Anomaly Detection and Failure Root Cause Analysis in (Micro) Service-Based Cloud Applications: A Survey
Open accessThe DOI matches its Crossref record; 104 of the 104 references it cites were found in a registry or an index.
Abstract
The proliferation of services and service interactions within microservices and cloud-native applications, makes it harder to detect failures and to identify their possible root causes, which is, on the other hand crucial to promptly recover and fix applications. Various techniques have been proposed to promptly detect failures based on their symptoms, viz., observing anomalous behaviour in one or more application services, as well as to analyse logs or monitored performance of such services to determine the possible root causes for observed anomalies. The objective of this survey is to provide a structured overview and qualitative analysis of currently available techniques for anomaly detection and root cause analysis in modern multi-service applications. Some open challenges and research directions stemming out from the analysis are also discussed.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The cited source says what the claim attributes to it.
In the citing paper
“Only two survey publications [26,27] directly related to our work were found in the most relevant digital libraries (IEEE Xplore, ACM Digital Library, Science Direct, Wiley Online Library, Springer Link, Scopus, and Web of Science).”
From Anomaly detection and root-cause identification in microservices: a survey (2026) · cites this paper as [26]
The cited source says what the claim attributes to it.
In the citing paper
“Soldani and Brogi [26] focused on microservices architecture.”
From Anomaly detection and root-cause identification in microservices: a survey (2026) · cites this paper as [26]
The cited source says what the claim attributes to it.
In the citing paper
“System faults observed in microservice applications include, but are not limited to, network latency, anomalous resource consumption and unavailability of system components [5].”
From Toward Context-Aware Anomaly Detection for AIOps in Microservices Using Dynamic Knowledge Graphs (2026) · cites this paper as [5]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · cited 3×
“…runs of the application, in such a way that it can be processed to train a classifier with a supervised machine learning algorithm (viz., nearest neighbour [3], random forest [10], naïve Bayes [36], or support vector machines [76]), assuming that no more than one anomaly occurs at the same time.”
BackgroundMethodAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“, a variational autoencoder [39] modelling the normal behaviour of the application and a convolutional neural network [23] recognising the type of failure affecting a service when the latter is affected by a performance anomaly.”
BackgroundJolliffe, I. (2005) · Encyclopedia of Statistics in Behavioral Science · doi:10.1002/0470013192.bsa501 · Cited by 14,310
Chandola, V., Banerjee, A., & Kumar, V. (2009) · ACM Computing Surveys · doi:10.1145/1541880.1541882 · Cited by 11,687 · cited 5×
“This is checked by applying formerly trained machine learning models for offline detection of anomalies on each service, viz., support vector machines [76] for latency anomalies, random forests [10] for error count anomalies, and 3-sigma rule [16] for throughput anomalies.”
BackgroundMethodInfluentialPeng, H., Long, F., & Ding, C. (2005) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2005.159 · Cited by 10,544 · cited 1×
“Wang et al. [86] then apply mutual information [64] to determine the dependency of the anomaly degree on the KPIs monitored on application services in the same interval.”
BackgroundRobust principal component analysis?
Candès, E. J., Li, X., Ma, Y., & Wright, J. (2011) · Journal of the ACM · doi:10.1145/1970392.1970395 · Cited by 6,921 · cited 1×
“When a matrix is corrupted by gross sparse errors, RPCA can extract the columns where the errors appear [13].”
Advances in kernel methods: support vector learning
Schölkopf, B., Burges, C. J. C., & Smola, A. J. (1999) · doi:10.5555/299094 · Cited by 5,789 · cited 2×
“…runs of the application, in such a way that it can be processed to train a classifier with a supervised machine learning algorithm (viz., nearest neighbour [3], random forest [10], naïve Bayes [36], or support vector machines [76]), assuming that no more than one anomaly occurs at the same time.”
BackgroundMethodAn Introduction to Kernel and Nearest-Neighbor Nonparametric Regression
Altman, N. S. (1992) · The American Statistician · doi:10.1080/00031305.1992.10475879 · Cited by 5,708 · cited 2×
“, nearest neighbour [3], random forest [10], naïve Bayes [36], or support vector machines [75]), assuming that no more than one anomaly occurs at the same time.”
BackgroundHandbook of Parametric and Nonparametric Statistical Procedures
(2004) · Technometrics · doi:10.1198/tech.2004.s209 · Cited by 4,661
Causation, Prediction, and Search
Spirtes, P., Glymour, C., & Scheines, R. (2001) · doi:10.7551/mitpress/1754.001.0001 · Cited by 4,521
Research works printed but not linked: 17
- 10.5555/151741 · doi:10.5555/151741
- 10.5555/1965046 · doi:10.5555/1965046
- 10.5555/3086952 · doi:10.5555/3086952
- 10.5555/1869904 · doi:10.5555/1869904
- IBM. 2021. IBM operations analytics predictive insights. Retrieved November 18th, 2021 from https://www.ibm.com/support/knowledgecenter/SSJQQ3.
