隨著網路流量快速增長，第四代行動網路 (The fourth generation mobile network, 4G) 已經無法滿足大量的網路應用需求，為了解決這個問題，第三代合作夥伴計劃(3rd Generation Partnership Project, 3GPP)為第五代行動網路 (The fifth generation mobile network, 5G)定義了三大發展方向，包含移動寬頻增強 (enhanced Mobile Broadband, eMBB)、大規模物聯網 (Massive Machine Type Communications, mMTC) 以及超高可靠超低時延通信 (Ultra-Reliable Low-Latency Communications, URLLC)。其中，毫米波(Millimeter Wave, mmWave)的使用是5G發展的關鍵技術，雖然毫米波可以增強網路寬頻、提升網路速度，但是相較於6 Ghz以下的頻段，毫米波的繞射能力差，導致基地台的傳輸距離受到限制，雖然可以透過密集地佈署基地台來改善，但是高頻電波經過障礙物導致的高路徑損耗成為基地台佈署的挑戰之一，因此為了實現高品質的5G服務，首要解決的問題為5G的基地台佈署。
由於5G標準已於2020年制定完成，許多營運商正在佈署5G的基地台，為了避免5G網路流量快速成長帶來的影響和衝擊，本研究基於網路流量預測進行多目標三維微型基地台的佈署規劃於後5G行動通訊網路 (Beyond 5G, B5G)，在網路流量預測部分，考量時空相關性提出一種輕量級的時空卷積神經網絡（Lightweight Spatial-Temporal Convolutional Neural Network, LSTCNN）架構，透過此架構可以減少流量預測的運算成本及增加實際應用的泛用性，此外，針對時空相關性問題，提出及優化輸入資料的轉換方法，模擬結果表明LSTCNN可以大幅減少神經網絡的參數且保有一定的準確性。針對微型基地台的佈署問題，本研究將其定義為多目標最佳化問題，考量覆蓋率、佈署成本及無線接收信號強度的權衡關係，提出結合虛擬力與模擬退火機制之非支配排序基因算法演算法(Virtual force and Annealing mechanism for Non-dominated Sorting Genetic Algorithm II, VA-NSGA-II)來最佳化三維微型基地台的佈署，此外，為了提升覆蓋範圍以及避免無法收斂的問題，提出虛擬力機制和退火機制來改善佈署成效，藉由模擬的方式測試在不同材質組合的環境下的佈署結果，最後針對不同的應用場景給予佈署目標的選擇建議。

With the rapid growth of network traffic, the fourth-generation mobile network (4G) cannot satisfy the requirements of massive network applications. In order to solve this problem, the 3rd Generation Partnership Project (3GPP) has defined three major development directions for the fifth-generation mobile network (5G), including Enhanced Mobile Broadband (eMBB), Massive Machine Type Communications (mMTC) and Ultra-Reliable Low-Latency Communications (URLLC). Among them, the use of Millimeter Wave (mmWave) is a key technology for 5G development. Although mmWave can enhance network bandwidth and network speed, compared with the frequency band below 6 GHz, the diffraction capability of mmWave is poor, resulting in the limited transmission distance of base stations. Although it can be improved by intensively deploying base stations, the high path loss caused by high-frequency radio waves passing through obstacles has become one of the challenges of base station deployment. Therefore, in order to achieve high-quality 5G services, the primary problem to be solved is the deployment of 5G base stations.
Since the 5G standard has been completed in 2020, many operators are deploying 5G base stations. In order to avoid the impact of the rapid growth of 5G network traffic, this study focuses on traffic-prediction-based multi-objective three-dimensional (3D) small cell deployment optimization for beyond 5G mobile communication network (B5G). For cellular traffic prediction problem, we consider spatial-temporal dependencies and propose a lightweight spatial-temporal convolutional neural network (LSTCNN) architecture, which can reduce the computational cost of traffic prediction and enhance the universality. In addition, we also propose and optimize a conversion method of input data according to spatial-temporal dependencies. The simulation results show that LSTCNN can greatly reduce the parameters of the neural network and maintain a certain accuracy. For deployment problem of base stations, we formulate it as a multi-objective optimization problem. Considering the trade-off relationship between coverage rate, deployment cost, and Received Signal Strength Indicator (RSSI), the Virtual force and Annealing mechanism for Non-dominated Sorting Genetic Algorithm II (VA-NSGA-II) algorithm is proposed to optimize the deployment of three-dimensional small cells. In addition, in order to improve the coverage rate and avoid the problem of non-convergence, a virtual force mechanism and an annealing mechanism are adopted to improve the deployment performance. We evaluate the deployment results in different material combinations environments through simulation and recommend the suitable deployment objective function for different application scenarios.

