scholarly journals KPI-TSAD: A Time-Series Anomaly Detector for KPI Monitoring in Cloud Applications

Symmetry ◽  
2019 ◽  
Vol 11 (11) ◽  
pp. 1350 ◽  
Author(s):  
Juan Qiu ◽  
Qingfeng Du ◽  
Chongshu Qian
Keyword(s):  
Time Series ◽  
Anomaly Detection ◽  
Short Term Memory ◽  
Performance Indicator ◽  
Classification Problem ◽  
Stationary Time Series ◽  
Imbalanced Classification ◽  
Usage Patterns ◽  
Benchmark Datasets ◽  
Anomaly Detector

Accurately detecting anomalies and timely interventions are critical for cloud application maintenance. Traditional methods for performance anomaly detection based on thresholds and rules work well for simple key performance indicator (KPI) monitoring. Unfortunately, it is difficult to find the appropriate threshold levels when there are significant differences between KPI values at different times during the day or when there are significant fluctuations stemming from different usage patterns. Therefore, anomaly detection presents a challenge for all types of temporal data, particularly when non-stationary time series have special adaptability requirements or when the nature of potential anomalies is vaguely defined or unknown. To address this limitation, we propose a novel anomaly detector (called KPI-TSAD) for time-series KPIs based on supervised deep-learning models with convolution and long short-term memory (LSTM) neural networks, and a variational auto-encoder (VAE) oversampling model was used to address the imbalanced classification problem. Compared with other related research on Yahoo’s anomaly detection benchmark datasets, KPI-TSAD exhibited better performance, with both its accuracy and F-score exceeding 0.90 on the A1benchmark and A2Benchmark datasets. Finally, KPI-TSAD continued to perform well on several KPI monitoring datasets from real production environments, with the average F-score exceeding 0.72.

scholarly journals An Enterprise Time Series Forecasting System for Cloud Applications Using Transfer Learning

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1590
Author(s):  
Arnak Poghosyan ◽  
Ashot Harutyunyan ◽  
Naira Grigoryan ◽  
Clement Pang ◽  
George Oganesyan ◽  
...  
Keyword(s):  
Time Series ◽  
Anomaly Detection ◽  
Transfer Learning ◽  
Performance Monitoring ◽  
Nonlinear Problems ◽  
Time Series Forecasting ◽  
Stationary Time Series ◽  
Learning Gain ◽  
Application Performance ◽  
Cloud Applications

The main purpose of an application performance monitoring/management (APM) software is to ensure the highest availability, efficiency and security of applications. An APM software accomplishes the main goals through automation, measurements, analysis and diagnostics. Gartner specifies the three crucial capabilities of APM softwares. The first is an end-user experience monitoring for revealing the interactions of users with application and infrastructure components. The second is application discovery, diagnostics and tracing. The third key component is machine learning (ML) and artificial intelligence (AI) powered data analytics for predictions, anomaly detection, event correlations and root cause analysis. Time series metrics, logs and traces are the three pillars of observability and the valuable source of information for IT operations. Accurate, scalable and robust time series forecasting and anomaly detection are the requested capabilities of the analytics. Approaches based on neural networks (NN) and deep learning gain an increasing popularity due to their flexibility and ability to tackle complex nonlinear problems. However, some of the disadvantages of NN-based models for distributed cloud applications mitigate expectations and require specific approaches. We demonstrate how NN-models, pretrained on a global time series database, can be applied to customer specific data using transfer learning. In general, NN-models adequately operate only on stationary time series. Application to nonstationary time series requires multilayer data processing including hypothesis testing for data categorization, category specific transformations into stationary data, forecasting and backward transformations. We present the mathematical background of this approach and discuss experimental results based on implementation for Wavefront by VMware (an APM software) while monitoring real customer cloud environments.

scholarly journals Comparing End-to-End Machine Learning Methods for Spectra Classification

2021 ◽  
Vol 11 (23) ◽  
pp. 11520
Author(s):  
Yue Sun ◽  
Sandor Brockhauser ◽  
Péter Hegedűs
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Short Term Memory ◽  
Classification Problem ◽  
High Energy ◽  
High Energy Density ◽  
Time Series Classification ◽  
Classification Models ◽  
Attention Model ◽  
End To End

In scientific research, spectroscopy and diffraction experimental techniques are widely used and produce huge amounts of spectral data. Learning patterns from spectra is critical during these experiments. This provides immediate feedback on the actual status of the experiment (e.g., time-resolved status of the sample), which helps guide the experiment. The two major spectral changes what we aim to capture are either the change in intensity distribution (e.g., drop or appearance) of peaks at certain locations, or the shift of those on the spectrum. This study aims to develop deep learning (DL) classification frameworks for one-dimensional (1D) spectral time series. In this work, we deal with the spectra classification problem from two different perspectives, one is a general two-dimensional (2D) space segmentation problem, and the other is a common 1D time series classification problem. We focused on the two proposed classification models under these two settings, the namely the end-to-end binned Fully Connected Neural Network (FCNN) with the automatically capturing weighting factors model and the convolutional SCT attention model. Under the setting of 1D time series classification, several other end-to-end structures based on FCNN, Convolutional Neural Network (CNN), ResNets, Long Short-Term Memory (LSTM), and Transformer were explored. Finally, we evaluated and compared the performance of these classification models based on the High Energy Density (HED) spectra dataset from multiple perspectives, and further performed the feature importance analysis to explore their interpretability. The results show that all the applied models can achieve 100% classification confidence, but the models applied under the 1D time series classification setting are superior. Among them, Transformer-based methods consume the least training time (0.449 s). Our proposed convolutional Spatial-Channel-Temporal (SCT) attention model uses 1.269 s, but its self-attention mechanism performed across spatial, channel, and temporal dimensions can suppress indistinguishable features better than others, and selectively focus on obvious features with high separability.

