YADING: Fast Clustering of Large-Scale Time Series Data

Fast and scalable analysis techniques are becoming increasingly important in the era of big data, because they are the enabling techniques to create real-time and interactive experiences in data analysis. Time series are widely available in diverse application areas. Due to the large number of time series instances (e.g., millions) and the high dimensionality of each time series instance (e.g., thousands), it is challenging to conduct clustering on large-scale time series, and it is even more challenging to do so in real-time to support interactive exploration. In this paper, we propose a novel end-to-end time series clustering algorithm, YADING, which automatically clusters large-scale time series with fast performance and quality results. Specifically, YADING consists of three steps: sampling the input dataset, conducting clustering on the sampled dataset, and assigning the rest of the input data to the clusters generated on the sampled dataset. In particular, we provide theoretical proof on the lower and upper bounds of the sample size, which not only guarantees YADING's high performance, but also ensures the distribution consistency between the input dataset and the sampled dataset. We also select L1 norm as similarity measure and the multi-density approach as the clustering method. With theoretical bound, this selection ensures YADING's robustness to time series variations due to phase perturbation and random noise. Evaluation results have demonstrated that on typical-scale (100,000 time series each with 1,000 dimensions) datasets, YADING is about 40 times faster than the state-of-the-art, sampling-based clustering algorithm DENCLUE 2.0, and about 1,000 times faster than DBSCAN and CLARANS. YADING has also been used by product teams at Microsoft to analyze service performance. Two of such use cases are shared in this paper.

[1]  David A. Patterson,et al.  A Simple Way to Estimate the Cost of Downtime , 2002, LISA.

[2]  Chonghui Guo,et al.  An Improved Piecewise Aggregate Approximation Based on Statistical Features for Time Series Mining , 2010, KSEM.

[3]  Eamonn J. Keogh,et al.  iSAX: disk-aware mining and indexing of massive time series datasets , 2009, Data Mining and Knowledge Discovery.

[4]  Renée J. Miller,et al.  Similarity search over time-series data using wavelets , 2002, Proceedings 18th International Conference on Data Engineering.

[5]  Alexander Hinneburg,et al.  DENCLUE 2.0: Fast Clustering Based on Kernel Density Estimation , 2007, IDA.

[6]  Chenghu Zhou,et al.  DECODE: a new method for discovering clusters of different densities in spatial data , 2009, Data Mining and Knowledge Discovery.

[7]  Hans-Peter Kriegel,et al.  OPTICS: ordering points to identify the clustering structure , 1999, SIGMOD '99.

[8]  Eamonn J. Keogh,et al.  Dimensionality Reduction for Fast Similarity Search in Large Time Series Databases , 2001, Knowledge and Information Systems.

[9]  Man Hon Wong,et al.  Fast time-series searching with scaling and shifting , 1999, PODS '99.

[10]  Peng Liu,et al.  VDBSCAN: Varied Density Based Spatial Clustering of Applications with Noise , 2007, 2007 International Conference on Service Systems and Service Management.

[11]  Georges Hébrail,et al.  Interactive Interpretation of Kohonen Maps Applied to Curves , 1998, KDD.

[12]  D. Piccolo.  A DISTANCE MEASURE FOR CLASSIFYING ARIMA MODELS , 1990 .

[13]  Martin Ester,et al.  Density‐based clustering , 2019, WIREs Data Mining Knowl. Discov..

[14]  Petra Perner,et al.  Data Mining - Concepts and Techniques , 2002, Künstliche Intell..

[15]  Sudipto Guha,et al.  CURE: an efficient clustering algorithm for large databases , 1998, SIGMOD '98.

[16]  Jing Cao,et al.  Combining Sampling Technique with DBSCAN Algorithm for Clustering Large Spatial Databases , 2000, PAKDD.

[17]  Alan Stuart,et al.  Basic ideas of scientific sampling , 1963 .

[18]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.

[19]  Eamonn J. Keogh,et al.  On the Need for Time Series Data Mining Benchmarks: A Survey and Empirical Demonstration , 2002, Data Mining and Knowledge Discovery.

[20]  P. Boesiger,et al.  A new correlation‐based fuzzy logic clustering algorithm for FMRI , 1998, Magnetic resonance in medicine.

[21]  Stefan Berchtold,et al.  Efficient Biased Sampling for Approximate Clustering and Outlier Detection in Large Data Sets , 2003, IEEE Trans. Knowl. Data Eng..

[22]  Jiawei Han,et al.  Efficient and Effective Clustering Methods for Spatial Data Mining , 1994, VLDB.

[23]  J. A. C. C. Watson-Gandy,et al.  Basic Ideas of Scientific Sampling , 1977 .

[24]  Vipin Kumar,et al.  The Challenges of Clustering High Dimensional Data , 2004 .

[25]  T. Warren Liao,et al.  Clustering of time series data - a survey , 2005, Pattern Recognit..

[26]  Daniel Barbará,et al.  Requirements for clustering data streams , 2002, SKDD.

[27]  Jiong Yang,et al.  STING: A Statistical Information Grid Approach to Spatial Data Mining , 1997, VLDB.

[28]  Christos Faloutsos,et al.  Efficient retrieval of similar time sequences under time warping , 1998, Proceedings 14th International Conference on Data Engineering.

[29]  Hans-Peter Kriegel,et al.  Density‐based clustering , 2011, WIREs Data Mining Knowl. Discov..

[30]  Hans-Peter Kriegel,et al.  The X-tree : An Index Structure for High-Dimensional Data , 2001, VLDB.

[31]  Christos Faloutsos,et al.  Fast Time Sequence Indexing for Arbitrary Lp Norms , 2000, VLDB.

[32]  Dat Tran,et al.  Fuzzy C-Means Clustering-Based Speaker Verification , 2002, AFSS.

[33]  Nicole Immorlica,et al.  Locality-sensitive hashing scheme based on p-stable distributions , 2004, SCG '04.

[34]  Hans-Peter Kriegel,et al.  The R*-tree: an efficient and robust access method for points and rectangles , 1990, SIGMOD '90.