An Intelligent Anomaly Detection Scheme for Micro-Services Architectures With Temporal and Spatial Data Analysis
The DOI matches its Crossref record; 51 of the 51 references it cites were found in a registry or an index.
Abstract
Service-oriented 5G mobile systems are commonly believed to reshape the landscape of the Internet with ubiquitous services and infrastructures. The micro-services architecture has attracted significant interests from both academia and industry, offering the capabilities of agile development and scale capacity. The emerging mobile edge computing is able to firmly maintain efficient resource utility of 5G systems, which can be empowered by micro-services. However, such capabilities impose significant challenges on micro-services system management. Although substantial data are produced for system maintenance, the interleaved temporal-spatial information has not been fully exploited. Additionally, the flooding data impose heavy pressures on automatic analysis tools. Automated digestion of data is in an urgent need for system maintenance. In this paper, we propose a new learning-based anomaly detection framework for service-provision systems with micro-services architectures using service execution logs (temporally) and query traces (spatially). It includes two major parts: logging and tracing representation, and two-stage identification via a sequential model and temporal-spatial analysis. The experimental results show that the temporal-spatial features can accurately capture the nature of operational data. The proposed framework performs well on anomaly detection, and helps gain in-depth insights of large-scale systems.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Hybrid methods combine multiple data sources: for instance, Zuo et al. [87] fuse log and trace data for improved anomaly detection.”
From Anomaly detection and root-cause identification in microservices: a survey (2026) · cites this paper as [87]
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 1×
“The adopted sequential model is one of the RNN models, i.e., LSTM [44].”
MethodLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Glove: Global Vectors for Word Representation
Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071 · cited 1×
“networks for word distributed representations (also called word embedding and word2vec) [26], [27], [28].”
Background(2008) · Journal of Machine Learning Research · Cited by 33,051
(2003) · Journal of Machine Learning Research · doi:10.5555/944919.944937 · Cited by 32,337
Efficient Estimation of Word Representations in Vector Space
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1301.3781 · Cited by 26,568 · cited 3×
“Document distributed representation, called doc2vec, stems from word distributed representation [26], which is called word2vec.”
BackgroundMethodDistributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533 · cited 2×
“The input xt is the log templates representation learned by word embedding [27] similar to the transactional representation construction, which will be presented in Section VI-A.”
BackgroundMethodMining association rules between sets of items in large databases
Agrawal, R., Imieliński, T., & Swami, A. (1993) · Proceedings of the 1993 ACM SIGMOD international conference on Management of data · doi:10.1145/170035.170072 · Cited by 14,907 · cited 1×
“The downward closure property [43] is introduced, also known as Apriori property, by which unstructured and natural language-related log messages can be compressed to compact text form.”
BackgroundConvolutional Neural Networks for Sentence Classification
Kim, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1181 · Cited by 14,831 · cited 1×
“The authors in [30] and [31] focused on convolutional neural networks (CNN) to grasp a representation of a sentence, meanwhile [32] and [33], leveraged recurrent neural networks (RNN) to model word sequences.”
BackgroundBlei, D. M., Ng, A. Y., & Jordan, M. I. (2002) · Advances in Neural Information Processing Systems 14 · doi:10.7551/mitpress/1120.003.0082 · Cited by 12,223
Andrews, J. G., Buzzi, S., Choi, W., Hanly, S. V., Lozano, A., Soong, A. C. K., & Zhang, J. C. (2014) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2014.2328098 · Cited by 8,106 · cited 1×
“the fourth generation system (4G) for realizing the next generation of telecommunication systems [1].”
BackgroundDistributed Representations of Sentences and Documents
Le, Q. V., & Mikolov, T. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1405.4053 · Cited by 4,934 · cited 2×
“The authors in [29] were inspired by word embedding and offered a simple and effective approach for training alongside word2vec to accomplish topic modeling.”