- Istio Authors. 2020. Istio. Retrieved November 18th, 2021 from https://istio.io.
- 10.5555/2074158.2074196 · doi:10.5555/2074158.2074196
- J. Lewis and M. Fowler. 2014. Microservices. ThoughtWorks. Retrieved from https://martinfowler.com/articles/microservices.html.
- 10.5555/541177 · doi:10.5555/541177
- 10.5555/525544 · doi:10.5555/525544
- Prometheus Authors. 2021. Prometheus: Monitoring System & Time Series Database. Retrieved November 18th, 2021 from https://prometheus.io.
- 10.5555/3045118.3045281 · doi:10.5555/3045118.3045281
- C. Richardson. 2018. Microservices Patterns (1st ed.). Manning Publications, Shelter Island.
- 10.5555/1594884 · doi:10.5555/1594884
- 10.5555/1529939 · doi:10.5555/1529939
- 10.5555/1088844 · doi:10.5555/1088844
- A. van Hoorn. 2014. Model-Driven Online Capacity Management for Component-Based Software Systems. Ph.D. Dissertation. Faculty of Engineering Kiel University Kiel Germany.
Cited by
Items 101–200 of 300
Gu, W., Zhong, R., Yu, G., Sun, X., Liu, J., Huo, Y., Chen, Z., Zhang, J., Gu, J., Yang, Y., et al. (2025) · Empirical Software Engineering · doi:10.1007/s10664-025-10769-0 · Cited by 8
“When a performance issue is detected ( i.e. , the alarm KPI is abnormal), it is crucial to identify the root cause Soldani and Brogi (2022) ( e.g. , which underlying instances cause the abnormal performance of the service).”
TORAI: Multi-source Root Cause Analysis for Blind Spots in Microservice Service Call Graph
Pham, L., Ha, H., Zhang, X., & Zhang, H. (2026) · Proceedings of the ACM on software engineering. · doi:10.1145/3808137 · Cited by 15
Grammar-Based Anomaly Detection of Microservice Systems Execution Traces
D’Angelo, A., & d’Aloisio, G. (2024) · ACM/SPEC International Conference on Performance Engineering (ICPE) · doi:10.1145/3629527.3651844 · Cited by 6
“In particular, anomaly detection of microservice systems is a widely addressed topic in the literature [26].”
BackgroundIlluminating the Gray Zone: Non-intrusive Gray Failure Localization in Server Operating Systems
Zhang, S., Zhao, Y., Xiong, X., Sun, Y., Nie, X., Zhang, J., Wang, F., Zheng, X., Zhang, Y., & Pei, D. (2024) · ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) · doi:10.1145/3663529.3663834 · Cited by 7
“These methods can be roughly divided into statistical, graph-based, and feature learning methods [38].”
URCD: Unsupervised Root Cause Detection in Microservices Architecture with HGAN
Borse, H., Satapathy, U., Mandal, M., & Mitra, B. (2024) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs60910.2024.00137 · Cited by 4
“Figure 2 represents traces for four different request with their heath state in traditional and our breakdown format, where we can observe that the detailed breakdown of latency can help us locate the faulty part efficiently compared to traditional representation (wait time fault in R4) [4], [5].”
BackgroundDeoxys: A Causal Inference Engine for Unhealthy Node Mitigation in Large-scale Cloud Infrastructure
Zhang, C., Yao, R., Qin, S., Li, Z., Agrawal, S. S., Mishra, B. R., Tran, T. M., Ma, M., Lin, Q., Chintalapati, M., et al. (2024) · ACM Symposium on Cloud Computing (SoCC) · doi:10.1145/3698038.3698534 · Cited by 8
yRCA: An explainable failure root cause analyser
Soldani, J., Forti, S., & Antonio Brogi, A. (2023) · Science of Computer Programming · doi:10.1016/j.scico.2023.102997 · Cited by 7
Self-citationIntelligent Identification over Power Big Data: Opportunities, Solutions, and Challenges
Luo, L., Li, X., Yang, K., Wei, M., Chen, J., Yang, J., & Yao, L. (2022) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2022.021198 · Cited by 4
PyRCA: A Library for Metric-based Root Cause Analysis
Liu, C., Yang, W., Mittal, H., Singh, M., Sahoo, D., & Hoi, S. C. H. (2023) · arXiv · doi:10.48550/arxiv.2306.11417 · Cited by 4
“Root Cause Analysis (RCA) is a commonly used method for ensuring the reliability and efficiency of production systems in various domains, including IT operations (Soldani and Brogi, 2022), telecommunications (Zhang et al., 2021), and epidemiology (Landsittel et al., 2020).”
MethodMicroKGCL: A Knowledge Graph for Root Cause Localization of Feedback Issues in Microservices
Yao, X.-W., Lu, Q.-C., Li, Q., Liu, L.-L., & Zhu, Z.-C. (2023) · 2023 IEEE 23rd International Conference on Software Quality, Reliability, and Security (QRS) · doi:10.1109/qrs60937.2023.00067 · Cited by 3
“Metric-based approaches use agents to monitor metrics on their services, and by then processing such metrics to detect anomalies[11].”
