InSlicing: Interpretable Learning-Assisted Network Slice Configuration in Open Radio Access Networks
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912241584963584 |
|---|---|
| author | Zhao, Ming Zhang, Yuru Liu, Qiang Kak, Ahan Choi, Nakjung |
| author_facet | Zhao, Ming Zhang, Yuru Liu, Qiang Kak, Ahan Choi, Nakjung |
| contents | Network slicing is a key technology enabling the flexibility and efficiency of 5G networks, offering customized services for diverse applications. However, existing methods face challenges in adapting to dynamic network environments and lack interpretability in performance models. In this paper, we propose a novel interpretable network slice configuration algorithm (\emph{InSlicing}) in open radio access networks, by integrating Kolmogorov-Arnold Networks (KANs) and hybrid optimization process. On the one hand, we use KANs to approximate and learn the unknown performance function of individual slices, which converts the blackbox optimization problem. On the other hand, we solve the converted problem with a genetic method for global search and incorporate a trust region for gradient-based local refinement. With the extensive evaluation, we show that our proposed algorithm achieves high interpretability while reducing 25+\% operation cost than existing solutions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_15918 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | InSlicing: Interpretable Learning-Assisted Network Slice Configuration in Open Radio Access Networks Zhao, Ming Zhang, Yuru Liu, Qiang Kak, Ahan Choi, Nakjung Networking and Internet Architecture Network slicing is a key technology enabling the flexibility and efficiency of 5G networks, offering customized services for diverse applications. However, existing methods face challenges in adapting to dynamic network environments and lack interpretability in performance models. In this paper, we propose a novel interpretable network slice configuration algorithm (\emph{InSlicing}) in open radio access networks, by integrating Kolmogorov-Arnold Networks (KANs) and hybrid optimization process. On the one hand, we use KANs to approximate and learn the unknown performance function of individual slices, which converts the blackbox optimization problem. On the other hand, we solve the converted problem with a genetic method for global search and incorporate a trust region for gradient-based local refinement. With the extensive evaluation, we show that our proposed algorithm achieves high interpretability while reducing 25+\% operation cost than existing solutions. |
| title | InSlicing: Interpretable Learning-Assisted Network Slice Configuration in Open Radio Access Networks |
| topic | Networking and Internet Architecture |
| url | https://arxiv.org/abs/2502.15918 |