[1] S. C. Wang, W. S. Hsiung, K. Q. Yan, and Y. T. Tsai, " Optimal Agreement Achievement in a Fog Computing Based IoT," Journal of Internet Technology, vol. 20, no.6, pp. 1767-1779, Nov. 2019.
[2] W. C. Chien, C. F. Lai, M. S. Hossain, and G. Muhammad, "Heterogeneous space and terrestrial integrated networks for IoT: Architecture and challenges," IEEE Network, vol. 33, no. 1, pp. 15-21, January 2019
[3] W. C. Chien, C. F. Lai, H. H. Cho, and H. C. Chao, "A SDN-SFC-based service-oriented load balancing for the IoT applications," Journal of Network and Computer Applications, vol. 114, no.15, pp.88-97, July 2018.
[4] C. Zhang, H. H. Cho, C. Y. Chen, T. K. Shih, and H. C. Chao, " Fuzzy-Based 3-D Stream Traffic Lightweighting Over Mobile P2P Network," IEEE Systems Journal, 2019.
[5] G. Araniti, I. Bisio, M. De Sanctis, A. Orsino, and J. Cosmas, "Multimedia content delivery for emerging 5G-satellite networks, "IEEE Transactions on Broadcasting, vol. 62, no.1, pp.10-23, 2016.
[6] S. Scott-Hayward, and E. Garcia-Palacios, "Multimedia resource allocation in mmwave 5G networks," IEEE Communications Magazine, vol. 53, no.1, pp.240-247, 2015.
[7] S. Y. Lien, S. L. Shieh, Y. Huang, B. Su, Y. L. Hsu, and H. Y. Wei, "5G new radio: Waveform, frame structure, multiple access, and initial access," IEEE communications magazine, vol.55, no.6, pp.64-71, 2017.
[8] I. A. T. Hashem, et al., "The role of big data in smart city," International Journal of Information Management, vol. 36, no.5, pp.748-758, 2016.
[9] S. K. Rao, and R. Prasad, "Impact of 5G technologies on smart city implementation," Wireless Personal Communications, vol.100, no.1, pp.161-176, 2018.
[10] P. Popovski, K. F. Trillingsgaard, O. Simeone, and G. Durisi, "5G wireless network slicing for eMBB, URLLC, and mMTC: A communication-theoretic view," IEEE Access, vol. 6, pp. 55765-55779,September 2018.
[11] A. Anand, G. De Veciana, and S. Shakkottai, "Joint scheduling of URLLC and eMBB traffic in 5G wireless networks," IEEE/ACM Transactions on Networking, vol. 28. no. 2, pp.477-490, February 2020.
[12] A. A. Esswie, and K. I. Pedersen, "Opportunistic spatial preemptive scheduling for URLLC and eMBB coexistence in multi-user 5G networks," IEEE Access, vol. 6, pp. 38451-38463, July 2018.
[13] W. Shi, J. Cao, Q. Zhang, Y. Li, and L. Xu, "Edge computing: Vision and challenges," IEEE Internet of Things Journal, vol. 3, no, 5, pp. 637-646, Jun. 2016.
[14] W. Shi, and S. Dustdar, "The promise of edge computing, "Computer, vol. 49, no, 5, pp. 78-81, May. 2016.
[15] Y. C. Hu, M. Patel, D. Sabella, N. Sprecher, and V. Young, " Mobile edge computing—A key technology towards 5G. ETSI white paper, " vol. 11, no, 11, pp. 1-16, Sep. 2015.
[16] T. H. Luan, L. Gao, Z. Li, Y. Xiang, G. Wei, and L. Sun, "Fog computing: Focusing on mobile users at the edge," arXiv preprint arXiv:1502.01815, Mar 2016.
[17] S. Y. Lien, S. L. Shieh, Y. Huang, B. Su, Y. L. Hsu, and H. Y. Wei, "5G new radio: Waveform, frame structure, multiple access, and initial access," IEEE communications magazine, vol.55, no.6, pp.64-71, 2017.