BackgroundRobust Anomaly Diagnosis in Heterogeneous Microservices Systems under Variable Invocations
Yang, J., Guo, Y., Chen, Y., Zhao, Y., Lu, Z., & Liang, Y. (2022) · GLOBECOM 2022 - 2022 IEEE Global Communications Conference · doi:10.1109/globecom48099.2022.10001270 · Cited by 3
“Graph-based methods ignore the effect of variable invocations, have a high computation complexity, and are time-consuming to perform online on medium or large-scale applications [18].”
MethodO’Shea, K., Yan, S., Yu, M., Chen, X., Mauceri, S., Dhariyal, B., Xu, L., O'Connor, N. E., & Liu, M. (2025) · IEEE Transactions on Cloud Computing · doi:10.1109/tcc.2025.3634737 · Cited by 5
AI-Driven Log Analysis: Advances and Challenges
Wang, Y., Gan, W., & Yu, P. S. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11401507 · Cited by 5
“In the past three years, more than 100 studies related to logs have been published in academic journals or conferences, covering topics including log recording [4], log compression [5], log parsing [6], anomaly detection [7], fault prediction [8], and fault RCA [9].”
Graph-Augmented Multi-Agent Robust Root Cause Analysis in AIOps
Zou, H., Zhao, Y., Chen, X., Wang, L., Yu, J., & Yuan, L. (2026) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2026.077908 · Cited by 4
Panahandeh, M., Ezzati‐Jivan, N., Hamou‐Lhadj, A., & Miller, J. (2024) · ACM/SPEC International Conference on Performance Engineering (ICPE) · doi:10.1145/3629527.3651426 · Cited by 4
ML Driven Root Cause Analysis (RCA) in Telco Microservices Continuum
Enz, S., Nigg, S., Kalinagac, O., Ermiş, O., & Gür, G. (2024) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops59551.2024.10615702 · Cited by 3
“An overview of different concepts is provided in the surveys of Sol´e et al. [5] and of Soldani and Brogi [6].”
BackgroundResultThe Past, Present, and Future of Research on the Continuous Development of AI
Steidl, M., Ramler, R., & Felderer, M. (2024) · 2024 50th Euromicro Conference on Software Engineering and Advanced Applications (SEAA) · doi:10.1109/seaa64295.2024.00054 · Cited by 3
Intelligent CI/CD Pipelines: Leveraging AI for Predictive Maintenance and Incident Management
Baswareddy, J. P. R. (2025) · European Journal of Computer Science and Information Technology · doi:10.37745/ejcsit.2013/vol13n75065 · Cited by 3
Insights into KPI-based performance anomaly detection in database systems: A comprehensive study
Gao, X., Yuan, P., Han, S., Liu, Y., Xia, X., Zhang, H., Cui, J., Li, H., & Zhao, K. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127959 · Cited by 3
Mecheri, C., Nguyen, N. Q., Ouazène, Y., Yalaoui, F., & Scaglia, T. (2025) · Production & Manufacturing Research · doi:10.1080/21693277.2025.2542175 · Cited by 5
“Statistical tools can be categorized into different groups and are used at various steps of the process (Soldani & Brogi, 2022).”
An unsupervised cross project model for crashing fault residence identification
Liu, X., Zhou, X., Yang, D., Yan, M. L., Zhang, W., Zhao, H., Xue, L., & Fan, M. Y. (2022) · IET Software · doi:10.1049/sfw2.12073 · Cited by 3
“Soldani et al. [23] surveyed the existing techniques for anomaly detection and root cause analysis in multi ‐ service applications, including log ‐ based methods, visualisation ‐ based methods, distributed tracing ‐ based, and monitoring ‐ based methods.”
MethodNishikawa, A., Hattori, K., Tanaka, M., Muranami, H., & Nishi, H. (2022) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon49645.2022.9969098 · Cited by 3
“From the perspective of usefulness in the field, an anomaly detection system should also identify the cause of the anomaly because an automatic identification of the cause would enable operators to address the abnormality faster and more efficiently [3].”
BackgroundTsubouchi, Y., & Tsuruta, H. (2024) · IEEE Access · doi:10.1109/access.2024.3374334 · Cited by 5
Towards Sustainable Deployment of Microservices over the Cloud-IoT Continuum, with FREEDA
Soldani, J., Amadini, R., Antonio Brogi, A., Forti, S., Giallorenzo, S., Plebani, P., Vitali, M., & Zavattaro, G. (2024) · Workshop on Flexible Resource and Application Management on the Edge (FRAME) · doi:10.1145/3659994.3660311 · Cited by 3
Self-citationSteidl, M., Leitner, M., Urbanke, P., Gattringer, M., Felderer, M., & Ristov, S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78386-9_31 · Cited by 3
Energy Metrics for Edge Microservice Request Placement Strategies
Toczé, K., & Nadjm‐Tehrani, S. (2025) · ACM/SPEC International Conference on Performance Engineering (ICPE) · doi:10.1145/3676151.3719380 · Cited by 3
“As seen in Table 5, the different optimization objectives lead to similar request completion times.”
