Analisis Prediksi Hotspot Berbasis Convolutional Neural Network (CNN) Untuk Virtual Small Cell (VSC)
Abstract
Pengelolaan trafik pada area dengan kepadatan pengguna tinggi menjadi salah satu tantangan dalam jaringan 5G. Salah satu pendekatan yang digunakan untuk mengatasi hal ini adalah penerapan Virtual Small Cell (VSC), yang memungkinkan pembentukan cell virtual secara dinamis tanpa infrastruktur fisik tambahan. Dalam penelitian ini, VSC dikombinasikan dengan teknik beamforming untuk mengarahkan sinyal ke area-area potensial (hotspot) secara lebih efisien. Kanal adaptif diterapkan guna menyesuaikan parameter transmisi terhadap kondisi kanal yang berubah secara real-time. Untuk memaksimalkan efektivitas strategi ini digunakan metode prediksi pergerakan pengguna berdasarkan data heatmap jaringan. Convolutional Neural Network (CNN) dipilih karena kemampuannya dalam mengekstraksi pola spasial dan temporal dari data trafik, sehingga mampu memetakan dan memprediksi distribusi pengguna secara akurat. Hasil eksperimen menunjukkan bahwa model CNN-GRU yang dilatih hingga 500 epoch mampu menghasilkan prediksi SINR, RSSI, dan efisiensi bandwidth dengan deviasi kecil terhadap data aktual. Rata-rata selisih masing-masing parameter adalah 3,6 dB untuk SINR, 0,16 dBm untuk RSSI, dan 1,08 bps/Hz untuk efisiensi bandwidth. Temuan ini menunjukkan bahwa CNN dapat digunakan secara efektif dalam sistem prediksi kanal untuk mendukung penerapan beamforming adaptif pada VSC. Kata kunci— Virtual Small Cell, Hotspot Prediction, 5G, Beamforming, Convolutional Neural Network (CNN)
References
[1] Y. Liu, X. Wang, G. Boudreau, A. Bin Sediq, and H. Abou-Zeid, “Deep Learning Based Hotspot Prediction and Beam Management for Adaptive Virtual Small Cell in 5G Networks,” IEEE Trans Emerg Top Comput Intell, vol. 4, pp. 83–94, Feb. 2020, doi: 10.1109/TETCI.2019.2926769.
[2] A. Ö. Kaya and H. Viswanathan, “Deep learning-based predictive beam management for 5G mmWave systems,” in IEEE Wireless Communications and Networking Conference, WCNC, Institute of Electrical and Electronics Engineers Inc., 2021. doi: 10.1109/WCNC49053.2021.9417452.
[3] Ieee, “Secure MSC Coverage zone NC Cooperative user MSC Coverage zone LTE Fronthaul Coverage zone MRN NR Coverage zone MSC Coverage zone LTE SC MCN BBU pool BBU pool BBU pool.”
[4] E. Zhang, T. Harada, and R. Thawonmas, “Using Graph Convolution Network for Predicting Performance of Automatically Generated Convolution Neural Networks,” 2019.
[5] A. R. Taufiqurrahman and I. Palupi, “Forest Fire Hotspot Prediction Model Using GAF CNN-LSTM.”
[6] F. Kurniawan, S. Sulaiman, S. Konate, and M. A. A. Abdalla, “Deep learning approaches for MIMO time-series analysis,” International Journal of Advances in Intelligent Informatics, vol. 9, no. 2, pp. 286–300, Jul. 2023, doi: 10.26555/ijain.v9i2.1092.
[7] Y. Li, Q. Xu, W. Li, and J. Nie, “Automatic Clustering-Based Two-Branch CNN for Hyperspectral Image Classification,” IEEE Transactions on Geoscience and Remote Sensing, vol. 59, no. 9, pp. 7803–7816, Sep. 2021, doi: 10.1109/TGRS.2020.3038425.
[8] J. Li et al., “Cluster-Based 3-D Channel Modeling for Massive MIMO in Subway Station Environment,” IEEE Access, vol. 6, pp. 6257–6272, 2018, doi: 10.1109/ACCESS.2017.2779119.
[9] H. Al Kassir, Z. D. Zaharis, P. I. Lazaridis, N. V. Kantartzis, T. V. Yioultsis, and T. D. Xenos, “A Review of the State of the Art and Future Challenges of Deep Learning-Based Beamforming,” 2022, Institute of Electrical and Electronics Engineers Inc. doi: 10.1109/ACCESS.2022.3195299.
