MétaCan
Menu
Back to cohort

Leveraging Large Language Models for Auto-remediation in Microservices Architecture

2023· article· en· W4389576384 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicSoftware System Performance and Reliability
Canadian institutionsYork University
Fundersnot available
KeywordsMicroservicesComputer scienceTroubleshootingScalabilitySoftware deploymentSoftware engineeringCorrectnessCloud computingOperating systemProgramming language

Abstract

fetched live from OpenAlex

Microservices architecture is popular due to its scalability and flexibility. However, managing and troubleshooting distributed microservices-based systems can be challenging and time consuming. Auto-remediation of anomalies, that is the automated detection and root-causes generation and execution of repair scripts, can reduce the down-times and increase the availability of systems. This thesis will explore the potential and effectiveness of using large language models (LLMs) in auto-remediation. It will develop an auto-remediation framework to mitigate the effects of performance-based anomalies in self-adaptive microservice architectures. Multiple sample microservice applications as test-bed will be rigorously studied, and a dataset will be created to evaluate LLM-based codegeneration models using semantic, lexical, and correctness metrics in zero-shot and few-shot scenarios. Additionally, we will develop reliable prompts for automated Ansible runbook generation and assess their efficiency for orchestrating the auto-remediation process, including deployment, configuration changes, and system recovery to improve application reliability and operational efficiency.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.759
Threshold uncertainty score0.248

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.015
GPT teacher head0.263
Teacher spread0.248 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it