InfluentialPORCA: Root Cause Analysis with Partially Observed Data
Gong, C., Yao, D., Wang, J., Li, W., Fang, L., Xie, Y., Feng, K., Han, P., & Bi, J. (2026) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde65706.2026.00087 · Cited by 4
“Some previous studies emphasize on the concept of “observability” and leverage data engineering techniques, e.g. , increasing the number of monitoring metrics or dive into metric, trace, and log data iteratively, to enhance perception domain [2].”
Advancing Software Monitoring: An Industry Survey on ML-Driven Alert Management Strategies
Hrusto, A., Runeson, P., Engström, E., & Ohlsson, M. C. (2024) · Euromicro Conference on Software Engineering and Advanced Applications (SEAA) · doi:10.1109/seaa64295.2024.00073 · Cited by 3
“Most recent and relevant surveys [3], [11] provide valuable insights, but each from unique and differing viewpoints regarding cloud monitoring practices and the adoption of machine learning in the industry, particularly for software failure prediction.”
Generating Executable Microservice Applications for Performance Benchmarking
Lubas, Y., Straesser, M., Bauer, A., & Kounev, S. (2025) · ACM/SPEC International Conference on Performance Engineering (ICPE) · doi:10.1145/3676151.3719361 · Cited by 4
“Prominent examples from the literature include root cause localization [23], autoscaling [8], placement [2], and many more.”
AmocRCA: At Most One Change Segmentation and Relative Correlation Ranking for Root Cause Analysis
Altenbernd, A., Zhi-yuan, W., & Kao, O. (2025) · ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) · doi:10.1145/3696630.3731612 · Cited by 4
Mistry, H. K., & Mavani, C. (2025) · World Journal of Advanced Engineering Technology and Sciences · doi:10.30574/wjaets.2025.16.3.1327 · Cited by 2
CIRCA: A Framework for Collaborative Identification of Root Cause Analysis in IoT Microservices
Jiang, X., Luo, H., Sun, Y., & Das, S. K. (2025) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2025.3631804 · Cited by 4
A Decentralized Root Cause Localization Approach for Edge Computing Environments
Fernando, D., Rodríguez, M. V. R., & Buyya, R. (2026) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2026.3668228 · Cited by 2
“Index Terms —Edge computing, root cause localization, anomaly detection, microservices, decentralized systems, Personalized PageRank, performance diagnosis.”
Thota, M. R. (2025) · International Journal of Scientific Research in Science Engineering and Technology · doi:10.32628/ijsrst25121450 · Cited by 2
Fine-grained Spatiotemporal Features-Based for Anomaly Detection in Microservice Systems
Yang, X., Wang, J., Zhou, B., Wang, W., Liu, W., & Dong, Y. (2022) · IEEE International Conference on High Performance Computing and Communications; IEEE International Conference on Smart City; IEEE International Conference on Data Science and Systems (HPCC/SmartCity/DSS) · doi:10.1109/hpcc-dss-smartcity-dependsys57074.2022.00138 · Cited by 4
“Many Internet companies provide the core business of microservice architecture, such as Amazon, Netflix, Spotify, and Twitter [1].”
BackgroundClassification of Software Bugs using Support Vector Machine
Kusumaniswari, V., Chinta, M., & Shareff, S. N. (2023) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt56998.2023.10308104 · Cited by 2
Microservice Traces Anomaly Detection Based on Structural Clustering and Graph Attention Autoencoder
He, Y. H., Zhang, X., Wang, P., Liu, M., & Cao, Z. (2024) · International Conference on Advanced Algorithms and Control Engineering (ICAACE) · doi:10.1109/icaace61206.2024.10549242 · Cited by 2
“Trace anomaly detection is an important component of Artificial Intelligence for IT Operations (AIOps) [1] .”
BackgroundHanada, H., & Ishibashi, K. (2024) · IEEE Annual International Computer Software and Applications Conference (COMPSAC) · doi:10.1109/compsac61105.2024.00391 · Cited by 3
“One approach to managing the complexity in microser-vices architectures involves incorporating automation into the system recovery workflow, such as anomaly detection and root cause analysis [4].”
BackgroundMicroHFRCL: A History Faults Based Root Cause Localization Framework in Microservice Systems
Zhang, L., Shi, Y., Qi, K., Wu, D. F., Wang, X., Yan, Z., & Chen, Z. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650929 · Cited by 2
“…service response time caused by resource competition such as CPU, memory, and network may propagate along the service call chain and ultimately lead to availability issues at the business level, such as failed or timeout business requests, causing difficulties in operation and maintenance work [3].”