MethodMining association rules between sets of items in large databases
Agrawal, R., Imieliński, T., & Swami, A. (1993) · ACM SIGMOD Record · doi:10.1145/170036.170072 · Cited by 4,551
A Convolutional Neural Network for Modelling Sentences
Kalchbrenner, N., Grefenstette, E., & Blunsom, P. (2014) · Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.3115/v1/p14-1062 · Cited by 3,601 · cited 1×
“The authors in [30] and [31] focused on convolutional neural networks (CNN) to grasp a representation of a sentence, meanwhile [32] and [33], leveraged recurrent neural networks (RNN) to model word sequences.”
BackgroundSupport Vector Method for Novelty Detection
Schölkopf, B., Williamson, R. C., Smola, A. J., Shawe-Taylor, J. S., & Platt, J. C. (1999) · Cited by 2,040
DeepLog: Anomaly Detection and Diagnosis from System Logs through Deep Learning
Du, M., Li, F., Zheng, G., & Srikumar, V. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3134015 · Cited by 1,835 · cited 6×
“On top of deep learning, DeepLog [16] was proposed to fit a long term short memory (LSTM) model in natural language-like sequential log data.”
BackgroundMethodInfluentialOne-class svms for document classification
Manevitz, L. M., & Yousef, M. (2002) · doi:10.5555/944790.944808 · Cited by 1,207
Network Slicing in 5G: Survey and Challenges
Foukas, X., Patounas, G., Elmokashfi, A., & Marina, M. K. (2017) · IEEE Communications Magazine · doi:10.1109/mcom.2017.1600951 · Cited by 1,162 · cited 1×
“scale architecture through ubiquitous infrastructures from the service-oriented perspective [2], [3].”
BackgroundDapper, a Large-Scale Distributed Systems Tracing Infrastructure
Sigelman, B. H., Barroso, L. A., Burrows, M., Stephenson, P., Plakal, M., Beaver, D., Jaspan, S., & Shanbhag, C. (2010) · Cited by 899
LogAnomaly: Unsupervised Detection of Sequential and Quantitative Anomalies in Unstructured Logs
Meng, W., Liu, Y., Zhu, Y., Zhang, S., Pei, D., Liu, Y., Chen, Y., Zhang, R., Tao, S., Sun, P., et al. (2019) · Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/658 · Cited by 708 · cited 1×
“In addition, the authors in [41] attempted to interpret semantical implications from logging sequences by “template2vec”, which focused on logging word embeddings”
BackgroundWhat Supercomputers Say: A Study of Five System Logs
Oliner, A., & Stearley, J. (2007) · 37th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN'07) · doi:10.1109/dsn.2007.103 · Cited by 620 · cited 3×
“BlueGene/L [17], a supercomputer developed by IBM Watson Research Center.”
BackgroundMethodInfluentialOne-class classification: taxonomy of study and review of techniques
Khan, S. S., & Madden, M. G. (2014) · The Knowledge Engineering Review · doi:10.1017/s026988891300043x · Cited by 600 · cited 3×
“From the OCC algorithm, the one-class support vector machine (OSVM) [48] [49] is of special interest.”
Experience Report: System Log Analysis for Anomaly Detection
He, S., Zhu, J., He, P., & Lyu, M. R. (2016) · 2016 IEEE 27th International Symposium on Software Reliability Engineering (ISSRE) · doi:10.1109/issre.2016.21 · Cited by 593 · cited 1×
“[39] conducted a comprehensive empirical evaluation based on several open-sourced log analysis toolkits, including supervised learning: logistic regression, decision tree, and support vector machine (SVM); unsupervised learning: log clustering, principal component analysis (PCA), and invariants mining.”
MethodTools and benchmarks for automated log parsing
Zhu, J., He, S., Liu, J., He, P., Xie, Q., Zheng, Z., & Lyu, M. R. (2019) · 2019 IEEE/ACM 41st International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP) · doi:10.1109/icse-seip.2019.00021 · Cited by 574 · cited 2×
“More relevant algorithms are introduced and evaluated in [23] and [24].”
