Comparative Analysis of the Features of a 5G Network Production Dataset: The Machine Learning Approach



Abstract Views
176

Downloads
258

Citations

Share

##plugins.themes.bootstrap3.article.sidebar##

Submitted Feb 6, 2023
Published Apr 2, 2023
10.24018/ejeng.2023.8.2.2994

Abstract viewed = 176 times

Table of Contents

##plugins.themes.bootstrap3.article.main##

5G networks deployment is much data driven, leading to more energy consumption. The need to efficiently manage this energy consumption is a major drive in the comparative analysis of the features of a 5G production dataset. The features of the 5G production dataset generated with G-Net track pro were analyzed using Python programming language. From the correlation coefficient results obtained, the highest correlation value of 0.78 exists between the reference signal power and the received signal reference power of the neighbouring cells. Using the significant indicator, we observed that the signal to noise ratio is the most important of all the features. Using heat map and scatter plots, we further observed that there were good relationships between the key features selected from the significant indicator. These features will play a big role in improving the energy efficiency of a 5G network.

Keywords: 5G Artificial Intelligence Dataset Machine Learning

Downloads

Download data is not yet available.

References

  1. Yadav R. Challenges and evolution of next generations wireless communication. In Proc. Int. MultiConf. Eng. Comput. Scientists, 2017; 2: 619-623.
     Google Scholar
  2. Panwar N, Sharma S, Singh AK. A survey on 5G: The next generation of mobile communication. Phys. Commun. 2016; 18: 64-84.
    DOI  |   Google Scholar
  3. Ericsson mobility report. [Internet] Retrieved from: https://www.ericsson.com/49da93/assets/local/mobility-report/documents/2020/june2020-ericsson-mobility-report.pdf.
     Google Scholar
  4. DEEPSIG. Howartificialintelligenceimproves5G wireless capabilities. [Internet] Retrieve from: https://www.deepsig.ai/how-artificial-intelligence-improves-5g-wireless-capabilities.
     Google Scholar
  5. Johnson DD. The 5G dilemma: more base stations, more antennas-less energy?[Internet] Retrieve from: https://spectrum.ieee.org/energywise/telecom/wireless/will-increased-energy-consumption-be-the-achilles-heals-of-5g-networks 2018.
     Google Scholar
  6. Rajoria S, Trivedi A, Godfrey WW. A comprehensive survey: small cells meet massive MIMO. Phys. Commun. 2018; 26: 40-49.
    DOI  |   Google Scholar
  7. Haidine A, Salman FZ, Aqqal A, Dahbi A. Artificial Intelligence and Machine Learning in 5G and beyond: A Survey and Perspectives. Moving broadband mobile communication forward intelligent technologies for 5G and beyond. 2021. DOI: 10.5772/intechopen.98517.
    DOI  |   Google Scholar
  8. Raca D, Leahy D, Sreenan CJ, Quinlan JJ. Beyond throughput, the next generation: A 5G dataset with channel and context metrics. ACM Multimedia Systems Conference (MMSys), 2020, Instanbul, Turkey.
    DOI  |   Google Scholar
  9. Fonseca A, Kazman R, Lago P. A Manifesto for Energy-Aware Software. IEEE Software, 2019; 36(6): 79–82. https://doi.org/10.1109/ms.2019.2924498.
    DOI  |   Google Scholar
  10. Bjornson E, Kountouris M, Debbah M. Massive MIMO and small cells: Improving energy efficiency by optimal soft-cell coordination. ICT 2013, 2013. https://doi.org/10.1109/ictel.2013.6632074.
    DOI  |   Google Scholar
  11. Bjornson E, Sanguinetti L, Hoydis J, Debbah M. Optimal Design of Energy-Efficient Multi-User MIMO Systems: Is Massive MIMO the answer? IEEE Transactions on Wireless Communications,2015; 14(6): 3059-3075. https://arXiv.org/pdf/1403.6150v2.
    DOI  |   Google Scholar