BackgroundMulti-stage Location for Root-Cause Metrics in Online Service Systems
Zhao, Y., Zhang, W., Wang, Z., Zhang, S., Sui, K., Dong, E., & Yang, J. (2023) · IEEE/IFIP Network Operations and Management Symposium (NOMS) · doi:10.1109/noms56928.2023.10154325 · Cited by 2
“3) Baselines: Although there has been a lot of work on root-cause metrics location [34], most of them rely on extra input or require long initialization, so we selected four representative works among the easy-to-deploy methods for comparison: • ϵ -Diagnosis [6]’s core idea is that root-cause…”
MethodModernizing Mainframe Monitoring: A Comparative Analysis of Observability Dashboarding Tools
Lazarus, R. (2024) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2024.63866 · Cited by 2
RADICE: Causal Graph Based Root Cause Analysis for System Performance Diagnostic
Tonon, A., Zhang, M., Caglayan, B., Shen, F., Gui, T., Wang, M., & Zhou, R. (2025) · IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER) · doi:10.1109/saner64311.2025.00050 · Cited by 3
“Root cause analysis is widely used to ensure the reliability of production systems [3], [10] in many domains such as IT operations [23], telecommunications, etc. Commonly used root cause analysis algorithms are based on correlation [4], [22], [25].”
A 2-Phase Strategy for Intelligent Cloud Operations
Lanciano, G., Andreoli, R., Cucinotta, T., Bacciu, D., & Passarella, A. (2023) · IEEE Access · doi:10.1109/access.2023.3312218 · Cited by 2
“ysis [9], [10], to understand what caused it, and ultimately what is the right fix.”
BackgroundYu, L., Fang, J., Wang, Q., Li, F., & Liu, H. (2026) · Machines · doi:10.3390/machines14050476 · Cited by 1
G-Cause: Parameter-free Global Diagnosis for Hyperscale Web Service Infrastructures
Jiang, X., Zhang, Y., Bi, T., Shen, X., Zhang, L. Y., Pan, Y., Ma, M., Han, L., Wang, F., Liu, X., et al. (2024) · IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws62655.2024.00119 · Cited by 1
“Based on the granularity of the returned results, root cause localization is divided into coarse-grained application-level (returning the service where the root cause is located) and fine-grained service-level (returning the KPI of the root cause service) [23].”
BackgroundEnhancing Failure Resilience of Cloud-Edge Microservices: The FREEDA Approach
Ponce, F., Forti, S., Soldani, J., & Antonio Brogi, A. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-84617-5_9 · Cited by 1
Self-citationHuang, X., Zhou, F., Deng, T., Chen, F., Chen, J., & Chen, N. (2025) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001425540084 · Cited by 1
NetEventCause: Event-Driven Root Cause Analysis for Large Network System Without Topology
Yuan, Z., Ma, L., Wei, W., Zhu, X., Sun, M., Chen, D., & Ban, X. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3574316 · Cited by 3
“return type: Derivative, [ ˆ R e i [1] , . . . , ˆ R e i [ K ]] 9: end if D. Summary of NEC Algorithms 1 and 2 provide the pseudocode for the training and utilizing the trained neural TPP to identify root events and causal events, respectively.”
Robust and Lightweight Root Cause Analysis for Microservice Metrics
Fukuda, N., Nozue, H., Oishi, H., & Tayama, K. (2025) · IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws67624.2025.00023 · Cited by 1
“A typical microservice-based system consists of dozens to hundreds of services, each with numerous metrics that must be continuously monitored [1].”
GUIDE - GNN based Unified Incident Detection for Microservices Application Deployments
Dutt, A., Jang, D., Nadkarni, J., Su, K., & Gandhi, A. (2025) · IEEE International Conference on Distributed Computing Systems Workshops (ICDCSW) · doi:10.1109/icdcsw63273.2025.00047 · Cited by 1
“Below, we discuss the most relevant related work for incident detection in microservices applications; for a broader overview, we refer readers to survey articles [14].”
Wu, W., Li, C., Zhang, Y., Zhai, H., Wang, Y., Dong, K., Zhao, S., Yang, M., & Huang, G. Q. (2025) · Engineering · doi:10.1016/j.eng.2025.09.034 · Cited by 1
RootScan: Unveiling Microservice Anomalies through Fine-Grained, Interpretable Root Cause Analysis
Li, C., Ye, C., & Zhou, H. (2025) · IEEE Symposium on Reliable Distributed Systems (SRDS) · doi:10.1109/srds69199.2025.00024 · Cited by 3
Pei, J., Hu, Y., Yu, H., Tian, L., Wang, Z., & Pei, X. (2026) · Future Generation Computer Systems · doi:10.1016/j.future.2026.108430 · Cited by 1
Applications of anomaly detection algorithms in identifying abnormal events
Veeraiah, V., Velamala, R., Shrivastava, P., Pandey, J. K., & Garg, M. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-36408-2.00002-3 · Cited by 1
DeCausal: Deviation-Aware Causal Inference for Microservice Root Cause Analysis
Ding, W., Guo, Z., Zhang, J., & Ruan, J. (2026) · International Conference on Neural Networks, Information and Communication Engineering (NNICE) · doi:10.1109/nnice68970.2026.11466191 · Cited by 1
“Second, microservice failures often exhibit causal cascades: downstream symptoms can be more anomalous than the true upstream cause, so naive ranking by anomaly magnitude is unreliable [2].”
