#
An Enterprise Time Series Forecasting System for Cloud Applications Using Transfer Learning^{ †}

^{1}

^{2}

^{3}

^{*}

^{†}

## Abstract

**:**

## 1. Introduction

## 2. Related Work

## 3. Main Idea

## 4. Hypothesis Testing for Data Categorization

#### 4.1. Periodicity Analysis

#### 4.2. Trend Analysis

## 5. Time Series Forecasts with Confidence Bounds

#### 5.1. Stationary Time Series Data

#### 5.2. Trend-Stationary Time Series Data

#### 5.3. Stochastic-Trendy Time Series Data

#### 5.4. Stationary-Periodic Time Series Data

#### 5.5. Trend-Periodic Time Series Data

## 6. Anomaly Signals from Time Series Data Forecasts

## 7. Materials and Methods

## 8. Discussion

## 9. Conclusions and Future Work

## 10. Patents

## Author Contributions

## Funding

## Institutional Review Board Statement

## Informed Consent Statement

## Data Availability Statement

## Conflicts of Interest

## Abbreviations

ADF-test | Augmented Dickey–Fuller test |

AI | Artificial Intelligence |

AIOps | AI for IT operations |

APM | Application Performance Monitoring |

ARMA model | Auto Regressive Moving Average model |

ARIMA model | Auto Regressive Integrated Moving Average model |

CH-test | Canova-Hansen test |

CPU | Central Processing Unit |

DF-test | Dickey-Fuller test |

DL4J | Deep Learning For Java |

GPU | Graphical Processing Unit |

HEGY-test | Hylleberg-Engle-Granger-Yoo test |

IT | Information Technologies |

KPSS-test | Kwiatkowski-Phillips-Schmidt-Shin test |

LB | Lower Bound |

LOESS | Locally Estimated Scatterplot Smoothing |

LSTM network | Long Short Term Memory network |

ML | Machine Learning |

MLP network | Multi Layer Perceptron network |

NN | Neural Network |

OCSB-test | Osborn–Chui-Smith-Birchenhall test |

OLS | Ordinary Least Squares |

PDM-test/method | Phase Dispersion Minimization test/method |

RCA | Root Cause Analysis |

RMSRE | Root Mean Square Relative Error |

SaaS | Software as a Service |

SARIMA model | Seasonal ARIMA model |

STL decomposition | Seasonal and Trend decomposition using Loess |

UB | Upper Bound |

UI | User Interface |

## References

- Magic Quadrant for Application Performance Monitoring. Available online: https://www.gartner.com/doc/3983892 (accessed on 10 January 2021).
- Poghosyan, A.V.; Harutyunyan, A.N.; Grigoryan, N.M.; Pang, C.; Oganesyan, G.; Ghazaryan, S.; Hovhannisyan, N. W-TSF: Time series forecasting with deep learning for cloud applications. In Proceedings of the Second CODASSCA Workshop, Collaborative Technologies and Data Science in Artificial Intelligence Applications, Yerevan, Armenia, 9 January 2020; Hajian, A., Baloian, N., Inoue, T., Luther, W., Eds.; Logos Verlag: Berlin, Germany, 2020; pp. 152–158. [Google Scholar]
- Harutyunyan, A.N.; Poghosyan, A.V.; Grigoryan, N.M.; Hovhannisyan, N.A.; Kushmerick, N. On machine learning approaches for automated log management. J. Univers. Comput. Sci.
**2019**, 25, 925–945. [Google Scholar] - Harutyunyan, A.N.; Poghosyan, A.V.; Grigoryan, N.M.; Kushmerick, N.; Beybutyan, H. Identifying changed or sick resources from logs. In Proceedings of the 2018 IEEE 3rd International Workshops on Foundations and Applications of Self* Systems (FAS*W), Trento, Italy, 3–7 September 2018; pp. 86–91. [Google Scholar]
- Poghosyan, A.V.; Harutyunyan, A.N.; Grigoryan, N.M. Compression for time series databases using independent and principal component analysis. In Proceedings of the 2017 IEEE International Conference on Autonomic Computing, ICAC 2017, Columbus, OH, USA, 17–21 July 2017; Wang, X., Stewart, C., Lei, H., Eds.; IEEE Computer Society: Washington, DC, USA, 2017; pp. 279–284. [Google Scholar]
