HeMiRCA: Fine-Grained Root Cause Analysis for Microservices with Heterogeneous Data Sources
The DOI matches its Crossref record; 39 of the 39 references it cites were found in a registry or an index.
Abstract
Microservices architecture improves software scalability, resilience, and agility but also poses significant challenges to system reliability due to their complexity and dynamic nature. Identifying and resolving anomalies promptly is crucial because they can quickly propagate to other microservices and cause severe damage to the system. Existing root-cause metric localization approaches rely on metrics or metrics-anomalies correlations but overlook other monitoring data sources (e.g., traces). We are the first to identify and leverage the anomaly-aware monotonic correlation between heterogeneous monitoring data, motivated by which we propose a novel framework, Heterogeneous data sources in Microservice systems for Root Cause Analysis (HeMiRCA) , for hierarchical root cause analysis using Spearman correlation. HeMiRCA is based on the key observation that the microservice responsible for a particular type of fault exhibits a monotonic correlation between the trends of its associated metrics and the trace-based anomaly score of the system. HeMiRCA first calculates time-series anomaly scores using traces and then exploits the correlations between multivariate metrics and the scores to rank the suspicious metrics and microservices. HeMiRCA has been evaluated on two datasets collected from widely used microservice systems. The results show that HeMiRCA outperforms the state-of-the-art approaches by a large margin in identifying root causes at both service level and metric level, ac…
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
“Direct LLM output is brittle when used alone.Correctness comes from verifiers, repair loops, and explicit checks around the generator [75], [89], [90].”
From Large language models for agentic NetOps and AIOps: Architectures, evaluation, and safety (2027) · cites this paper as [75]
In the citing paper
“Instead, the LLM is most valuable as a controller of workflow: it translates intent into queries, routes evidence through verifiers, proposes minimally invasive diffs, and documents preconditions and rollback [9], [75], [76].”
From Large language models for agentic NetOps and AIOps: Architectures, evaluation, and safety (2027) · cites this paper as [75]
In the citing paper
“Recent work makes ambiguity explicit and studies how an LLM-driven assistant should ask questions before generating configurations [114], [75].”
From Large language models for agentic NetOps and AIOps: Architectures, evaluation, and safety (2027) · cites this paper as [75]
Citations
Cites
Bayesian Inference in Econometric Models Using Monte Carlo Integration
Geweke, J. (1989) · Econometrica · doi:10.2307/1913710 · Cited by 1,563 · cited 1×
“Monte Carlo integration [14] is often adopted to approximate the expectation in Equation 1, as Equation 2, where ( 𝑙 ) , 𝑙 = 1 , . . . , 𝐿 are samples from 𝑞 𝜙 ( 𝑧 | 𝑥 ) .”
Noise Reduction in Speech Processing
Cohen, I., Huang, Y., Chen, J., & Benesty, J. (2009) · Springer Topics in Signal Processing · doi:10.1007/978-3-642-00296-0 · Cited by 1,459
Encyclopedia of measurement and statistics
(2007) · Choice Reviews Online · doi:10.5860/choice.44-4214 · Cited by 1,385
(2015) · Cited by 1,279
Heaton, J. (2018) · Genetic Programming and Evolvable Machines · doi:10.1007/s10710-017-9314-z · Cited by 1,054
Gan, Y., Zhang, Y., Cheng, D., Shetty, A., Rathi, P., Katarki, N., Bruno, A., Hu, J., Ritchken, B., Jackson, B., et al. (2019) · Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems · doi:10.1145/3297858.3304013 · Cited by 665 · cited 2×
“These datasets were collected from widely-used microservice benchmark systems, namely TrainTicket [57] and SocialNetwork [13], which contain multi-source data, including metrics and traces.”
MethodProceedings of the VLDB Endowment
Alonso, G., Freire, J., Saçan, A., & Tatbul, N. (2011) · Cited by 653
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×
“In service-oriented software engineering, a variety of monitoring data play an essential role in maintaining the stability and reliability of microservice systems, such as metrics, traces, alerts, and logs [5, 7, 22, 34, 49].”
BackgroundSelf-citationZar, J. H. (2005) · Encyclopedia of Biostatistics · doi:10.1002/0470011815.b2a15150 · Cited by 566 · cited 2×
“This is crucial in environments where anomalies may not scale directly with metrics but still show a consistent direction, offering clearer insights into causal connections.”