Sanchez, B. R., Giamattei, L., Guerriero, A., Pietrantuono, R., & Malavolta, I. (2026) · Journal of Systems and Software · doi:10.1016/j.jss.2025.112626 · Cited by 1
Li, Z., Yu, J., Huang, Z., & Huang, Y. (2025) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2025.3631913 · Cited by 5
“As is indicated in [10], it could be confused with other similar words (such as fault localization and incident mitigation).”
ClusterRCA: An End-to-End Approach for Network Fault Localization and Classification for HPC System
Sun, Y., Pan, X., Xiong, X., Tao, L., Wang, J., Zhang, S., Yuan, Y., Li, Y., & Jian, K. (2025) · Proceedings/Proceedings - International Symposium on Software Reliability Engineering · doi:10.1109/issre66568.2025.00043 · Cited by 3
“2) Customized Random Walk: Random walk is commonly used for failure diagnosis in cluster or cloud environments, as referenced in [12], [33], [34].”
AHA: Scalable Alternative History Analysis for Operational Timeseries Applications
Kamarthi, H., Shah, H., Milner, H., Sinha, S., Li, Y., Prakash, B. A., & Sekar, V. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770854.3783945 · Cited by 1
AnoMod: A Dataset for Anomaly Detection and Root Cause Analysis in Microservice System
Ping, K., Mazhar, H. B., Wang, Y., Song, Y., & Mäntylä, M. (2026) · International Conference on Mining Software Repositories (MSR) · doi:10.1145/3793302.3793324 · Cited by 2
Provenance-enhanced Root Cause Analysis for Jupyter Notebooks
Xin, R., Stallinga, S., Liu, H., Chen, P., & Zhao, Z. (2022) · IEEE/ACM International Conference on Utility and Cloud Computing (UCC) · doi:10.1109/ucc56403.2022.00058 · Cited by 3
“Soldani et al. [34] distilled two main ways for root cause analysis: log-based and distributed tracing.”
Design and Implementation of an Advanced Planning and Scheduling System Based on Microservices
Zhang, H., Zhang, J., & Wang, Y. (2023) · Atlantis highlights in engineering/Atlantis Highlights in Engineering · doi:10.2991/978-94-6463-262-0_61 · Cited by 1
MPDP: A Probabilistic Architecture for Microservice Performance Diagnosis and Prediction
Noor, T. H. (2024) · Computer Systems Science and Engineering · doi:10.32604/csse.2024.052510 · Cited by 1
Sruthi, P. C., Guo, Z., Chu, D., Chen, Z., & Zhang, Y. (2024) · ACM Symposium on Cloud Computing (SoCC) · doi:10.1145/3698038.3698568 · Cited by 5
SinkFlow: Fast and traceable root-cause localization for multidimensional anomaly events
Hu, Z., Liu, L., Ma, L., & Yu, X. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109582 · Cited by 1
On the Integration of Large-Scale Time Series Distance Matrices Into Deep Visual Analytic Tools
Santamaria-Valenzuela, I., Rodríguez-Fernández, V., & Camacho, D. (2024) · Cognitive Computation · doi:10.1007/s12559-024-10394-x · Cited by 1
Toward an Automated Real-Time Anomaly Detection Engine in Microservice Architectures
Khan, M. (2023) · Carleton University's Institutional Repository (MacOdrum Library, Carleton University) · doi:10.22215/etd/2023-15397 · Cited by 4
Anomaly detection and root-cause identification in microservices: a survey
Barata, L. M., Sequeira, S., Lopes, E., Inácio, P. R. M., & Freire, M. M. (2026) · Cluster Computing · doi:10.1007/s10586-026-06095-9 · Cited by 4
“However, besides the topics addressed in our survey that were not considered in [26] (see Table 1), much research literature has been published in the last few months, so we also increased the value of the survey by including the latest publications on the subject.”
Wang, J., Chen, R., Wang, Y., Liao, X., Fan, Z., Wu, X., Wu, W., Liu, X., & Zhao, J. (2026) · 2026 IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws72778.2026.00056 · Cited by 1
“[1]–[3] However, this architectural shift also makes modern systems increasingly complex to operate: failures rarely stay local, and subtle issues can quickly propagate along service dependencies, producing amplified and misleading symptoms downstream [4], [5].”