- Poghosyan, A.V.; Harutyunyan, A.N.; Grigoryan, N.M. Managing cloud infrastructures by a multi-layer data analytics. In Proceedings of the 2016 IEEE International Conference on Autonomic Computing, ICAC 2016, Wuerzburg, Germany, 17–22 July 2016; Kounev, S., Giese, H., Liu, J., Eds.; IEEE Computer Society: Washington, DC, USA, 2016; pp. 351–356. [Google Scholar]
- Marvasti, M.A.; Poghosyan, A.V.; Harutyunyan, A.N.; Grigoryan, N.M. Ranking and updating beliefs based on user feedback: Industrial use cases. In Proceedings of the 2015 IEEE International Conference on Autonomic Computing, Grenoble, France, 7–10 July 2015; IEEE Computer Society: Washington, DC, USA, 2015; pp. 227–230. [Google Scholar]
- Marvasti, M.A.; Poghosyan, A.V.; Harutyunyan, A.N.; Grigoryan, N.M. An enterprise dynamic thresholding system. In Proceedings of the 11th International Conference on Autonomic Computing, ICAC 2014, Philadelphia, PA, USA, 18–20 June 2014; Zhu, X., Casale, G., Gu, X., Eds.; USENIX Association: Berkeley, CA, USA, 2014; pp. 129–135. [Google Scholar]
- Harutyunyan, A.N.; Poghosyan, A.V.; Grigoryan, N.M.; Marvasti, M.A. Abnormality analysis of streamed log data. In Proceedings of the 2014 IEEE Network Operations and Management Symposium, NOMS 2014, Krakow, Poland, 5–9 May 2014; pp. 1–7. [Google Scholar]
- Marvasti, M.A.; Poghosyan, A.V.; Harutyunyan, A.N.; Grigoryan, N.M. Pattern detection in unstructured data: An experience for a virtualized IT infrastructure. In Proceedings of the 2013 IFIP/IEEE International Symposium on Integrated Network Management, IM 2013, Ghent, Belgium, 27–31 May 2013; Turck, F.D., Diao, Y., Hong, C.S., Medhi, D., Sadre, R., Eds.; IEEE: New York, NY, USA, 2013; pp. 1048–1053. [Google Scholar]
- Amarbayasgalan, T.; Pham, V.H.; Theera-Umpon, N.; Ryu, K.H. Unsupervised anomaly detection approach for time-series in multi-domains using deep reconstruction error. Symmetry
**2020**, 12, 1251. [Google Scholar] [CrossRef] - Carta, S.; Podda, A.S.; Recupero, D.R.; Saia, R. A local feature engineering strategy to improve network anomaly detection. Future Internet
**2020**, 12, 177. [Google Scholar] [CrossRef] - Burgueño, J.; de-la Bandera, I.; Mendoza, J.; Palacios, D.; Morillas, C.; Barco, R. Online anomaly detection system for mobile networks. Sensors
**2020**, 20, 7232. [Google Scholar] [CrossRef] [PubMed] - Zhang, M.; Guo, J.; Li, X.; Jin, R. Data-driven anomaly detection approach for time-series streaming data. Sensors
**2020**, 20, 5646. [Google Scholar] [CrossRef] [PubMed] - Bronner, L. Overview of the capacity planning process for production data processing. IBM Syst. J.
**1980**, 19, 4–27. [Google Scholar] [CrossRef] - Hyndman, R.; Athanasopoulos, G. Forecasting: Principles and Practice; OTexts: Melbourne, Australia, 2018. [Google Scholar]
- Hamilton, J.D. Time Series Analysis; Princeton University Press: Princeton, NJ, USA, 1994. [Google Scholar]
- Cryer, J.D.; Chan, K.S. Time Series Analysis: With Applications in R; Springer: Berlin, Germany, 2008. [Google Scholar]
- Olson, T. Applied Fourier Analysis; Springer: Berlin, Germany, 2017. [Google Scholar]
- Cleveland, R.B.; Cleveland, W.S.; McRae, J.E.; Terpenning, I. STL: A seasonal-trend decomposition procedure based on Loess (with discussion). J. Off. Stat.
**1990**, 6, 3–73. [Google Scholar] - Lewis, N. Deep Time Series Forecasting with Python: An Intuitive Introduction to Deep Learning for Applied Time Series Modeling; CreateSpace Independent Publishing Platform: Scotts Valley, CA, USA, 2016. [Google Scholar]
- Rhee, M.J. Nonlinear Time Series Forecasting with Neural Networks; ProQuest LLC: Ann Arbor, MI, USA, 1995; p. 143. [Google Scholar]