Zhou, X., Peng, X., Xie, T., Sun, J., Ji, C., Li, W., & Ding, D. (2021) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2018.2887384 · Cited by 410
Research works printed but not linked: 14
- Kota Dohi, Takashi Endo, Harsh Purohit, Ryo Tanabe, and Yohei Kawaguchi. 2021. Flow-based self-supervised density estimation for anomalous sound detection. In Proceedings of the ICASSP 2021–2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 336–340.
- Mostafa Farshchi, Jean-Guy Schneider, Ingo Weber, and John Grundy. 2015. Experience report: Anomaly detection of cloud application operations using log and cloud metric correlation analysis. In Proceedings of the 2015 IEEE 26th International Symposium on Software Reliability Engineering (ISSRE). IEEE, 24–34.
- Dan Hendrycks Mantas Mazeika and Thomas Dietterich. 2018. Deep anomaly detection with outlier exposure. arXiv:1812.04606. Retrieved from https://arxiv.org/abs/1812.04606 · arXiv
- Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv:1412.6980. Retrieved from https://arxiv.org/abs/1412.6980 · arXiv
- Diederik P. Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv:1312.6114. Retrieved from https://arxiv.org/abs/1312.6114 · arXiv
- Cheryl Lee Tianyi Yang Zhuangbin Chen Yuxin Su and Michael R. Lyu. 2023. Eadro: An end-to-end troubleshooting framework for microservices on multi-source data. arXiv:2302.05092. Retrieved from https://arxiv.org/abs/2302.05092 · arXiv
- Dewei Liu, Chuan He, Xin Peng, Fan Lin, Chenxi Zhang, Shengfang Gong, Ziang Li, Jiayu Ou, and Zheshun Wu. 2021. MicroHECL: High-efficient root cause localization in large-scale microservice systems. In Proceedings of the 2021 IEEE/ACM 43rd International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP). IEEE, 338–347.
- Ping Liu, Yu Chen, Xiaohui Nie, Jing Zhu, Shenglin Zhang, Kaixin Sui, Ming Zhang, and Dan Pei. 2019. Fluxrank: A widely-deployable framework to automatically localizing root cause machines for software service failure mitigation. In Proceedings of the 2019 IEEE 30th International Symposium on Software Reliability Engineering (ISSRE). IEEE, 35–46.
- Jian-Guang Lou, Qingwei Lin, Rui Ding, Qiang Fu, Dongmei Zhang, and Tao Xie. 2013. Software analytics for incident management of online services: An experience report. In Proceedings of the 2013 28th IEEE/ACM International Conference on Automated Software Engineering (ASE). IEEE, 475–485.
- Meng Ma, Weilan Lin, Disheng Pan, and Ping Wang. 2019. Ms-rank: Multi-metric and self-adaptive root cause diagnosis for microservice applications. In Proceedings of the 2019 IEEE International Conference on Web Services (ICWS). IEEE, 60–67.
- Sasho Nedelkoski, Jorge Cardoso, and Odej Kao. 2019. Anomaly detection from system tracing data using multimodal deep learning. In Proceedings of the 2019 IEEE 12th International Conference on Cloud Computing (CLOUD). IEEE, 179–186.
- Danilo Jimenez Rezende, Shakir Mohamed, and Daan Wierstra. 2014. Stochastic backpropagation and approximate inference in deep generative models. In Proceedings of the 31st International Conference on Machine Learning. PMLR, 1278–1286.
- Ping Wang, Jingmin Xu, Meng Ma, Weilan Lin, Disheng Pan, Yuan Wang, and Pengfei Chen. 2018. Cloudranger: Root cause identification for cloud native systems. In Proceedings of the 2018 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID). IEEE, 492–502.
- Li Wu, Johan Tordsson, Jasmin Bogatinovski, Erik Elmroth, and Odej Kao. 2021. Microdiag: Fine-grained performance diagnosis for microservice systems. In Proceedings of the 2021 IEEE/ACM International Workshop on Cloud Intelligence (CloudIntelligence). IEEE, 31–36.
Cited by
No More Data Silos: Unified Microservice Failure Diagnosis With Temporal Knowledge Graph
Zhang, S., Zhao, Y., Xia, S., Wei, S., Sun, Y., Zhao, C., Ma, S., Kuang, J., Zhu, B., Pan, L., et al. (2024) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2024.3489444 · Cited by 29
“HeMiRCA [36] utilizes Spearman correlation to localize hierarchical root causes.”