Variance error of multi-classification based anomaly detection for time series data

2020 ◽  
pp. 1-16
Author(s):  
Baoquan Wang ◽  
Tonghai Jiang ◽  
Xi Zhou ◽  
Bo Ma ◽  
Fan Zhao ◽  
...  
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Anomaly Detection ◽  
Time Series Data ◽  
Short Term Memory ◽  
Computational Cost ◽  
Reconstruction Error ◽  
Detection Methods ◽  
Series Data ◽  
Data Set

For abnormal detection of time series data, the supervised anomaly detection methods require labeled data. While the range of outlier factors used by the existing semi-supervised methods varies with data, model and time, the threshold for determining abnormality is difficult to obtain, in addition, the computational cost of the way to calculate outlier factors from other data points in the data set is also very large. These make such methods difficult to practically apply. This paper proposes a framework named LSTM-VE which uses clustering combined with visualization method to roughly label normal data, and then uses the normal data to train long short-term memory (LSTM) neural network for semi-supervised anomaly detection. The variance error (VE) of the normal data category classification probability sequence is used as outlier factor. The framework enables anomaly detection based on deep learning to be practically applied and using VE avoids the shortcomings of existing outlier factors and gains a better performance. In addition, the framework is easy to expand because the LSTM neural network can be replaced with other classification models. Experiments on the labeled and real unlabeled data sets prove that the framework is better than replicator neural networks with reconstruction error (RNN-RS) and has good scalability as well as practicability.

scholarly journals An Enterprise Time Series Forecasting System for Cloud Applications Using Transfer Learning

2021 ◽  
Author(s):  
Arnak Poghosyan ◽  
Ashot Harutyunyan ◽  
Naira Grigoryan ◽  
Clement Pang ◽  
George Oganesyan ◽  
...  
Keyword(s):  
Time Series ◽  
Anomaly Detection ◽  
Performance Monitoring ◽  
Time Series Forecasting ◽  
Stationary Time Series ◽  
Learning Gain ◽  
Application Performance ◽  
Stationary Time ◽  
Forecasting System ◽  
Cloud Applications

One of the key components of application performance monitoring (APM) software is 2 AI/ML empowered data analytics for predictions, anomaly detection, event correlations and root 3 cause analysis. Time series metrics, logs and traces are three pillars of observability and the valuable 4 source of information for IT operations. Accurate, scalable and robust time series forecasting and 5 anomaly detection are desirable capabilities of the analytics. Approaches based on neural networks 6 (NN) and deep learning gain increasing popularity due to their flexibility and ability to tackle complex 7 non-linear problems. However, some of the disadvantages of NN-based models for distributed cloud 8 applications mitigate expectations and require specific approaches. We demonstrate how NN-models 9 pretrained on a global time series database can be applied to customer specific data using transfer 10 learning. In general, NN-models adequately operate only on stationary time series. Application 11 to non-stationary time series requires multilayer data processing including hypothesis testing for 12 data categorization, category specific transformations into stationary data, forecasting and backward 13 transformations. We present the mathematical background of this approach and discuss experimental 14 results from the productized implementation in Wavefront by VMware (an APM software) while 15 monitoring real customer cloud environments.

scholarly journals Multi-Time Resolution Ensemble LSTMs for Enhanced Feature Extraction in High-Rate Time Series

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 1954
Author(s):  
Vahid Barzegar ◽  
Simon Laflamme ◽  
Chao Hu ◽  
Jacob Dodson
Keyword(s):  
Time Series ◽  
Feature Extraction ◽  
Short Term Memory ◽  
Learning Algorithm ◽  
Computing Time ◽  
Heuristic Method ◽  
High Rate ◽  
Stationary Time Series ◽  
Rate System ◽  
Modeling Tools

