Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Artificial intelligence enabled behavior modeling and dual-task performance analysis of cloud-native software with

Fan Xu1, Wenjie Jiang2

  • 1School of Electrical, Electronic and Mechanical Engineering, University of Bristol, BS8 1QU, Bristol, England. xufanuk2026@outlook.com.

Scientific Reports
|July 14, 2026
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Epidemiological and clinical features of hypertrophic scar and keloid in Chinese college students: A university-based cross-sectional survey.

Heliyon·2023
Same author

Five new terpenoids from Viburnum odoratissimum var. sessiliflorum.

Chinese journal of natural medicines·2023
Same author

Characterization of a Riboflavin-Producing Mutant of <i>Bacillus subtilis</i> Isolated by Droplet-Based Microfluidics Screening.

Microorganisms·2023
Same author

Neuroprotection of SRT2104 in Murine Ischemia/Reperfusion Injury Through the Enhancement of Sirt1-Mediated Deacetylation.

Investigative ophthalmology & visual science·2023
Same author

SIRT6 ameliorates LPS-induced apoptosis and tight junction injury in ARDS through the ERK1/2 pathway and autophagy.

International journal of medical sciences·2023
Same author

Deep learning-based diagnosis of osteoblastic bone metastases and bone islands in computed tomograph images: a multicenter diagnostic study.

European radiology·2023

This study introduces the Multi-Modal and Multi-Scale Temporal Propagation (M[Formula: see text]TP) model for cloud-native microservice systems. It enhances performance prediction and bottleneck localization by integrating diverse data sources and improving efficiency.

Area of Science:

  • Cloud computing and distributed systems
  • Artificial intelligence and machine learning
  • Data science and analytics

Background:

  • Cloud-native microservice systems generate heterogeneous multi-source data (logs, metrics, call-chains).
  • Existing models struggle with collaborative modeling of temporal and topological features.
  • Dual-task optimization for performance prediction and bottleneck localization is often inefficient.

Purpose of the Study:

  • To propose an efficient model for performance prediction and bottleneck localization in microservice systems.
  • To address challenges of heterogeneous data and inadequate feature modeling.
  • To enhance AIOps capabilities for proactive monitoring and fault diagnosis.

Main Methods:

  • Developed a Multi-Modal and Multi-Scale Temporal Propagation (M[Formula: see text]TP) model.
Keywords:
Behavior modelingBottleneck localizationCloud-native softwareDeep learningMulti-source heterogeneous dataPerformance prediction

Related Experiment Videos

  • Utilized a Multi-modal Heterogeneous Embedding Module for unified data representation.
  • Employed Temporal-Graph Joint Learning and Dual-Task Collaborative Decoding for integrated analysis.

    • Main Results:

    • Achieved high scores: 0.95-0.96 for performance prediction and 0.93-0.94 F1 for bottleneck localization.
    • Demonstrated low inference latencies (6.5-7.1ms), outperforming 8 baseline models.
    • Ablation studies and case studies confirmed component effectiveness and accurate root-cause identification.

    Conclusions:

    • The M[Formula: see text]TP model effectively handles heterogeneous data and complex system dynamics.
    • It provides a robust technical foundation for cloud-native AIOps, enabling proactive monitoring.
    • The model significantly improves efficiency and accuracy in performance prediction and fault diagnosis.