한국정보처리학회:학술대회논문집 (Annual Conference of KIPS)

한국정보처리학회 (Korea Information Processing Society)
권호 표지

TSANTP: 공간 코딩 주의 메커니즘을 통합한 새로운 네트워크 트래픽 예측 모델

TSANTP: A Novel Network Traffic Prediction Model Integrating Space Coding and Attention Mechanisms

  • 이용비 (전남대학교 인공지능융합학과 ) ;
  • 김경백 (전남대학교 인공지능융합학과 )
  • LongFei Li (Dept. of Artificial Intelligence Convergence, Chonnam National University) ;
  • Kyungbaek Kim (Dept. of Artificial Intelligence Convergence, Chonnam National University)
  • 발행 : 2024.10.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

With the widespread application of 5G technology, network traffic has increased unprecedentedly, which has a significant impact on network traffic management. Traditional network traffic prediction methods rely on time series analysis of seasonal patterns, ignoring the inherent spatial correlation of network traffic. Graph convolutional networks (GCN) learn spatial correlations. By combining GCN with time series models, spatiotemporal features can be captured simultaneously, thereby improving prediction accuracy. This paper introduces a new network traffic prediction model TSA-NTP based on the attention mechanism, which aims to more effectively capture spatiotemporal features in complex network environments.

키워드

과제정보

This work was supported by Innovative Human Resource Development for Local Intellectualization program through the Institute of Information & Communications Technology Planning & Evaluation(IITP) grant funded by the Korea government(MSIT)(IITP-2024-RS-2022-00156287, 50%). This work was supported by Institute of Information & communications Technology Planning & Evaluation (IITP) under the Artificial Intelligence Convergence Innovation Human Resources Development (IITP-2023-RS-2023-00256629, 50%) grant funded by the Korea government(MSIT).

참고문헌

  1. Joshi M, Hadi T H. A review of network traffic analysis and prediction techniques[J]. arXiv preprint arXiv:1507.05722, 2015. 
  2. Li L, Kim K. GTT-NTP: A Graph Convolutional Networks-Based Network Traffic Prediction model[C]//NOMS 2024-2024 IEEE Network Operations and Management Symposium. IEEE, 2024: 1-7. 
  3. Mukherjee S, Ray R, Samanta R, et al. Nonlinearity and chaos in wireless network traffic[J]. Chaos, Solitons & Fractals, 2017, 96: 23-29. 
  4. Lazaris A, Prasanna V K. Deep learning models for aggregated network traffic prediction[C]//2019 15th International Conference on Network and Service Management (CNSM). IEEE, 2019: 1-5. 
  5. Yeom S, Choi C, Kolekar S S, et al. Graph convolutional network based link state prediction[C]//2021 22nd Asia-Pacific Network Operations and Management Symposium (APNOMS). IEEE, 2021: 246-249. 
  6. Zhou J, Cui G, Hu S, et al. Graph neural networks: A review of methods and applications[J]. AI open, 2020, 1: 57-81. 
  7. Vaswani A. Attention is all you need[J]. Advances in Neural Information Processing Systems, 2017. 
  8. Yu B, Yin H, Zhu Z. Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting[J]. arXiv preprint arXiv:1709.04875, 2017. 
  9. Zhao L, Song Y, Zhang C, et al. T-GCN: A temporal graph convolutional network for traffic prediction[J]. IEEE transactions on intelligent transportation systems, 2019, 21(9): 3848-3858.