Lightweight Latency Prediction Scheme for Edge Applications: A Rational Modelling Approach
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917059585114112 |
|---|---|
| author | Liyanage, Mohan Zhantileuov, Eldiyar Idrees, Ali Kadhum Schuster, Rolf |
| author_facet | Liyanage, Mohan Zhantileuov, Eldiyar Idrees, Ali Kadhum Schuster, Rolf |
| contents | Accurately predicting end-to-end network latency is essential for enabling reliable task offloading in real-time edge computing applications. This paper introduces a lightweight latency prediction scheme based on rational modelling that uses features such as frame size, arrival rate, and link utilization, eliminating the need for intrusive active probing. The model achieves state-of-the-art prediction accuracy through extensive experiments and 5-fold cross-validation (MAE = 0.0115, R$^2$ = 0.9847) with competitive inference time, offering a substantial trade-off between precision and efficiency compared to traditional regressors and neural networks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_02501 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Lightweight Latency Prediction Scheme for Edge Applications: A Rational Modelling Approach Liyanage, Mohan Zhantileuov, Eldiyar Idrees, Ali Kadhum Schuster, Rolf Networking and Internet Architecture Distributed, Parallel, and Cluster Computing Accurately predicting end-to-end network latency is essential for enabling reliable task offloading in real-time edge computing applications. This paper introduces a lightweight latency prediction scheme based on rational modelling that uses features such as frame size, arrival rate, and link utilization, eliminating the need for intrusive active probing. The model achieves state-of-the-art prediction accuracy through extensive experiments and 5-fold cross-validation (MAE = 0.0115, R$^2$ = 0.9847) with competitive inference time, offering a substantial trade-off between precision and efficiency compared to traditional regressors and neural networks. |
| title | Lightweight Latency Prediction Scheme for Edge Applications: A Rational Modelling Approach |
| topic | Networking and Internet Architecture Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2511.02501 |