Keywords
dependency-aware scoring
telemetry delay
paired simulation
reproducibility
Abstract
We evaluated dependency-aware scoring for microservice anomaly detection under 27% telemetry delay. A deterministic paired simulation generated 56 cases and preserved a rare-condition slice. Mean early-warning F1 changed from 0.501 to 0.544; the paired difference was +0.043 (95% interval +0.041 to +0.045). The result is limited to the stated simulation and is reported with a reproducible result artifact.
References
Zhang, Z., Liu, W., Tao, J., Zhu, H., Li, S., & Xiao, Y. (2025). Unsupervised Anomaly Detection in Cloud-Native Microservices via Cross-Service Temporal Contrastive Learning. 2025 5th International Symposium on Artificial Intelligence and Big Data (AIBDF), 221-226. https://doi.org/10.1109/aibdf67964.2025.11440805
Goli, S. R. (2025). Enhancing SRE with AI: Predictive Maintenance and Anomaly Detection in Distributed Cloud Services. https://doi.org/10.2139/ssrn.5741522
Islam, M. S. (2023). Anomaly Detection in Cloud Components. https://doi.org/10.32920/23296241.v1
Zhussupov, Y., Zhumadillayeva, A., Shinassylov, S., & Amirtayeva, A. (2026). COMPARATIVE ANALYSIS OF SEQUENCE-BASED AND GRAPH-BASED DEEP LEARNING FOR ANOMALY DETECTION IN MICROSERVICE TRACES. Journal of Problems in Computer Science and Information Technologies, 4(2). https://doi.org/10.26577/jpcsit4220265
Idamakanti, P. K. (2025). Cloud Network Anomaly Detection using Federated Learning and Explainable AI. International Journal on Science and Technology, 16(3), 7336. https://doi.org/10.71097/ijsat.v16.i3.7336
Marnerides, A. K. (2015). Anomaly Detection in Cloud Environments. Advances in Systems Analysis, Software Engineering, and High Performance Computing, 43-67. https://doi.org/10.4018/978-1-4666-8225-2.ch003
Jazib, M., & Anees, M. H. (2026). FinOps-AIOps Fusion: Cost-Aware Anomaly Attribution for Microservice-Based Cloud Systems. International Journal of Innovations in Science and Technology, 418. https://doi.org/10.33411/ijist/1796
Cao, W., Cao, Z., & Zhang, X. (2019). Research on Microservice Anomaly Detection Technology Based on Conditional Random Field. Journal of Physics: Conference Series, 1213(4), 042016. https://doi.org/10.1088/1742-6596/1213/4/042016
Liu, X., Zhu, S., Yang, F., & Liang, S. (2022). Research on unsupervised anomaly data detection method based on improved automatic encoder and Gaussian mixture model. Journal of Cloud Computing, 11(1), 58. https://doi.org/10.1186/s13677-022-00328-z
Detti, A., & Favale, A. (2025). Cost-Effective Cloud-Edge Elasticity for Microservice Applications. https://doi.org/10.36227/techrxiv.173626716.63354758/v1