Citation: Wang, H.; Zhang, Y.; Liu, Y.;
Liu, F.; Zhang, H.; Xing, B.; Xing, M.;
Wu, Q.; Chen, L. ASAD: Adaptive
Seasonality Anomaly Detection
Algorithm under Intricate KPI
Profiles. Appl. Sci. 2022, 12, 5855.
https://doi.org/10.3390/
app12125855
Academic Editors: Sławomir
Nowaczyk, Rita P. Ribeiro and
Grzegorz Nalepa
Received: 25 April 2022
Accepted: 7 June 2022
Published: 8 June 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
ASAD: Adaptive Seasonality Anomaly Detection Algorithm
under Intricate KPI Profiles
Hao Wang
1,†
, Yuanyuan Zhang
1,†
, Yijia Liu
1
, Fenglin Liu
1
, Hanyang Zhang
1
, Bin Xing
2
, Minghai Xing
3
,
Qiong Wu
1,
* and Liangyin Chen
1,4,
*
1
School of Computer Science, Sichuan University, Chengdu 610065, China;
wanghao2018@stu.scu.edu.cn (H.W.); yuanyuanzhang@stu.scu.edu.cn (Y.Z.);
2021223045139@stu.scu.edu.cn (Y.L.); liufenglin@163.com (F.L.); 2020141460181@stu.scu.edu.cn (H.Z.)
2
National Engineering Laboratory for Industrial Big-Data Application Technology, Beijing 100040, China;
xingbin@casic.com
3
CEC Jiutian Intelligent Technology Co., Ltd., Shuangliu Distinct, Chengdu 610299, China;
xingmh@cecjiutian.com
4
Institute for Industrial Internet Research, Sichuan University, Chengdu 610065, China
* Correspondence: wuqiong@scu.edu.cn (Q.W.); chenliangyin@scu.edu.cn (L.C.)
† These authors contributed equally to this work.
Abstract:
Anomaly detection is the foundation of intelligent operation and maintenance (O&M),
and detection objects are evaluated by key performance indicators (KPIs). For almost all computer
O&M systems, KPIs are usually the machine-level operating data. Moreover, these high-frequency
KPIs show a non-Gaussian distribution and are hard to model, i.e., they are intricate KPI profiles.
However, existing anomaly detection techniques are incapable of adapting to intricate KPI profiles.
In order to enhance the performance under intricate KPI profiles, this study presents a seasonal
adaptive KPI anomaly detection algorithm ASAD (Adaptive Seasonality Anomaly Detection). We
also propose a new eBeats clustering algorithm and calendar-based correlation method to further
reduce the detection time and error. Through experimental tests, our ASAD algorithm has the best
overall performance compared to other KPI anomaly detection methods.
Keywords: KPI anomaly detection; intricate KPI profiles; adaptive seasonality anomaly detection
1. Introduction
Computer operation and maintenance is always a vital component in guaranteeing
the high availability of the application systems. Operation and maintenance must evolve
from manual detection to intelligent detection with the explosive increase in the volume
of application data. According to Gartner’s report, more than 40% of global enterprises
have replaced their outdated O&M systems with intelligent solutions as of 2020. In these
intelligent systems, anomaly detection is critical to detect important performance indicators
(KPIs) such as CPU utilization, memory utilization and so on. To ensure a stable and reliable
O&M system, a rising number of researchers are investigating KPI anomaly detection
methods [1,2].
Traditional statistics, supervised learning and unsupervised learning algorithms are
the three types of KPI anomaly detection techniques. First, seasonal length is required as an
input parameter by traditional statistical approaches such as Argus [
3
] and TSD [
4
], but it is
frequently given manually. It may cause seasonality to be disrupted in intricate KPI profiles,
leading to erroneous anomaly detection. Secondly, supervised learning algorithms such as
Opperence [
5
] and EGADS [
6
] relied on classical statistical techniques, and they also did
not recognize seasonal length under intricate KPI profiles. Finally, among unsupervised
learning methods, Zhao, N. [
7
] developed a periodic adjustable approach called Period.
This paper considers time series data to be related to daily human activities, and it directly
assumed that the basic seasonal length of time-series data is 1 day. However, KPI time
Appl. Sci. 2022, 12, 5855. https://doi.org/10.3390/app12125855 https://www.mdpi.com/journal/applsci
