Mostrar el registro sencillo del ítem

Domain Adaptation for CI/CD Workload Prediction: Transferring Seasonality Patterns Across Non-Overlapping Time Windows

dc.creatorEscobar-Naranjo, Juan Camiloen
dc.creatorDuque-Mendez, Nestor Daríoen
dc.date2026-07-31
dc.date.accessioned2026-08-03T16:43:33Z
dc.date.available2026-08-03T16:43:33Z
dc.identifierhttps://imjeta.org/index.php/IMJETA/article/view/Domain-Adaptation-for-CI_CD_Workload_Prediction
dc.identifier10.67294/7zhrs226
dc.identifier.urihttp://bdigital2.ula.ve:8080/xmlui/654321/26942
dc.descriptionMachine learning models for workload prediction typically require training data from the same time period as deployment. In CI/CD environments, obtaining representative real-world training data is often difficult due to privacy concerns, data availability constraints, or the need to predict for newly established infrastructure. This paper presents a transfer learning methodology that enables transferring seasonality patterns and workload characteristics from real billing data collected during one-time period to real workflow execution logs from a completely non-overlapping period. The article approach combines two techniques: (1) Quantile Mapping to align duration distributions between the target- and source-domain data, preserving structural characteristics (shape, variability, skewness), and (2) Cross-Temporal Seasonality Transfer to map weekly activity patterns across time windows. Validated on GitHub Actions data spanning two distinct quarters (January-April 2023 billing data transferred to June-October 2023 real execution logs), our method achieved a strong correlation (r=0.8739, p=0.0101) for weekly patterns, explaining 76.4% of the variance in seasonality (R2=0.764), and aligned the duration distribution, reducing the CV error from 0.26 to 0.01, skewness from 1.06 to 0.03, and kurtosis from 2.33 to 0.07 relative to the source domain – all without overlapping temporal coverage between the two data sources.en
dc.formatapplication/pdf
dc.languageen
dc.publisherGrupo Afronta C.A.en
dc.relationhttps://imjeta.org/index.php/IMJETA/article/view/Domain-Adaptation-for-CI_CD_Workload_Prediction/24
dc.rightsCopyright (c) 2026 Juan Camilo Escobar-Naranjo, Nestor Darío Duque-Mendez (Author)en
dc.rightshttps://creativecommons.org/licenses/by-nc-nd/4.0en
dc.sourceInternational Multidisciplinary Journal of Emerging Technologies and Applications; Vol. 1 No. 4 (2026); 50-67en
dc.source3135-6214
dc.subjectTransfer Learningen
dc.subjectDomain Adaptationen
dc.subjectWorkload Predictionen
dc.subjectSeasonality Patternsen
dc.subjectContinuous Integrationen
dc.titleDomain Adaptation for CI/CD Workload Prediction: Transferring Seasonality Patterns Across Non-Overlapping Time Windowsen
dc.typeinfo:eu-repo/semantics/article
dc.typeinfo:eu-repo/semantics/publishedVersion


Ficheros en el ítem

FicherosTamañoFormatoVer

No hay ficheros asociados a este ítem.

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem