Mobile traffic forecasting plays a key role for optimizing the configuration of network cells. Network operators are very interested in predicting upcoming mobile traffic peaks in an accurate way, in order to improve quality of service via efficient resource allocation. However, forecasting potential peaks is very challenging considering that many peaks occur suddenly for no apparent reason; hence, it is very difficult to determine if a peak will occur in near future based on the temporal dynamics of mobile traffic, potentially leading to inaccurate predictions. To improve the performance of peak prediction, we propose a novel deep learning model called Mixture of Quantiles (MoQ). MoQ employs a mixture of experts model featuring a manager to fuse the predictions of multiple experts. In order to overcome the problem of overly smooth predictions on peaks, the experts are designed to have differentiated forecasting styles from conservative to aggressive. A cooperation mechanism is established through a carefully designed training process, whereby conservative experts are responsible for the forecasting of the off-peak region, and the employed experts are switched to the aggressive ones once the potential increasing trend is detected by manager, which leads to significantly improved peak predictions. Extensive experiments on real-world dataset showcase the effectiveness of the proposed MoQ model, which outperforms all the benchmarks and shows its superior performance in peak forecasting along with excellent interpretability.

To Be Conservative or To Be Aggressive? A Risk-Adaptive Mixture of Experts for Mobile Traffic Forecasting / Li, Shuyang; Magli, Enrico; Francini, Gianluca. - ELETTRONICO. - (2023), pp. 5471-5476. (Intervento presentato al convegno 2023 International Conference on Communications tenutosi a Roma (Italy) nel 28 May 2023 - 01 June 2023) [10.1109/ICC45041.2023.10279534].

To Be Conservative or To Be Aggressive? A Risk-Adaptive Mixture of Experts for Mobile Traffic Forecasting

Shuyang Li;Enrico Magli;
2023

Abstract

Mobile traffic forecasting plays a key role for optimizing the configuration of network cells. Network operators are very interested in predicting upcoming mobile traffic peaks in an accurate way, in order to improve quality of service via efficient resource allocation. However, forecasting potential peaks is very challenging considering that many peaks occur suddenly for no apparent reason; hence, it is very difficult to determine if a peak will occur in near future based on the temporal dynamics of mobile traffic, potentially leading to inaccurate predictions. To improve the performance of peak prediction, we propose a novel deep learning model called Mixture of Quantiles (MoQ). MoQ employs a mixture of experts model featuring a manager to fuse the predictions of multiple experts. In order to overcome the problem of overly smooth predictions on peaks, the experts are designed to have differentiated forecasting styles from conservative to aggressive. A cooperation mechanism is established through a carefully designed training process, whereby conservative experts are responsible for the forecasting of the off-peak region, and the employed experts are switched to the aggressive ones once the potential increasing trend is detected by manager, which leads to significantly improved peak predictions. Extensive experiments on real-world dataset showcase the effectiveness of the proposed MoQ model, which outperforms all the benchmarks and shows its superior performance in peak forecasting along with excellent interpretability.
File in questo prodotto:
File Dimensione Formato  
ICC 2023_To Be Conservative or To Be Aggressive? A Risk-Adaptive Mixture of Experts for Mobile Traffic Forecasting.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: Pubblico - Tutti i diritti riservati
Dimensione 4.21 MB
Formato Adobe PDF
4.21 MB Adobe PDF Visualizza/Apri
To_be_Conservative_or_to_be_Aggressive_A_Risk-Adaptive_Mixture_of_Experts_for_Mobile_Traffic_Forecasting.pdf

accesso riservato

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 4.27 MB
Formato Adobe PDF
4.27 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2983064