Hypothesize-Then-Verify: Speculative Root Cause Analysis for Microservices with Pathwise Parallelism
Zhang, L., Jia, T., Zhai, Y., Pan, L., Duan, C., He, M., Xiao, P., & Li, Y. (2026) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1145/3786582.3786803 · Cited by 17
Agentic Memory Enhanced Recursive Reasoning for Root Cause Localization in Microservices
Zhang, L.-Z., Jia, T., Zhai, Y.-P., Pan, L.-Y., Duan, C.-M., He, M.-H., Jia, M., & Li, Y. (2026) · SEIP@ICSE · doi:10.1145/3786583.3786853 · Cited by 16
Rethinking the Evaluation of Microservice RCA with a Fault Propagation-Aware Benchmark
Fang, A., Zhang, S., Yang, Y., Wu, H., Xu, J., Wang, X., Wang, R., Wang, M., Lu, Q., & He, P. (2026) · Proceedings of the ACM on software engineering. · doi:10.1145/3797100 · Cited by 16
Self-citationLarge language models for agentic NetOps and AIOps: Architectures, evaluation, and safety
Bilal, M., Crowcroft, J., Wang, R., Xu, X., & Dustdar, S. (2027) · Computer Science Review · doi:10.1016/j.cosrev.2026.101075 · Cited by 10
“…engines, and telemetry queries [9], [10], [86] Evidence trace E ; hypothesis set H ; RCA evidence pointers; contradiction checks [10], [58], [59], [103] Citation to tool outputs; stop rules; escalation policy; no unsupervised write execution [10], [67], [74] RCA report; audit-ready trace of…”
InfluentialTORAI: 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
A review of major ICT failures and recovery strategies: Strengthening digital resilience
Adel, A., Saleem, N. H., Jan, T., & Prasad, M. (2025) · Computers & Security · doi:10.1016/j.cose.2025.104678 · Cited by 6
Li, Z., Yu, J., Huang, Z., & Huang, Y. (2025) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2025.3631913 · Cited by 5
“Zhu et al. propose a trace–metric correlation method using anomaly scores and monotonic Spearman correlations to rank metrics and services, achieving significantly higher top-1 localization accuracy than prior approaches [27].”
Fine-grained Tracing for Performance Anomaly Diagnosis of Serverless Functions
Wang, R., Yu, G., Casale, G., Chen, P. X., & Filieri, A. (2026) · ACM Transactions on Autonomous and Adaptive Systems · doi:10.1145/3785005 · Cited by 3
A Graph Transformer-Based Framework for Multi-Modal Failure Diagnosis in Microservice Systems
Kiss, Á., & Nehéz, K. (2026) · International Journal of Cloud Applications and Computing · doi:10.4018/ijcac.402208 · Cited by 3
KRCA: An Efficient Root Cause Analysis System in Hyper-scale Microservice Systems via Agentic AI
Jiang, J., Feng, J., Luo, Y., Zhang, Q., Su, Y. W., Gu, W., Zhang, S., Cui, T., Wu, Y., Huang, J., et al. (2026) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1145/3832783.3834468 · Cited by 3
CARE: Context Aware Root Cause Identification Using Distributed Traces and Profiling Metrics
Panahandeh, M., Ezzati‐Jivan, N., Hamou‐Lhadj, A., & Miller, J. (2025) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2025.3645143 · Cited by 3
“Since our dataset structure differs significantly from the one recommended by HeMiRCA [48], we report resource usage for HeMiRCA based on our reimplementation, which closely follows the original script.”
InfluentialA 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
“Trace-based RCL, while useful for understanding request flows, is often too coarse-grained to effectively diagnose deeper system issues, such as resource bottlenecks or internal mi-croservice misbehaviors [17].”