Enhancing Continuous Integration Systems with Assisted Root Cause AnalysisPreprint
Bonic, S., Bonic, J., & Schmid, S. (2022) · doi:10.36227/techrxiv.20689594 · Cited by 1
Wireless Network Fault Localization via Metric Classification
Han, Y., Du, Q., & Xu, J. (2022) · IEEE International Conference on Mobile Ad-Hoc and Sensor Systems (MASS) · doi:10.1109/mass56207.2022.00049
“Monitoring metrics have been widely used in anomaly detection and fault localization [2].”
BackgroundMethodEnhancing Continuous Integration Systems with Assisted Root Cause AnalysisPreprint
Bonic, S., Bonic, J., & Schmid, S. (2023) · doi:10.36227/techrxiv.20689594.v2 · Cited by 1
Exploring Multiple Classification Systems for Online Time Series Anomaly Detection
Santamaria-Valenzuela, I., Rodríguez-Fernández, V., & Camacho, D. (2023) · International Conference on Networks, Multimedia and Information Technology (NMITCON) · doi:10.1109/nmitcon58196.2023.10276028
“Detection of time series data anomalies or outliers is crucial in big data analysis because their patterns provide valuable information for decision making in a variety of applications such as fraud detection, healthcare monitoring, and performance analysis [2], [3].”
BackgroundTowards Performance Analysis for Online Data Science Learning Platform
Banyan, Z., Zou, X., Xu, H., Ma, D., Lin, C., Zhang, B., Chen, M., & Li, H. (2024) · Communications in computer and information science · doi:10.1007/978-981-97-0791-1_31
Edge-Cloud Co-Evolutionary Task Offloading for Faulty Edge Microservices
Zhang, S., Ma, L., & Wang, Y. (2024) · International Conference on Information Science, Parallel and Distributed Systems (ISPDS) · doi:10.1109/ispds62779.2024.10667554
“Another approach is reactive fault tolerance, including root cause analysis [2] and fault repair (e.g., restart and check-pointing [3]).”
BackgroundMulti-source KPIs’ root cause localization in online service systems
Xia, H., Xu, J., Xiao, B., Jia, H., Gao, C., & Chen, Y. (2024) · International Conference on Networking and Network Applications (NaNA) · doi:10.1109/nana63151.2024.00072
“Dejavu [8] categorized all the metrics to create a fault dependency graph.”
BackgroundCausal Structure Learning of High-Dimensional Data Based on Local and Global Collaboration
Xue, Y., Wang, H., Liu, C., Li, W., Zhuang, J., Ma, L., Hao, Z., & Fan, Z. (2024) · International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD) · doi:10.1109/icnc-fskd64080.2024.10702301
Design and Implementation of Fault Reconfiguration System Based on MQTT
Ye, W., Wang, H., Cao, S., & Yan, L. (2024) · International Conference on Electronics and Communication, Network and Computer Technology (ECNCT) · doi:10.1109/ecnct63103.2024.10704320
Anytime Communication: A Human-AI Collaboration Framework for Causal-Based Root Cause Analysis
Deng, Z., Prugsanapan, P., & Kong, Z. (2025) · AIAA SciTech Forum · doi:10.2514/6.2025-2252 · Cited by 1
Fuzzy Analytic Hierarchy Process Based Health Evaluation of Business Systems
Gao, D., Yang, M., Wang, L., Zhang, B., Bao, F., & Du, J. (2024) · International Conference on Industrial Automation, Robotics and Control Engineering (IARCE) · doi:10.1109/iarce64300.2024.00092
“The evaluation of system health paves the way toward optimal resource allocation [2], heightened user experiences, proactive risk mitigation [3], streamlined operational costs, and fortified business decision-making.”
Microservice Applications and Their Workloads on GitHub
Lubas, Y., Straesser, M., Rohwer, I., Kounev, S., & Bauer, A. (2025) · ACM/SPEC International Conference on Performance Engineering (ICPE) · doi:10.1145/3680256.3721321 · Cited by 3
Tang, Y., Tan, Z., Chen, J., Yao, X., Zhong, G., & Liu, F. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-4503-9_17
Agarwal, S. (2025) · ISCSITR- INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND ENGINEERING · doi:10.63397/iscsitr-ijcse_2025_06_04_002
Cluster-Aware Causal Discovery Framework for Root Cause Analysis of Base Station Alarms
Zhang, K., Zhu, X., Zheng, J., Cao, J., Zhang, K., & Pan, L. (2024) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshp64532.2024.11101284
“Traditional RCA methods rely on constructing fault trees and extensive expert knowledge [1].”
FNoDe: Faulty Node Detection in Microservices Architecture
Borse, H., Satpathy, U., Mondal, M., & Mitra, B. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-02215-8_6
SysResolve: Study on In-Context LLM Generation of Resolution Scripts
Borse, H., Satpathy, U., Mondal, M., & Mitra, B. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-02049-9_10
Duan, T., Chen, R.-Q., Wang, P., Zhao, J., Liu, J., Han, S., Liu, Y., & Xu, F. (2025) · IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP) · doi:10.1109/icse-seip66354.2025.00049
“Root cause analysis (RCA) [6,7,33] aims to locate the root cause failures [34].”