Systems experiencing high-rate dynamic events, termed high-rate systems, typically undergo accelerations of amplitudes higher than 100 g-force in less than 10 ms. Examples include adaptive airbag deployment systems, hypersonic vehicles, and active blast mitigation systems. Given their critical functions, accurate and fast modeling tools are necessary for ensuring the target performance. However, the unique characteristics of these systems, which consist of (1) large uncertainties in the external loads, (2) high levels of non-stationarities and heavy disturbances, and (3) unmodeled dynamics generated from changes in system configurations, in combination with the fast-changing environments, limit the applicability of physical modeling tools. In this paper, a deep learning algorithm is used to model high-rate systems and predict their response measurements. It consists of an ensemble of short-sequence long short-term memory (LSTM) cells which are concurrently trained. To empower multi-step ahead predictions, a multi-rate sampler is designed to individually select the input space of each LSTM cell based on local dynamics extracted using the embedding theorem. The proposed algorithm is validated on experimental data obtained from a high-rate system. Results showed that the use of the multi-rate sampler yields better feature extraction from non-stationary time series compared with a more heuristic method, resulting in significant improvement in step ahead prediction accuracy and horizon. The lean and efficient architecture of the algorithm results in an average computing time of 25 μμs, which is below the maximum prediction horizon, therefore demonstrating the algorithm’s promise in real-time high-rate applications.

scholarly journals A Novel Deep Learning Approach for Anomaly Detection of Time Series Data

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Zhiwei Ji ◽  
Jiaheng Gong ◽  
Jiarui Feng
Keyword(s):  
Time Series ◽  
Anomaly Detection ◽  
Time Series Data ◽  
Short Term Memory ◽  
Training Data ◽  
Series Data ◽  
Real Time System ◽  
Statistical Strategy ◽  
Anomaly Classification ◽  
Real World Datasets

Anomalies in time series, also called “discord,” are the abnormal subsequences. The occurrence of anomalies in time series may indicate that some faults or disease will occur soon. Therefore, development of novel computational approaches for anomaly detection (discord search) in time series is of great significance for state monitoring and early warning of real-time system. Previous studies show that many algorithms were successfully developed and were used for anomaly classification, e.g., health monitoring, traffic detection, and intrusion detection. However, the anomaly detection of time series was not well studied. In this paper, we proposed a long short-term memory- (LSTM-) based anomaly detection method (LSTMAD) for discord search from univariate time series data. LSTMAD learns the structural features from normal (nonanomalous) training data and then performs anomaly detection via a statistical strategy based on the prediction error for observed data. In our experimental evaluation using public ECG datasets and real-world datasets, LSTMAD detects anomalies more accurately than other existing approaches in comparison.

scholarly journals LSTM-Based VAE-GAN for Time-Series Anomaly Detection

Sensors ◽  
2020 ◽  
Vol 20 (13) ◽  
pp. 3738
Author(s):  
Zijian Niu ◽  
Ke Yu ◽  
Xiaofei Wu
Keyword(s):  
Time Series ◽  
Anomaly Detection ◽  
Short Term Memory ◽  
Generative Adversarial Networks ◽  
Short Term ◽  
Term Memory ◽  
Adversarial Networks ◽  
Time Space ◽  
Detection Stage ◽  
Long Short Term Memory

Time series anomaly detection is widely used to monitor the equipment sates through the data collected in the form of time series. At present, the deep learning method based on generative adversarial networks (GAN) has emerged for time series anomaly detection. However, this method needs to find the best mapping from real-time space to the latent space at the anomaly detection stage, which brings new errors and takes a long time. In this paper, we propose a long short-term memory-based variational autoencoder generation adversarial networks (LSTM-based VAE-GAN) method for time series anomaly detection, which effectively solves the above problems. Our method jointly trains the encoder, the generator and the discriminator to take advantage of the mapping ability of the encoder and the discrimination ability of the discriminator simultaneously. The long short-term memory (LSTM) networks are used as the encoder, the generator and the discriminator. At the anomaly detection stage, anomalies are detected based on reconstruction difference and discrimination results. Experimental results show that the proposed method can quickly and accurately detect anomalies.

scholarly journals Anomaly Detection Using a Sliding Window Technique and Data Imputation with Machine Learning for Hydrological Time Series

Water ◽  
2021 ◽  
Vol 13 (13) ◽  
pp. 1862
Author(s):  
Lattawit Kulanuwat ◽  
Chantana Chantrapornchai ◽  
Montri Maleewong ◽  
Papis Wongchaisuwat ◽  
Supaluk Wimala ◽  
...  
Keyword(s):  
Time Series ◽  
Anomaly Detection ◽  
Short Term Memory ◽  
Interpolation Method ◽  
Spline Interpolation ◽  
Sliding Window ◽  
Superior Performance ◽  
Present System ◽  
Data Imputation ◽  
Window Technique

Water level data obtained from telemetry stations typically contains large number of outliers. Anomaly detection and a data imputation are necessary steps in a data monitoring system. Anomaly data can be detected if its values lie outside of a normal pattern distribution. We developed a median-based statistical outlier detection approach using a sliding window technique. In order to fill anomalies, various interpolation techniques were considered. Our proposed framework exhibited promising results after evaluating with F1-score and root mean square error (RMSE) based on our artificially induced data points. The present system can also be easily applied to various patterns of hydrological time series with diverse choices of internal methods and fine-tuned parameters. Specifically, the Spline interpolation method yielded a superior performance on non-cyclical data while the long short-term memory (LSTM) outperformed other interpolation methods on a distinct tidal data pattern.

Sign in / Sign up

Export Citation Format

Share Document