Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2509.15072 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914045993418752 |
|---|---|
| author | Cash, Martha Wyglinski, Alexander |
| author_facet | Cash, Martha Wyglinski, Alexander |
| contents | We present a novel framework that leverages time series clustering to improve internet traffic matrix (TM) prediction using deep learning (DL) models. Traffic flows within a TM often exhibit diverse temporal behaviors, which can hinder prediction accuracy when training a single model across all flows. To address this, we propose two clustering strategies, source clustering and histogram clustering, that group flows with similar temporal patterns prior to model training. Clustering creates more homogeneous data subsets, enabling models to capture underlying patterns more effectively and generalize better than global prediction approaches that fit a single model to the entire TM. Compared to existing TM prediction methods, our method reduces RMSE by up to 92\% for Abilene and 75\% for GÉANT. In routing scenarios, our clustered predictions also reduce maximum link utilization (MLU) bias by 18\% and 21\%, respectively, demonstrating the practical benefits of clustering when TMs are used for network optimization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_15072 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Improving Internet Traffic Matrix Prediction via Time Series Clustering Cash, Martha Wyglinski, Alexander Machine Learning We present a novel framework that leverages time series clustering to improve internet traffic matrix (TM) prediction using deep learning (DL) models. Traffic flows within a TM often exhibit diverse temporal behaviors, which can hinder prediction accuracy when training a single model across all flows. To address this, we propose two clustering strategies, source clustering and histogram clustering, that group flows with similar temporal patterns prior to model training. Clustering creates more homogeneous data subsets, enabling models to capture underlying patterns more effectively and generalize better than global prediction approaches that fit a single model to the entire TM. Compared to existing TM prediction methods, our method reduces RMSE by up to 92\% for Abilene and 75\% for GÉANT. In routing scenarios, our clustered predictions also reduce maximum link utilization (MLU) bias by 18\% and 21\%, respectively, demonstrating the practical benefits of clustering when TMs are used for network optimization. |
| title | Improving Internet Traffic Matrix Prediction via Time Series Clustering |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.15072 |