BackgroundMethodMicroservices: The Journey So Far and Challenges Ahead
Jamshidi, P., Pahl, C., Mendonca, N. C., Lewis, J., & Tilkov, S. (2018) · IEEE Software · doi:10.1109/ms.2018.2141039 · Cited by 554 · cited 2×
“the micro-services scheme only accounts for a sub-type of SOA with Web service communication prototypes [6], it is no doubt that systems, including 5G, substantially benefit from shifting to micro-services [7], [8].”
BackgroundA data clustering algorithm for mining patterns from event logs
Vaarandi, R. (2004) · Proceedings of the 3rd IEEE Workshop on IP Operations & Management (IPOM 2003) (IEEE Cat. No.03EX764) · doi:10.1109/ipom.2003.1251233 · Cited by 453 · cited 1×
“The authors in [20] made an effort to template extraction based on word frequency, called Simple Logfile Clustering Tool (SLCT).”
MethodX-trace: a pervasive network tracing framework
Fonseca, R., Porter, G., Katz, R. H., Shenker, S. J., & Stoica, I. G. (2007) · Cited by 438
Clustering event logs using iterative partitioning
Makanju, A. A. O., Zincir-Heywood, A. N., & Milios, E. E. (2009) · Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1557019.1557154 · Cited by 338 · cited 1×
“[21], [22] proposed an iterative partitioning based algorithm, called Iterative Partitioning Log Mining (IPLoM) tool, gaining efficient template extraction.”
MethodMicroservices tenets: Agile approach to service development and deployment
Zimmermann, O. (2017) · Computer Science - Research and Development · doi:10.1007/s00450-016-0337-0 · Cited by 305 · cited 1×
“the micro-services scheme only accounts for a sub-type of SOA with Web service communication prototypes [6], it is no doubt that systems, including 5G, substantially benefit from shifting to micro-services [7], [8].”
BackgroundAdvances and challenges in log analysis
Oliner, A., Ganapathi, A., & Xu, W. (2012) · Communications of the ACM · doi:10.1145/2076450.2076466 · Cited by 290 · cited 1×
“It is because logging is able to probe record writers inside the core functional components [14].”
BackgroundAn Evaluation Study on Log Parsing and Its Use in Log Mining
He, P., Zhu, J., He, S., Li, J., & Lyu, M. R. (2016) · 2016 46th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN) · doi:10.1109/dsn.2016.66 · Cited by 230 · cited 2×
“More relevant algorithms are introduced and evaluated in [23] and [24].”
BackgroundMethodDiscovering Discrete Latent Topics with Neural Variational Inference
Miao, Y., Grefenstette, E., & Blunsom, P. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.00359 · Cited by 198 · cited 1×
“, [34] and [35] by adapting deep variation inference into latent topic modeling.”
BackgroundTopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependency
Dieng, A. B., Wang, C., Gao, J., & Paisley, J. W. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.01702 · Cited by 175 · cited 1×
“The authors in [30] and [31] focused on convolutional neural networks (CNN) to grasp a representation of a sentence, meanwhile [32] and [33], leveraged recurrent neural networks (RNN) to model word sequences.”
BackgroundData-driven dynamic resource scheduling for network slicing: A Deep reinforcement learning approach
Wang, H., Wu, Y., Min, G., Xu, J., & Tang, P. (2019) · Information Sciences · doi:10.1016/j.ins.2019.05.012 · Cited by 160 · cited 1×
“The purpose of this paper is for intelligent network management [10], [11], [12], [13] of micro-services through learning cognitive knowledge from enormous and multi-source networking data.”
BackgroundSelf-citationA Lightweight Algorithm for Message Type Extraction in System Application Logs
Makanju, A., Zincir-Heywood, A. N., & Milios, E. E. (2012) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2011.138 · Cited by 145 · cited 4×
“To form comprehensive systematic states, the work aims at mining compact, stable and interpretable message representations, called message patterns and templates [22].”
BackgroundMethodInfluentialBig Data Analytics for Large-scale Wireless Networks: Challenges and Opportunities
Dai, H.-N., Wong, R. C.-W., Wang, H., Zheng, Z., & Vasilakos, A. V. (2020) · ACM Computing Surveys · doi:10.1145/3337065 · Cited by 124
Microservices in Practice, Part 1: Reality Check and Service Design
Pautasso, C., Zimmermann, O., Amundsen, M., Lewis, J., & Josuttis, N. (2017) · IEEE Software · doi:10.1109/ms.2017.24 · Cited by 121 · cited 1×
“has gained large popularity, which makes use of lightweight communication style to decouple closely related and overlapped services [5].”
BackgroundOpenStack Cloud Computing Cookbook
Jackson, K. L., Bunch, C., & Sigler, E. (2012) · Cited by 103
Microservices and Their Design Trade-Offs: A Self-Adaptive Roadmap
Hassan, S., & Bahsoon, R. (2016) · 2016 IEEE International Conference on Services Computing (SCC) · doi:10.1109/scc.2016.113 · Cited by 98 · cited 1×
“Therefore, it requires well devised mechanisms integrated into the system to well track the execution status, and well maintain functionality and stability [9].”
BackgroundCloudSeer: Workflow Monitoring of Cloud Infrastructures via Interleaved Logs
Yu, X., Joshi, P., Xu, J., Jin, G., Zhang, H., & Jiang, G. (2016) · Proceedings of the Twenty-First International Conference on Architectural Support for Programming Languages and Operating Systems · doi:10.1145/2872362.2872407 · Cited by 93 · cited 1×
“[40] aimed at building a tool called CloudSeer for cloud computing platform monitoring.”
MethodSOA Modeling Patterns for Service-Oriented Discovery and Analysis
Bell, M. M. (2009) · Cited by 89
Improved Variational Autoencoders for Text Modeling using Dilated Convolutions
Yang, Z., Hu, Z., Salakhutdinov, R., & Berg-Kirkpatrick, T. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.08139 · Cited by 85 · cited 1×
“, [34] and [35] by adapting deep variation inference into latent topic modeling.”
BackgroundLearning-based network path planning for traffic engineering
Zuo, Y., Wu, Y., Min, G., & Cui, L. (2019) · Future Generation Computer Systems · doi:10.1016/j.future.2018.09.043 · Cited by 73 · cited 1×
“The purpose of this paper is for intelligent network management [10], [11], [12], [13] of micro-services through learning cognitive knowledge from enormous and multi-source networking data.”
BackgroundSelf-citationBig Data Analytics for Large Scale Wireless Networks: Challenges and Opportunities
Dai, H., Wong, R. C.-W., Wang, H. H., Zheng, Z., & Vasilakos, A. V. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.08069 · Cited by 59
One Class Classification for Anomaly Detection: Support Vector Data Description Revisited
Pauwels, E., & Ambekar, O. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-23184-1_3 · Cited by 35 · cited 1×
“To this end, one-class classification (OCC) [46] is investigated, which is prevalent in anomaly detection sphere [46], [47].”
Lu, H., Xie, L., Kang, N., Wang, C., & Xie, J. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.10670 · Cited by 35 · cited 1×
“The authors in [30] and [31] focused on convolutional neural networks (CNN) to grasp a representation of a sentence, meanwhile [32] and [33], leveraged recurrent neural networks (RNN) to model word sequences.”
BackgroundExploring microservices for enhancing internet QoS
Bhamare, D., Samaka, M., Erbad, A., Jain, R. K., & Gupta, L. (2018) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.3445 · Cited by 32 · cited 1×
“the micro-services scheme only accounts for a sub-type of SOA with Web service communication prototypes [6], it is no doubt that systems, including 5G, substantially benefit from shifting to micro-services [7], [8].”
BackgroundAnalyzing system logs: a new view of what's important
Sivan Sabato, A., Yom‐Tov, E., Tsherniak, A., & Rosset, S. (2007) · Cited by 27
Service‐oriented 5G network architecture: an end‐to‐end software defining approach
Yang, M. F., Li, Y., Li, B., Jin, D., & Chen, S. (2015) · International Journal of Communication Systems · doi:10.1002/dac.2941 · Cited by 19 · cited 1×
“scale architecture through ubiquitous infrastructures from the service-oriented perspective [2], [3].”
BackgroundCloudSeer: Workflow Monitoring of Cloud Infrastructures via Interleaved Logs
Yu, X., Joshi, P., Xu, J., Jin, G., Zhang, H., & Jiang, G. (2016) · ACM SIGPLAN Notices · doi:10.1145/2954679.2872407 · Cited by 18
A Survey of Big Data and Computational Intelligence in Networking
Zhu, Y., Wu, Y., Min, G., Zomaya, A. Y., & Hu, F. (2017) · CRC Press eBooks · doi:10.1201/9781315155678-2 · Cited by 2 · cited 1×
“The purpose of this paper is for intelligent network management [10], [11], [12], [13] of micro-services through learning cognitive knowledge from enormous and multi-source networking data.”
BackgroundSelf-citation
Research works printed but not linked: 3
- 2019, OpenStack OSprofiler
- 2019, Zipkin A Distributed Tracing System
- 2019, Jaeger Open Source End-to-End Distributed Tracing
Cited by
A Data-Driven Auto-CNN-LSTM Prediction Model for Lithium-Ion Battery Remaining Useful Life
Ren, L., Dong, J., Wang, X., Meng, Z., Zhao, L., & Deen, M. J. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.3008223 · Cited by 690
“Itovercomestheproblem that an RNN cannot handle long-distance dependences [24].”
BackgroundVariational LSTM Enhanced Anomaly Detection for Industrial Big Data
Zhou, X., Hu, Y., Liang, W., Ma, J., & Jin, Q. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.3022432 · Cited by 402
“Zuo et al. [19] built a learning-based anomaly detection framework, which combined a logging-tracing model and a temporal-spatial model to detect the network traffic intrusion.”
BackgroundLi, Y., Song, Y., Jia, L., Gao, S., Li, Q., & Qiu, M. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.3008010 · Cited by 399
“Many studies have been carried out for processing massive data from the manufacturing facilities in the workshop [1], [2], which is of great significance for promoting the development of data-driven prognostic and health management (PHM) systems.”
BackgroundGraph Neural Networks for Anomaly Detection in Industrial Internet of Things
Wu, Y., Dai, H.-N., & Tang, H. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3094295 · Cited by 338
“On the other hand, one of the benefits of digital transformation of many industries is to use the collected data to detect abnormal situations in a timely manner or even in advance of the actual happening of anomalies [21], [22].”
BackgroundSelf-citationA Survey on Automated Log Analysis for Reliability Engineering
He, S., He, P., Chen, Z., Yang, T., Su, Y., & Lyu, M. R. (2022) · ACM Computing Surveys · doi:10.1145/3460345 · Cited by 334
“eir work by proposing a semantic-aware representation framework for online log analysis. The issues of log-specific word embedding and out-of-vocabulary (OOV) are both addressed. Recently, Zuo et al. [167] combined the transaction-level topic modeling for learning the embedding of logs, where a transaction is a group…”
Background
Metadata
- Authors
- Zuo, Y., Wu, Y., Min, G., Huang, C., & Pei, K.
- Affiliations
- University of Exeter (GB)
- Huawei Technologies (China) (CN)
- Venue
- IEEE Transactions on Cognitive Communications and Networking
- Published
- 2020-06
- Volume
- 6
- Issue
- 2
- Pages
- 548-561
- ISSN
- 2332-7731 (ISSN-L)
- 2372-2045
- OpenAlex
- W2998908795
- Cited by
- 94
- References
- 51
- Citations by year
- 2026: 5 · 2025: 5 · 2024: 8 · 2023: 20 · 2022: 30 · 2021: 16 · 2020: 10
- FWCI
- 8.93
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Cognitive Communications and Networking (publishedVersion)
- Open Research Exeter (University of Exeter) (acceptedVersion)
- Figshare (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Software System Performance and Reliability
- Physical Sciences › Computer Science › Artificial Intelligence › Anomaly Detection Techniques and Applications
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
- Keywords
- anomaly detection, mobile edge computing, service-oriented systems, spatio-temporal analysis, sequential model, system maintenance
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.