Toward In-Depth Root Cause Localization for Microservices With Multi-Agent Recursion-of-Thought
Zhang, L., Jia, T., Wang, K., Duan, C., He, M., Wang, R., Peng, X., Wang, M., Zhang, G., Chen, R., et al. (2026) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2026.3706572 · Cited by 4
GALA: Graph-Augmented LLM Agents for Root Cause Analysis and Incident Response in Microservices
Tian, Y., Liu, Y., Chong, Z., Huang, Z., Li, Y., & Jacobsen, H. (2026) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1145/3832783.3834335 · Cited by 4
Scalable Microservices: Design, Implementation, and Optimization for High-Traffic SaaS Platforms
Bonikela, H. R., & Mishra, D. R. (2025) · International Journal for Research Publication and Seminars · doi:10.36676/jrps.v16.i1.48 · Cited by 1
Duggirala, S., & Mishra, D. R. (2025) · International Journal for Research Publication and Seminars · doi:10.36676/jrps.v16.i1.49 · Cited by 1
Heterogeneous data-driven resolution generation for software systems via large language models
Liu, W., Sun, D., Yang, H., Wang, Y., & Huang, W. (2025) · Information Processing & Management · doi:10.1016/j.ipm.2025.104376 · Cited by 1
Park, G. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.04709 · Cited by 1
“Despite the critical role of performance metrics in root cause analysis during incident investigations, their representation of time-series modality is not aligned with the text embedding spaces of LLMs [17, 18, 19].”
LLM for Automated Root Cause Analysis in Microservices Architectures
Mhatre, A. S. A. (2025) · Journal of Information Systems Engineering & Management · doi:10.52783/jisem.v10i13s.2100 · Cited by 1
“Nonetheless, additional research is needed to validate its robustness across diverse microservices environments and operational conditions [9].”
Wang, K., Tian, Q., Zhou, R., Liu, C., & Xing, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3462-3_25
Ekhlasi, M., Fiorini, A., Dagenais, M., Ezzati‐Jivan, N., & Lamothe, M. (2025) · IEEE International Conference on Software Maintenance (ICSM) · doi:10.1109/icsme64153.2025.00056 · Cited by 2
“We test our approach against three state-of-the-art approaches: MicroRank [38], Nezha [39], and HemiRCA [47].”
InfluentialFrom Monolith to SOA: Evaluating service health metrics and taxonomy in practice
Lucas, M., Holterman, M., Havinga, T., & Capiluppi, A. (2026) · Journal of Systems and Software · doi:10.1016/j.jss.2026.113002
Zhao, S., Liu, K., Lu, J., Xu, Z., Yan, M., & Qiu, K. (2026) · Journal of Artificial Intelligence and Soft Computing Research · doi:10.2478/jaiscr-2026-0017
“HeMiRCA [44] performs root cause localization by combining traces and metrics, using correlation mining for metric ranking, but its fusion strategy is static and does not consider coordinated modality shifts.”
Uncovering Microservice Faults: A Temporal Graph Approach to Root Cause Analysis
Aharon, U., Dvir, A. Z., Dubin, R., Marbel, R., & Hajaj, C. (2026) · International Conference on Communications · doi:10.1109/icc59461.2026.11586787
“Zhu et al. [15] use a Variational Autoencoder to derive anomaly scores from traces and apply Spearman correlation with metrics.”
MicroInspect: A Progressive Framework for Metric-Level Root Cause Localization in Microservices
Yin, Y., Zhu, T., Chen, T., Lv, M., Song, Q., & Ji, B. (2026) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2026.3713967
“Evaluation Metrics: Following existing works [22][24] [30], for anomaly detection, we report precision, recall, and F1-score; for root-cause localization, we adopt the standard top-k hit ratio HR @ k and use normalized discounted cumulative gain NDCG @ k to measure ranking quality.”
InfluentialMSAQM: A Quality Model for Mixed-Source Architecture Evaluation
Zhang, C., Li, B., & Chen, H. (2026) · International Journal of Software Engineering and Knowledge Engineering · doi:10.1142/s0218194026500634
K-Sense: A Non-Invasive eBPF Framework For QoS Inference
Muslim, A., Aydenlou, A. B., & Recker, S. (2026) · IEEE International Conference on Fog and Edge Computing (ICFEC) · doi:10.1109/icfec69006.2026.00008
“1: Spearman correlation between kernel metrics and application latency. identify monotonic relationships between system metrics and service-level behavior [18].”
Meng, L. (2026) · IEEE Annual International Computer Software and Applications Conference (COMPSAC) · doi:10.1109/compsac69091.2026.00453
TD-RCA: Topology-Aware and Dual-Perspective Decoupling for Root Cause Analysis in Microservices
He, S., Tang, B., Wei, M., Xiang, L., & Xie, K. (2026) · International Workshop on Quality of Service · doi:10.1109/iwqos70441.2026.11661074
“Both academia and industry have made substantial progress in RCA for microservices [6], evolving from single-modality KPI correlation analysis [7], [8] through trace-based topology modeling [9]–[11] to deep graph learning approaches [12]–[15].”
