TEALED: A Multi-Step Workload Forecasting Approach Using Time-Sensitive EMD and Auto LSTM Encoder-Decoder

• Published in: Database Systems for Advanced Applications Vol. 13246; pp. 706 - 713
• Main Authors: Huang, Xiuqi, Cheng, Yunlong, Gao, Xiaofeng, Chen, Guihai
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2022; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Empirical mode decomposition; Long short-term memory; Multi-step prediction; Self-driving DBMS; Workload forecasting
• ISBN: 9783031001253; 3031001257
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-031-00126-0_55

Many data-driven methods and machine learning techniques are constantly being applied to the database management system (DBMS), which are based on the judgment of future workloads to achieve a better tuning result. We propose a novel multi-step workload forecasting approach named TEALED which applies time-sensitive empirical mode decomposition and auto long short-term memory based encoder-decoder to predict resource utilization and query arrival rates for DBMSs. We first improve the empirical mode decomposition method by considering time translation and extending short series. Then we utilize the encoder-decoder network to extract features from decomposed workloads and generate workload predictions. Moreover, we combine hyper-parameter search technologies to guarantee performance under varying workloads. The experiment results show the effectiveness and robustness of TEALED, and indicate the ability of multi-step workload forecasting.