Attention-driven AI model generalization for workload forecasting in the compute continuum
Effective resource management in edge-cloud networks demands precise forecasting of diverse workload resource usage. Due to the fluctuating nature of user demands, prediction models must have strong generalization abilities, ensuring high performance amidst sudden traffic changes or unfamiliar patte...
| Autores: | , , |
|---|---|
| Tipo de recurso: | artículo |
| Fecha de publicación: | 2025 |
| País: | España |
| Institución: | Universitat Politècnica de Catalunya (UPC) |
| Repositorio: | UPCommons. Portal del coneixement obert de la UPC |
| Idioma: | inglés |
| OAI Identifier: | oai:upcommons.upc.edu:2117/446241 |
| Acceso en línea: | https://hdl.handle.net/2117/446241 https://dx.doi.org/10.1109/TMLCN.2025.3584009 |
| Access Level: | acceso abierto |
| Palabra clave: | Attention mechanisms Deep learning Edge-cloud computing Resource optimization Temporal clustering Time-series transformers Workload prediction Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Telemàtica i xarxes d'ordinadors |
| Sumario: | Effective resource management in edge-cloud networks demands precise forecasting of diverse workload resource usage. Due to the fluctuating nature of user demands, prediction models must have strong generalization abilities, ensuring high performance amidst sudden traffic changes or unfamiliar patterns. Existing approaches often struggle with handling long-term dependencies and the diversity of temporal patterns. This paper introduces OmniFORE (Framework for Optimization of Resource forecasts in Edge-cloud networks), which integrates attention-based time-series models with temporal clustering to enhance generalization and predict diverse workloads efficiently in volatile settings. By training on carefully selected subsets from extensive datasets, OmniFORE captures both short-term stability and long-term shifts in resource usage patterns. Experiments show that OmniFORE outperforms state-of-the-art methods in prediction accuracy, inference speed, and generalization to unseen data, particularly in scenarios with dynamic workload changes and varying trace variance. These improvements enable more efficient resource management in the compute continuum. |
|---|