- Enterprise Observability for Multi-Cloud Environments. Available online: https://tanzu.vmware.com/observability (accessed on 10 January 2021).
- Simonyan, K.; Zisserman, A. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv
**2015**, arXiv:cs.CV/1409.1556. [Google Scholar] - He, K.; Zhang, X.; Ren, S.; Sun, J. Deep residual learning for image recognition. arXiv
**2015**, arXiv:cs.CV/1512.03385. [Google Scholar] - Szegedy, C.; Liu, W.; Jia, Y.; Sermanet, P.; Reed, S.; Anguelov, D.; Erhan, D.; Vanhoucke, V.; Rabinovich, A. Going deeper with convolutions. arXiv
**2014**, arXiv:cs.CV/1409.4842. [Google Scholar] - Devlin, J.; Chang, M.W.; Lee, K.; Toutanova, K. BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv
**2019**, arXiv:cs.CL/1810.04805. [Google Scholar] - Pan, S.J.; Yang, Q. A survey on transfer learning. IEEE Trans. Knowl. Data Eng.
**2010**, 22, 1345–1359. [Google Scholar] [CrossRef] - Faraway, J.; Chatfield, C. Time series forecasting with neural networks: A comparative study using the airline data. J. R. Stat. Soc. Ser. C (Appl. Stat.)
**1998**, 47, 231–250. [Google Scholar] [CrossRef] - Hansen, J.; Nelson, R. Forecasting and recombining time-series components by using neural networks. J. Oper. Res. Soc.
**2003**, 54, 307–317. [Google Scholar] [CrossRef] - Zhang, G.P.; Qi, M. Neural network forecasting for seasonal and trend time series. Eur. J. Oper. Res.
**2005**, 160, 501–514. [Google Scholar] [CrossRef] - Wang, X.; Smith, K.; Hyndman, R. Characteristic-based clustering for time series data. Data Min. Knowl. Discov.
**2006**, 13, 335–364. [Google Scholar] [CrossRef] - Zhang, G.P. Neural networks for time-series forecasting. In Handbook of Natural Computing; Springer: Berlin/Heidelberg, Germany, 2012; pp. 461–477. [Google Scholar]
- Kolarik, T.; Rudorfer, G. Time series forecasting using neural networks. SIGAPL APL Quote Quad
**1994**, 25, 86–94. [Google Scholar] [CrossRef] - Nelson, M.; Hill, T.; Remus, W.; O’Connor, M. Time series forecasting using neural networks: Should the data be deseasonalized first? J. Forecast.
**1999**, 18, 359–367. [Google Scholar] [CrossRef] - Fawaz, H.I.; Forestier, G.; Weber, J.; Idoumghar, L.; Muller, P.A. Deep learning for time series classification: A review. Data Min. Knowl. Discov.
**2019**, 33, 917–963. [Google Scholar] [CrossRef] [Green Version] - Kwiatkowski, D.; Phillips, P.C.; Schmidt, P.; Shin, Y. Testing the null hypothesis of stationarity against the alternative of a unit root: How sure are we that economic time series have a unit root? J. Econom.
**1992**, 54, 159–178. [Google Scholar] [CrossRef] - Dickey, D.A.; Fuller, W.A. Distribution of the estimators for autoregressive time series with a unit root. J. Am. Stat. Assoc.
**1979**, 74, 427–431. [Google Scholar] - Dickey, D.A.; Fuller, W.A. Likelihood ratio statistics for autoregressive time series with a unit root. Econometrica
**1981**, 49, 1057–1072. [Google Scholar] [CrossRef] - Saïd, S.E.; Dickey, D.A. Testing for unit roots in autoregressive-moving average models of unknown order. Biometrika
**1984**, 71, 599–607. [Google Scholar] [CrossRef] - Phillips, P.C.B. Time series regression with a unit root. Econometrica
**1987**, 55, 277–301. [Google Scholar] [CrossRef] - Fuller, W.A. Introduction to Statistical Time Series; Wiley: Hoboken, NJ, USA, 1995; p. 728. [Google Scholar]
- Stellingwerf, R.F. Period determination using phase dispersion minimization. Astrophys. J.
**1978**, 224, 953–960. [Google Scholar] [CrossRef] - Davies, S.R. An improved test for periodicity. Mon. Not. R. Astron. Soc.
**1990**, 244, 93–95. [Google Scholar] - Davies, S.R. Davies’ periodicity test revisited. Mon. Not. R. Astron. Soc.
**1991**, 251, 64–65. [Google Scholar] [CrossRef] [Green Version] - Canova, F.; Hansen, B.E. Are seasonal patterns constant over time? A test for seasonal stability. J. Bus. Econ. Stat.
**1995**, 13, 237–252. [Google Scholar] - Hylleberg, S.; Engle, R.F.; Granger, C.W.J.; Yoo, B.S. Seasonal integration and cointegration. J. Econom.
**1990**, 44, 215–238. [Google Scholar] [CrossRef] - Osborn, D.R.; Chui, A.; Smith, J.P.; Birchenhall, C. Seasonality and the order of integration for consumption. Oxf. Bull. Econ. Stat.
**1933**, 50, 4. [Google Scholar] [CrossRef] - Hylleberg, S. Modelling Seasonality; Oxford University Press: Hong Kong, China, 1992. [Google Scholar]
- Dickey, D.A.; Hasza, D.P.; Fuller, W.A. Testing for unit roots in seasonal time series. J. Am. Stat. Assoc.
**1984**, 79, 355–367. [Google Scholar] [CrossRef] - Dickey, D.A. Seasonal unit roots in aggregate US data. J. Econom.
**1993**, 55, 329–331. [Google Scholar] [CrossRef] - Darne, O.; Diebolt, C. Note on seasonal unit root tests. Qual. Quant.
**2002**, 36, 305–310. [Google Scholar] [CrossRef] - Thudumu, S.; Branch, P.; Jin, J.; Singh, J.J. A comprehensive survey of anomaly detection techniques for high dimensional Big Data. J. Big Data
**2020**, 7, 43–57. [Google Scholar] [CrossRef] - Blázquez-García, A.; Conde, A.; Mori, U.; Lozano, J.A. A review on outlier/anomaly detection in time series data. arXiv
**2020**, arXiv:cs.LG/2002.04236. [Google Scholar] - Pang, G.; Shen, C.; Cao, L.; van den Hengel, A. Deep learning for anomaly detection: A review. arXiv
**2020**, arXiv:cs.LG/2007.02500. [Google Scholar] - He, Q.; Zheng, Y.; Zhang, C.; Wang, H. MTAD-TF: Multivariate time series anomaly detection using the combination of temporal pattern and feature pattern. Complexity
**2020**, 2020, 1–9. [Google Scholar] [CrossRef] - Chandola, V.; Banerjee, A.; Kumar, V. Anomaly detection: A survey. ACM Comput. Surv. (CSUR)
**2009**, 41, 1–58. [Google Scholar] [CrossRef] - Hodge, V.; Austin, J. A survey of outlier detection methodologies. Artif. Intell. Rev.
**2004**, 22, 85–126. [Google Scholar] [CrossRef] [Green Version] - Geiger, A.; Liu, D.; Alnegheimish, S.; Cuesta-Infante, A.; Veeramachaneni, K. TadGAN: Time series anomaly detection using generative adversarial networks. arXiv
**2020**, arXiv:cs.LG/2009.07769. [Google Scholar] - Grill, M.; Pevný, T.; Rehak, M. Reducing false positives of network anomaly detection by local adaptive multivariate smoothing. J. Comput. Syst. Sci.
**2017**, 83, 43–57. [Google Scholar] [CrossRef] - Deep learning for Java. Available online: https://deeplearning4j.org (accessed on 10 January 2012).
- Available online: https://docs.wavefront.com/ai_genie.html (accessed on 10 January 2012).

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2021 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 (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Poghosyan, A.; Harutyunyan, A.; Grigoryan, N.; Pang, C.; Oganesyan, G.; Ghazaryan, S.; Hovhannisyan, N.
An Enterprise Time Series Forecasting System for Cloud Applications Using Transfer Learning. *Sensors* **2021**, *21*, 1590.
https://doi.org/10.3390/s21051590

**AMA Style**

Poghosyan A, Harutyunyan A, Grigoryan N, Pang C, Oganesyan G, Ghazaryan S, Hovhannisyan N.
An Enterprise Time Series Forecasting System for Cloud Applications Using Transfer Learning. *Sensors*. 2021; 21(5):1590.
https://doi.org/10.3390/s21051590

**Chicago/Turabian Style**

Poghosyan, Arnak, Ashot Harutyunyan, Naira Grigoryan, Clement Pang, George Oganesyan, Sirak Ghazaryan, and Narek Hovhannisyan.
2021. "An Enterprise Time Series Forecasting System for Cloud Applications Using Transfer Learning" *Sensors* 21, no. 5: 1590.
https://doi.org/10.3390/s21051590