Deep Learning for Telecom Self-Optimized Networks: Benefits and Implications

被引:0
|
作者
Alhaqui, Farah [1 ]
Lahsen-Cherif, Iyad [1 ]
Elkhechafi, Mariam [2 ]
Elkhadimi, Ahmed [1 ]
机构
[1] INPT, AGNOX Lab, Rabat 10000, Morocco
[2] ISCAE, SID Dept, LAREM Lab, Casablanca 8114, Morocco
来源
IEEE ACCESS | 2024年 / 12卷
关键词
Predictive models; Telecommunications; Long short term memory; Convolutional neural networks; Deep learning; 5G mobile communication; Recurrent neural networks; Prediction algorithms; Telecommunication traffic; Hands; self optimized networks; traffic prediction; recurrent neural networks; long-short-term memory; gated recurrent unit; CELLULAR TRAFFIC PREDICTION; NEURAL-NETWORK; FRAMEWORK;
D O I
10.1109/ACCESS.2024.3521282
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Self-Optimized networks (SON) have emerged as a pivotal solution for telecom operators to automate their networks' implementation, configuration and resources optimization based on network's own intelligence. Among the challenges tackled by SON, traffic prediction stands out as a critical endeavor allowing dynamic and optimal resource allocation in the short term and giving a clearer visibility about network's future needs in terms of capacity and energy on the long run. However, most existing studies rely on highly complex models with low interpretability, resulting in inefficient solutions with substantial implementation and computational costs. This makes them unsuitable for real-world scenarios, where simplicity, transparency, and adaptability to dynamic conditions are critical for practical deployment. This study introduces an efficient traffic prediction approach that combines an innovative data partitioning strategy to capture spatial dependencies with Long Short-Term Memory (LSTM) networks to model temporal patterns. Leveraging real traffic data from a leading Moroccan telecom operator, the proposed model accurately forecasts future traffic patterns and their geographic distribution, achieving an absolute prediction error of less than 15 GB. These high-precision forecasts significantly improved network awareness, enabling the deployment of energy optimization strategies that reduced energy consumption across 1,100 base stations by an average of 11% per station.
引用
收藏
页码:195422 / 195435
页数:14
相关论文
共 50 条
  • [31] Self-optimized metal coatings for fiber plasmonics by electroless deposition
    Bialiayeu, A.
    Caucheteur, C.
    Ahamad, N.
    Ianoul, A.
    Albert, J.
    OPTICS EXPRESS, 2011, 19 (20): : 18742 - 18753
  • [32] SOPM - A SELF-OPTIMIZED METHOD FOR PROTEIN SECONDARY STRUCTURE PREDICTION
    GEOURJON, C
    DELEAGE, G
    PROTEIN ENGINEERING, 1994, 7 (02): : 157 - 164
  • [33] MIIPSO-EFS: Learning system with self-optimized parameters for chaotic time series online prediction
    Hu, Lei
    Xu, Xinghan
    Liu, Jianwei
    Yan, Xiaohui
    Han, Min
    KNOWLEDGE-BASED SYSTEMS, 2025, 310
  • [34] DNN-BASED SOURCE ENHANCEMENT SELF-OPTIMIZED BY REINFORCEMENT LEARNING USING SOUND QUALITY MEASUREMENTS
    Koizumi, Yuma
    Niwa, Kenta
    Hioka, Yusuke
    Kobayashi, Kazunori
    Haneda, Yoichi
    2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2017, : 81 - 85
  • [35] Self-Optimized Agent for Load Balancing and Energy Efficiency: A Reinforcement Learning Framework With Hybrid Action Space
    Attia, Bishoy Salama
    Elgharably, Aamen
    Aboelwafa, Mariam Nabil
    Alsuhli, Ghada
    Banawan, Karim
    Seddik, Karim G.
    IEEE OPEN JOURNAL OF THE COMMUNICATIONS SOCIETY, 2024, 5 : 4902 - 4919
  • [36] Optimized deep networks structure to improve the accuracy of estimator algorithm in deep networks learning
    Nezhad, H. Rezaei
    Keynia, F.
    Molahosseini, A. Sabbagh
    SCIENTIA IRANICA, 2024, 31 (05) : 417 - 429
  • [37] An efficient self-optimized sampling method for rare events in nonequilibrium systems
    JIANG HuiJun
    PU MingFeng
    HOU ZhongHuai
    Science China(Chemistry), 2014, (01) : 165 - 171
  • [38] SOCS: A Self-Optimized Coverage Scheme For Femto-Enterprise Deployment
    Mhiri, Fadoua
    Sethom, Kaouthar
    Bouallegue, Ridha
    Pujolle, Guy
    2011 IFIP WIRELESS DAYS (WD), 2011,
  • [39] An efficient self-optimized sampling method for rare events in nonequilibrium systems
    HuiJun Jiang
    MingFeng Pu
    ZhongHuai Hou
    Science China Chemistry, 2014, 57 : 165 - 171
  • [40] Model Predictive Control for the Self-optimized Operation in Wastewater Treatment Plants
    Francisco, Mario
    Skogestad, Sigurd
    Vega, Pastora
    12TH INTERNATIONAL SYMPOSIUM ON PROCESS SYSTEMS ENGINEERING (PSE) AND 25TH EUROPEAN SYMPOSIUM ON COMPUTER AIDED PROCESS ENGINEERING (ESCAPE), PT B, 2015, 37 : 1703 - 1708