InfluentialHussain, S., & Panjwani, H. C. (2026) · IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume (DSN-S) · doi:10.1109/dsn-s70715.2026.00023
“MRCA [7] uses reinforcement learning to prune causal graphs before ranking, and HeMiRCA [8] integrates heterogeneous data sources through statistical correlation.”
Capto: End-To-End Assurance for LLM Training and Inference in Datacenters
Gupta, J., Banka, T., Gupta, R., & Dharmaraj, M. (2026) · IEEE/IFIP Network Operations and Management Symposium (NOMS) · doi:10.1109/noms69089.2026.11668412
“Previous works such as MicroRCA [6], Sage [6], HeMiRCA [7] and MicroDiag [8] have focused predominantly on mi-croservices and cloud-native applications.”
SCALER: LLM-Based Cross-Modal Alignment for Microservice Root Cause Analysis
Yang, S., Wang, G., Ming, Z., He, D., Cui, L., Yu, X., & Zhou, X. (2026) · IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws72778.2026.00101
“Representative works, such as Nezha [40], MULAN [10], HeMiRCA [12], and RCRank [13], further demonstrate the effectiveness of multi-modal alignment and causal modeling in microservice systems.”
DCRL: Dynamic Causal Representation Learning for Root Cause Localization in Microservice Systems
Liu, C., Zhang, J., Shi, Y., Liu, S., Zhang, D., Qi, K., & Chen, Z. (2026) · IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws72778.2026.00080
“• HeMiRCA [28] leverages VAE to generate anomaly scores from trace data and performs root cause analysis by exploiting the monotonic correlations between anomaly scores and monitoring metrics.”
Xin, Q. (2026) · JEECS (Journal of Electrical Engineering and Computer Sciences) · doi:10.54732/jeecs.v11i2.3
“HeMiRCA, BARO, and CHASE further show the value of heterogeneous telemetry, robust change detection, and causal heterogeneous graphs [14]–[16].”
Release-Aware Prior-Guided Regex Planning for Token-Bounded Log Retrieval in AIOps
Murugesan, S. B. P. (2026) · International Symposium on Networks, Computers and Communications (ISNCC) · doi:10.1109/isncc70543.2026.11693861
Expanding Guard Reach: Online Learning-Driven Incremental Kernel Panic Diagnosis
Sui, Y., Wang, X., Zhang, H., Zhang, S., Jiang, B., Zheng, H., Sun, Y., Zhang, Y., Zhang, Y., Wu, X., et al. (2026) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1145/3832783.3834474
ARCHITECTURAL AND PROCESS MODELS FOR IT SERVICE QUALITY MANAGEMENT IN MULTI-LEVEL CORPORATE SYSTEMS
Amir, R. (2026) · CyberLeninK (CyberLeninka)
Sun, S., Teng, F., Zheng, D., & Xu, J. (2026) · Journal of Systems and Software · doi:10.1016/j.jss.2026.113166
Metadata
- Authors
- Zhu, Z., Lee, C., Tang, X., & He, P.
- Affiliations
- Chinese University of Hong Kong, Shenzhen (CN)
- Chinese University of Hong Kong (HK)
- Shenzhen Research Institute of Big Data (CN)
- Venue
- ACM Transactions on Software Engineering and Methodology
- Published
- 2024-11-21
- Volume
- 33
- Issue
- 8
- Pages
- 1-25
- ISSN
- 1049-331X (ISSN-L)
- 1557-7392
- OpenAlex
- W4400212265
- Cited by
- 26
- References
- 39
- Citations by year
- 2026: 18 · 2025: 7 · 2024: 1
- FWCI
- 4.34
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- ACM Transactions on Software Engineering and Methodology (publishedVersion)
- Funders
- National Natural Science Foundation of China (62102340)
- Guangdong Basic and Applied Basic Research Foundation (2024A1515010145)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Software System Performance and Reliability
- Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- Physical Sciences › Computer Science › Information Systems › Cloud Computing and Resource Management
- Keywords
- root cause analysis, microservices, anomaly detection, Spearman correlation, system reliability
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.