Academic Journal of Computing & Information Science, 2022, 5(4); doi: 10.25236/AJCIS.2022.050408.
Yihong Zhang1, Zenan Ji2
1School of Science, North China Institute of Science & Technology, Langfang, 065201, China
2School of Data Science, Zhejiang University of Finance & Economics, Hangzhou, 310018, China
Anomaly detection and trend prediction based on KPI business indicators play a key role in intelligent operation and maintenance in various fields. The types of indicators analyzed vary greatly for different scenarios of operation and maintenance, but all have time-series characteristics. In this paper, three core indicators are selected based on time series to build anomaly detection and trend prediction models. After preprocessing the index data, a statistical-based S-ESD time series anomaly detection method is firstly implemented. Anomaly detection is performed on three core indexes, and the detected anomalies are extracted and corrected. Use the revised KPI indicator data to further build a Prophet trend prediction model based on decomposable (trend + season + holiday), select MAPE as the evaluation index, perform model training on the indicator data, predict the next three days by step size, and get the fitting Curve and trend for the next three days. After parameter tuning, the MAPE of the Prophet prediction model is less than 0.1, the running time is shorter, and the trend prediction accuracy is higher, which can be practically applied to the field of intelligent operation and maintenance.
Intelligent O&M; S-ESD Anomaly Detection; Prophet; Grid Search
Yihong Zhang, Zenan Ji. Anomaly Detection and Trend Prediction in Intelligent Operations Based on Prophet and S-ESD. Academic Journal of Computing & Information Science (2022), Vol. 5, Issue 4: 46-51. https://doi.org/10.25236/AJCIS.2022.050408.
[1] WU Rui, ZHANG Anqin, TIAN Xiuxia, et al. Anomaly Detection Algorithm for Power Data Based on Improved K-means [J]. Journal of East China Normal University:Natural Science Edition, 2020(4): 9.
[2] ZHONG Cheng, LUO Cheng. Clustering and Sequence Analysis Methods for Unsupervised Anomaly Detection [J]. Journal of Computer Research and Development, 2008(z1): 6.
[3] XU Qinzhen, YANG Luxi. An Anomaly Detection Method Based on Hierarchical Support Vector Machine for Supervised Local Decision Making [J]. Journal of Electronics and Information Technology, 2010(10): 5.
[4] CUI Weilan, YIN Xunwei, CHENG Yongqiang. A Network Traffic Anomaly Detection Method Based on Statistics [J]. Network Security Technology and Application, 2008(1): 2.
[5] Hochenbaum, Jordan, Owen S. Vallis, and Arun Kejariwal. "Automatic Anomaly Detection in the Cloud Via Statistical Learning." arXiv preprint arXiv:1704.07706 (2017).
[6] WANG Xin, WU Ji, LIU Chao, et al. Fault Time Series Prediction Based on LSTM Recurrent Neural Network [J]. Journal of Beihang University, 2018, 44(4): 13.
[7] Taylor SJ, Letham B. 2017. - Scale forecasting. PeerJ 5 Preprint: e3190v2
[8] Gorbach AN, Tseitlin NA Shopping behavior: spontaneous series analysis and regression models in market research. - Kiev: Osvita Ukrainy, 2011. -- 298 pages.
[9] YANG Zhen, NIE Yanwu, SUN Yahong, et al. Prediction and Comparative Analysis of Tuberculosis Incidence Based on Prophet et al. Time Series Seasonal Models [J]. Modern Preventive Medicine, 2021, 48(21): 7.
[10] PENG Pan, LIU Min. Short-term Load Forecasting Method Based on Prophet-LSTM Combined Model [J]. Proceedings of the CSU-EPSA, 2021, 33(11): 6.