSTM cardinality estimation complex database systems query optimiser Word2vec 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]