Mobile traffic forecasting is crucial for optimizing the network configuration and improving Quality-of-Service (QoS); accurate mobile traffic predictions can help the network operators better configure the network and adapt to the trend of mobile demand. However, improving mobile traffic forecasting is challenging as traffic patterns exhibit strong periodicity while also retaining a certain level of randomness; this makes it difficult to model the sequence correlation. To obtain better mobile traffic predictions, we proposed a deep learning-based predictor called Temporal Dynamics Aware Network (TDANet). TDANet is carefully designed to extract both the global and the local temporal patterns employing recurrent and attention components; a linear module is employed to make the predictions more sensitive to the magnitude of mobile traffic, which makes the model better able to capture fast dynamics. Extensive experiments are conducted on a real-world mobile traffic dataset, and the results show that TDANet outperforms all the baseline models on all evaluation metrics, including both accuracy and complexity.

TDANet: an efficient solution for short-term mobile traffic forecasting / Li, Shuyang; Magli, Enrico; Francini, Gianluca. - ELETTRONICO. - (2023), pp. 1-5. (Intervento presentato al convegno 2023 IEEE 97th Vehicular Technology Conference (VTC2023-Spring) tenutosi a Florence (Italy) nel 20-23 June 2023) [10.1109/VTC2023-Spring57618.2023.10199607].

TDANet: an efficient solution for short-term mobile traffic forecasting

Li, Shuyang;Magli, Enrico;
2023

Abstract

Mobile traffic forecasting is crucial for optimizing the network configuration and improving Quality-of-Service (QoS); accurate mobile traffic predictions can help the network operators better configure the network and adapt to the trend of mobile demand. However, improving mobile traffic forecasting is challenging as traffic patterns exhibit strong periodicity while also retaining a certain level of randomness; this makes it difficult to model the sequence correlation. To obtain better mobile traffic predictions, we proposed a deep learning-based predictor called Temporal Dynamics Aware Network (TDANet). TDANet is carefully designed to extract both the global and the local temporal patterns employing recurrent and attention components; a linear module is employed to make the predictions more sensitive to the magnitude of mobile traffic, which makes the model better able to capture fast dynamics. Extensive experiments are conducted on a real-world mobile traffic dataset, and the results show that TDANet outperforms all the baseline models on all evaluation metrics, including both accuracy and complexity.
2023
979-8-3503-1114-3
File in questo prodotto:
File Dimensione Formato  
TDANet_An_Efficient_Solution_For_Short-Term_Mobile_Traffic_Forecasting.pdf

accesso riservato

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 1.56 MB
Formato Adobe PDF
1.56 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
VTC2023_TDANet, An Efficient Solution For Short-Term Mobile Traffic Forecasting.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: Pubblico - Tutti i diritti riservati
Dimensione 841.93 kB
Formato Adobe PDF
841.93 kB Adobe PDF Visualizza/Apri
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/11583/2981146