[10] H. Huang, Y. Peng, J. Yang, W. Xia, and G. Gui, “Fast Beamforming Design via Deep Learning,” IEEE Trans Veh Technol, vol. 69, no. 1, pp. 1065–1069, Jan. 2020, doi: 10.1109/TVT.2019.2949122.
[11] A. Shrestha and A. Mahmood, “Review of deep learning algorithms and architectures,” 2019, Institute of Electrical and Electronics Engineers Inc. doi: 10.1109/ACCESS.2019.2912200.
[12] H. El-Amir and M. Hamdy, Deep Learning Pipeline. Apress, 2020. doi: 10.1007/978-1-4842-5349-6.
[13] J. Li, B. Ai, R. He, M. Yang, Z. Zhong, and Y. Hao, “A cluster-based channel model for massive MIMO communications in indoor hotspot scenarios,” IEEE Trans Wirel Commun, vol. 18, no. 8, pp. 3856–3870, Aug. 2019, doi: 10.1109/TWC.2019.2919026.
[14] Venkateswararao, K., Swain, P., Christophorou, C., & Pitsillides, A. (2019). Dynamic selection of Virtual Small Base Station in 5G Ultra-Dense Network using Initializing Matching Connection Algorithm. 2019 IEEE International Conference on Advanced Networks and Telecommunications Systems (ANTS), 1-6. https://doi.org/10.1109/ANTS47819.2019.9118045.
[15] C. Janiesch, P. Zschech, and K. Heinrich, “Machine learning and deep learning”, doi: 10.1007/s12525-021-00475-2/Published.
[16] A. Paszke et al., “PyTorch: An Imperative Style, High-Performance Deep Learning Library,” Dec. 2019, [Online]. Available: http://arxiv.org/abs/1912.01703
[17] N. Ketkar, “Introduction to PyTorch,” in Deep Learning with Python, Apress, 2017, pp. 195–208. doi: 10.1007/978-1-4842-2766-4_12.
[18] S. Skansi, “Convolutional Neural Networks,” 2018, pp. 121–133. doi: 10.1007/978-3-319-73004-2_6.
[19] B. Leibe and D. Stutz, “Understanding Convolutional Neural Networks,” 2014.
[20] X. Zhu, Z. Cui, T. Zhang, Y. Li, and J. Yang, “Going Deeper in Frequency Convolutional Neural Network: A Theoretical Perspective,” Aug. 2021, [Online]. Available: http://arxiv.org/abs/2108.05690
[21] A. Khan, A. Sohail, U. Zahoora, and A. S. Qureshi, “A survey of the recent architectures of deep convolutional neural networks,” Artif Intell Rev, vol. 53, no. 8, pp. 5455–5516, Dec. 2020, doi: 10.1007/s10462-020-09825-6.
[22] V. Nguyen, J. Cai, and J. Chu, “Hybrid CNN-GRU model for high efficient handwritten digit recognition,” in ACM International Conference Proceeding Series, Association for Computing Machinery, Aug. 2019, pp. 66–71. doi: 10.1145/3357254.3357276.
[23] D. Liang, J. Zhang, S. Jiang, X. Zhang, J. Wu, and Q. Sun, “Mobile Traffic Prediction Based on Densely Connected CNN for Cellular Networks in Highway Scenarios.”
[24] , A., Basotia, V., & Kumar, R. (2024). Analysis on Probability Mass Function and Probability Density Function. Irish Interdisciplinary Journal of Science & Research. https://doi.org/10.46759/iijsr.2024.8102.
[25] Weng, C., & Zhuang, S. (2014). CDF formulation for solving an optimal reinsurance problem. Scandinavian Actuarial Journal, 2017, 395 - 418. https://doi.org/10.1080/03461238.2016.1167114.
[26] Hamdi, K. (2009). On the statistics of signal-to-interference plus noise ratio in wireless communications. IEEE Transactions on Communications, 57. https://doi.org/10.1109/TCOMM.2009.11.060425.
[27] Mohsin, H., Kadhim, K., & Khudhier, Z. (2019). Study and performance analysis of received signal strength indicator (RSSI) in wireless communication systems.
[28] Shah, A., & Shaikh, A. (2011). Transmission bandwidth efficiency enhancement techniques
