Geodesic
Anomaly detection in long time series on high-performance cluster with GPUs
Numerical methods and programming, Tome 24 (2023) no. 3, pp. 291-304.

Voir la notice de l'article provenant de la source Math-Net.Ru

Currently, the discovery of anomalies in long time series occurs in a wide range of subject areas: digital industry, healthcare, climate modeling, financial analytics, etc. Discord formalizes the anomaly concept being defined as a time series subsequence that has a distance of at least r to its non-overlapping nearest neighbor, where r is a prespecified threshold. This article presents a new algorithm for discord discovery on a high-performance computing cluster, where each cluster node is equipped with a GPU. The algorithm employs the data parallelism concept: the time series is divided into disjoint fragments that are processed separetely by GPUs of the cluster nodes. Using a parallel algorithm previously developed by the authors, local candidates for discords are selected at each node. Further, through the data exchanges, a set of global candidates is formed at each node as a union of all local candidates. Then each node performs a global refinement, removing false-positive discords from the global candi date set. Global refinement is parallelized based on block multiplication of the candidate matrix and the subsequence matrix of the fragment. The resulting set of discords is formed as the intersection of the sets obtained by the nodes as a result of global refinement. Computational experiments with synthetic and real time series, carried out on the Lomonosov-2 and Lobachevsky supercomputers equipped with 48–64 GPUs, show the high scalability of the developed algorithm.
Keywords: time series; anomaly detection; discord; parallel algorithm; computer cluster; GPU; CUDA; DRAG; MERLIN; PD3; PALMAD. 
@article{VMP_2023_24_3_a4,
     author = {Ya. A. Kraeva and M. L. Tsymbler},
     title = {Anomaly detection in long time series on high-performance cluster with {GPUs}},
     journal = {Numerical methods and programming},
     pages = {291--304},
     publisher = {mathdoc},
     volume = {24},
     number = {3},
     year = {2023},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/VMP_2023_24_3_a4/}
}
TY  - JOUR
AU  - Ya. A. Kraeva
AU  - M. L. Tsymbler
TI  - Anomaly detection in long time series on high-performance cluster with GPUs
JO  - Numerical methods and programming
PY  - 2023
SP  - 291
EP  - 304
VL  - 24
IS  - 3
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/VMP_2023_24_3_a4/
LA  - ru
ID  - VMP_2023_24_3_a4
ER  - 
%0 Journal Article
%A Ya. A. Kraeva
%A M. L. Tsymbler
%T Anomaly detection in long time series on high-performance cluster with GPUs
%J Numerical methods and programming
%D 2023
%P 291-304
%V 24
%N 3
%I mathdoc
%U http://geodesic.mathdoc.fr/item/VMP_2023_24_3_a4/
%G ru
%F VMP_2023_24_3_a4
Ya. A. Kraeva; M. L. Tsymbler. Anomaly detection in long time series on high-performance cluster with GPUs. Numerical methods and programming, Tome 24 (2023) no. 3, pp. 291-304. http://geodesic.mathdoc.fr/item/VMP_2023_24_3_a4/