[18] K. Kawasaki,"Millimeter wave transmission device, millimeter wave transmission method, and millimeter wave transmission system." U.S. Patent No. 9,608,683. 28 March 2017.
[19] M. Xiao, et al.," Millimeter wave communications for future mobile networks," IEEE Journal on Selected Areas in Communications, vol. 35, no. 9, pp. 1909-1935, June 2017.
[20] M. Xiao, et al.," Millimeter wave communications for future mobile networks," IEEE Journal on Selected Areas in Communications, vol. 35, no. 9, pp. 1909-1935, June 2017.
[21] M. R. Akdeniz, Y. Liu, M. K. Samimi, S. Sun, S. Rangan, T. S. Rappaport and E. Erkip, "Millimeter Wave Channel Modeling and Cellular Capacity Evaluation," IEEE Journal on Selected Areas in Communications, vol. 32 , no. 6, pp. 1164 - 1179, June 2014.
[22] J. An, K. Yang, J. Wu, N. Ye, S. Guo, and Z. Liao, "Achieving sustainable ultra-dense heterogeneous networks for 5G, "IEEE Communications Magazine, vol. 55. no. 12, pp. 84-90, December 2017.
[23] C. Huang, Q. Chen, and L. Tang, "Hybrid inter-cell interference management for ultra-dense heterogeneous network in 5G, " Science China Information Sciences, vol. 59, no. 8, pp. 082305, April 2016.
[24] B. Yang, G. Mao, X. Ge, M. Ding, and X. Yang, "On the energy-efficient deployment for ultra-dense heterogeneous networks with NLoS and LoS transmissions," IEEE Transactions on Green Communications and Networking, vol. 2, no. 2, pp. 369-384, January 2018.
[25] S. Mumtaz, A. Bo, A. Al-Dulaimi, and K. F. Tsang,"Guest editorial 5G and beyond mobile technologies and applications for industrial IoT (IIoT)," IEEE Transactions on Industrial Informatics, vol.14, no.6, pp.2588-2591, April 2018.
[26] D. M. Drukker, H. Peng, I. Prucha, and R. Raciborski, "SPPACK: Stata module for cross-section spatial-autoregressive models," 2018.
[27] W. Scherrer, and M. Deistler, "Vector autoregressive moving average models," Conceptual Econometrics Using R, 145, 2019.
[28] C. Yuan, S. Liu, and Z. Fang, "Comparison of China's primary energy consumption forecasting by using ARIMA (the autoregressive integrated moving average) model and GM (1, 1) model," Energy, vol.100, pp.384-390, April 2016.
[29] N. S. El_Jerjawi, and S. S. Abu-Naser, "Diabetes prediction using artificial neural network, vol.121, pp. 54-64, 2018.
[30] A. Rahman, V. Srikumar, and A. D. Smith, "Predicting electricity consumption for commercial and residential buildings using deep recurrent neural networks," Applied energy, vol.212, pp.372-385, February 2018.
[31] C.-F. Lai, W.-C. Chien, L. T. Yang, W. Qiang , " LSTM and Edge Computing for Big Data Feature Recognition of Industrial Electrical Equipment," IEEE Transactions on Industrial Informatics, Vol. 15, No.4, pp.2469-2477, January 2019.
[32] L. Ren, X. Cheng, X. Wang, J. Cui, and L. Zhang, "Multi-scale dense gate recurrent unit networks for bearing remaining useful life prediction," Future Generation Computer Systems, vol. 94, pp. 601-609, May 2019.
[33] C. Wang, C. Liang, F. R. Yu, Q. Chen, and L. Tang, “Computation offloading and resource allocation in wireless cellular networks with mobile edge computing,” IEEE Transactions on Wireless Communications, vol. 16, no. 8, pp. 4924-4938, May 2017.
[34] X. Ge, S. Tu, G. Mao, C. Wang and T. Han, "5G Ultra-Dense Cellular Networks," IEEE Wireless Communications, vol. 23, no. 1, pp. 72 - 79, February 2016.
[35] S. Niknam, A. A. Nasir, H. Mehrpouyan, and B. Natarajan, "A multiband OFDMA heterogeneous network for millimeter wave 5G wireless applications," IEEE Access, vol.4, pp.5640-5648, September 2016.
