Bahdanau Attention based LSTM for Wireless Network Traffic Prediction

  • Unique Paper ID: 208610
  • Volume: 13
  • Issue: 4
  • PageNo: 2213-2220
  • Abstract:
  • Wireless networks and data intensive applications continue to grow at a fast pace, and there is a critical need for accurate traffic predictions so that resources can be allocated efficiently, traffic congestion can be controlled and Quality of Service (QOS) can be managed [1]. Traditional Long Short-Term Memory (LSTM)s can learn temporal dependence, but there is no explicit identification of important time steps in the past [2]. In this study, a new Bahdanau Attention-LSTM model is proposed for predict the wireless network traffic by combining the temporal feature extraction module with the attention mechanism [3]. The attention mechanism weights the historical hidden state so that it can concentrate on informative traffic patterns [3]. The performance is compared with that of a conventional LSTM. The models are assessed with the following statistics: Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), Symmetric Mean Absolute Percentage Error (SMAPE), Coefficient of Determination ("R" ^2Score), Nash-Sutcliffe Efficiency (NSE) and Theil's U [1]. This is shown in result for the effectiveness of the proposed model in better prediction accuracy and proactive network management, resource optimization, and congestion mitigation [3].

Copyright & License

Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

BibTeX

@article{208610,
        author = {MEENIGE PAVANI PRATHYUSHA},
        title = {Bahdanau Attention based LSTM for Wireless Network Traffic Prediction},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {4},
        pages = {2213-2220},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=208610},
        abstract = {Wireless networks and data intensive applications continue to grow at a fast pace, and there is a critical need for accurate traffic predictions so that resources can be allocated efficiently, traffic congestion can be controlled and Quality of Service (QOS) can be managed [1]. Traditional Long Short-Term Memory (LSTM)s can learn temporal dependence, but there is no explicit identification of important time steps in the past [2]. In this study, a new Bahdanau Attention-LSTM model is proposed for predict the wireless network traffic by combining the temporal feature extraction module with the attention mechanism [3]. The attention mechanism weights the historical hidden state so that it can concentrate on informative traffic patterns [3]. The performance is compared with that of a conventional LSTM. The models are assessed with the following statistics: Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), Symmetric Mean Absolute Percentage Error (SMAPE), Coefficient of Determination ("R" ^2Score), Nash-Sutcliffe Efficiency (NSE) and Theil's U [1]. This is shown in result for the effectiveness of the proposed model in better prediction accuracy and proactive network management, resource optimization, and congestion mitigation [3].},
        keywords = {Wireless Network Traffic, LSTM, Bahdanau Attention, Time-Series Forecasting, Deep Learning, Traffic Prediction, Network Management.},
        month = {September},
        }

Cite This Article

PRATHYUSHA, M. P. (2026). Bahdanau Attention based LSTM for Wireless Network Traffic Prediction. International Journal of Innovative Research in Technology (IJIRT). https://doi.org/doi.org/10.64643/IJIRT208610

Related Articles