A Review of Machine Learning Approaches for Real-Time Alerting in Service Level Objective Monitoring
Sarni, T., & Nurminen, J. K. (2025) · IEEE International Conference on Software Services Engineering (SSE) · doi:10.1109/sse67621.2025.00026
“A recent survey by Soldani and Brogi [12] demonstrates that unsupervised anomaly detection approaches conduct training based on the data from services operating under normal conditions (i.e., samples should not contain anomalies).”
InfluentialXin, R., Gao, F., Gong, S., & Chen, P. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5498415
PERFORMANCE PERCENTILE ANALYSIS FOR API-BASED TESTING
Khlamov, S. V., Mendielieva, M., Vovk, O., Trunova, T., & Teslenko, Y. (2025) · doi:10.36059/978-966-397-538-2-13
Root Cause Analysis in Microservice-Based System Using Trace Anomaly Score and Correlation Analysis
Roshna, K. R., Martin, J. P., & Joseph, C. T. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-4691-3_12 · Cited by 1
Fukuyama, Y., Kubo, M., & Sato, H. (2025) · Artificial Life and Robotics · doi:10.1007/s10015-025-01084-4
Zhang, S., Li, Y., Tang, J., Zhao, C., Gu, W., Sun, Y., & Pei, D. (2025) · Proceedings/Proceedings - International Symposium on Software Reliability Engineering · doi:10.1109/issre66568.2025.00041
Leveraging Edge Computing for IoT Device Observability in Smart City Environments
Fleck, J., Katzenberg, F., & Sachweh, S. (2025) · IEEE European Technology and Engineering Management Summit (E-TEMS) · doi:10.1109/e-tems64751.2025.11239205
“In the context of identifying and mitigating the root causes of these failures, distributed tracing and the collection of metrics have become increasingly pivotal components of distributed software architectures [5].”
LogCALM: a log-based causal discovery and semantic modeling approach for network fault diagnosis
Ye, X., Wang, X., Zhou, Y., Kong, X., & Qi, H. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130553
DALAD: Unsupervised Detection of Global and Local Anomalies in Microservice Systems
Tian, X., Ying, S., Li, T., Zhang, T., & Wang, Y. (2025) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2025.3649198 · Cited by 2
Failure-resilient and carbon-efficient deployment of microservices over the cloud-edge continuum
Ponce, F., Gazza, S., D'Iapico, A., Amadini, R., Antonio Brogi, A., Forti, S., Giallorenzo, S., Plebani, P., Usai, D., Vitali, M., et al. (2026) · Cluster Computing · doi:10.1007/s10586-026-06520-z · Cited by 1
Self-citationRaeiszadeh, M., Estrada‐Solano, F., & Glitho, R. (2026) · IEEE Communications Magazine · doi:10.1109/mcom.001.2500123
“Due to their highly distributed and dynamic nature, cloud-native architectures are particularly vulnerable to anomalies [2].”
AS-Rank: Automatic and Self-Adaptive Fault Root Cause Localization for Microservice Architecture
Wu, Y., Gao, Y., Song, J., Yang, L., & Nie, L. (2025) · International Conference on Cyber-Physical Social Intelligence (ICCSI) · doi:10.1109/cpsi66656.2025.11343968
“However, despite these advantages, microservice architectures introduce new challenges for software reliability, particularly in identifying the root causes of system failures [2].”
Yu, F., Li, X., Xu, L., Tong, F., & Zhao, D. (2025) · International Conference on High Performance Compilation, Computing and Communications (HP3C) · doi:10.1145/3774949.3774957
“Crowdsourced testing platforms and plug-and-play architectures [26] often suffer from unpredictable quality in externally contributed subsystems, given the heterogeneous origins and varying development practices.”
Metadata
- Authors
- Soldani, J., & Brogi, A.
- Affiliations
- University of Pisa (IT)
- University of Pisa, Pisa, PI, Italy
- Venue
- ACM Computing Surveys
- Published
- 2022-02-03
- Volume
- 55
- Issue
- 3
- Pages
- 1-39
- ISSN
- 0360-0300 (ISSN-L)
- 1557-7341
- OpenAlex
- W3165186175
- Cited by
- 256
- References
- 95
- Citations by year
- 2026: 78 · 2025: 63 · 2024: 67 · 2023: 31 · 2022: 15
- FWCI
- 19.53
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- ACM Computing Surveys (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- CINECA IRIS Institutial research information system (University of Pisa) (submittedVersion, other-oa)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Software System Performance and Reliability
- Physical Sciences › Computer Science › Information Systems › Cloud Computing and Resource Management
- Physical Sciences › Computer Science › Computer Networks and Communications › Distributed systems and fault tolerance
- Keywords
- anomaly detection, root cause analysis, microservices, cloud-native applications, log analysis, performance monitoring, fault diagnosis, service failure
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.