[36] M. Klymash, H. Beshley, O. Panchenko, and M. Beshley, "Method for optimal use of 4G/5G heterogeneous network resourses under M2M/IoT traffic growth conditions. In IEEE 2017 International Conference on Information and Telecommunication Technologies and Radio Electronics (UkrMiCo), September 2017. pp. 1-5.
[37] N. N. Dao, M. Park, J. Kim, J. Paek, and S. Cho, "Resource-aware relay selection for inter-cell interference avoidance in 5G heterogeneous network for Internet of Things systems, "Future Generation Computer Systems, vol. 93, pp. 877-887, April 2019.
[38] "The 1000× Mobile Data Challenge," [Online]. Available: https://www.qualcomm.com/media/documents/files/1000x-mobile-data-challenge.pdf.
[39] H. Zhang, H. Liu, J. Cheng, and V. C. Leung, "Downlink energy efficiency of power allocation and wireless backhaul bandwidth allocation in heterogeneous small cell networks," IEEE transactions on communications, vol. 66, no.4, pp.1705-1716, October 2017.
[40] H. H. Yang, G. Geraci, and T. Q. Quek, "Energy-efficient design of MIMO heterogeneous networks with wireless backhaul," IEEE Transactions on Wireless Communications, vol.15, no.7, pp.4914-4927, April 2016.
[41] X. Ge, S. Tu, G. Mao, V. K. Lau, and L. Pan, "Cost efficiency optimization of 5g wireless backhaul networks, "IEEE Transactions on Mobile Computing, vol. 18, no. 12, pp. 2796-2810, December 2018.
[42] X. Ge, H. Cheng, M. Guizani and T. Han, "5G wireless backhaul networks: challenges and research advances," IEEE Network, vol. 28, no. 6, pp. 6 - 11, November - December 2014.
[43] R. Kaviarasan, and A. Amuthan, "Hyperbolic Distance-based NLOS Nodes Detection Mechanisms in VANETs: A Survey," In IEEE 2019 International Conference on Intelligent Sustainable Systems (ICISS), February 2019, pp. 396-401.
[44] R. Kaviarasan, and A. Amuthan, "Detection methodologies to overcome Non line of Sight (NLOS) in Adhoc Networks: A Survey, "In IEEE 2019 International Conference on Computer Communication and Informatics (ICCCI), January 2019, pp. 1-5.
[45] P. Korrai, and K. D. Rao, "Performance analysis of downlink mmWave networks under LoS/NLoS propagation with blockage and directional beamforming," Telecommunication Systems, vol.72, no.1, pp.53-68, 2019.
[46] S. K. Islam and M. R. Haider, "Sensors and Low Power Signal Processing," 2010.
[47] "ABI Research Anticipates In-Building Mobile Data Traffic to Grow by More Than 600% by 2020," [Online]. Available: https://www.abiresearch.com/press/abi-research-anticipates-building-mobile-data-traf/
[48] M. S. Islam, F. Begum, A. U. Hani, M. A. Matin and M. M. Hossain, "On the determination of penetration losses of microwave signals in different building materials," 5th Brunei International Conference on Engineering and Technology (BICET 2014), Bandar Seri Begawan, 2014, pp. 1-5.
[49] "5G; Study on channel model for frequencies from 0.5 to 100 GHz (3GPP TR 38.901 version 14.3.0 Release 14)," [Online]. Available: https://www.etsi.org/deliver/etsi_tr/138900_138999/138901/14.03.00_60/tr_138901v140300p.pdf
[50] H. D. Trinh, L. Giupponi, and P. Dini, “Mobile traffic prediction from raw data using LSTM networks,” In 2018 IEEE 29th Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC), pp. 1827-1832, December 2018.
[51] A. Dalgkitsis, M. Louta, and G. T. Karetsos, “Traffic forecasting in cellular networks using the LSTM RNN,” In Proceedings of the 22nd Pan-Hellenic Conference on Informatics, pp. 28-33, November 2018.
[52] E. P. L. Shiang, W. C. Chien, C. F. Lai, and H. C. Chao, “Gated Recurrent Unit Network-based Cellular Trafile Prediction,” In 2020 International Conference on Information Networking (ICOIN) , pp. 471-476, March 2020.
[53] C. Zhang, H. Zhang, D. Yuan, and M. Zhang, “Citywide cellular traffic prediction based on densely connected convolutional neural networks,” IEEE Communications Letters, vol. 22, no. 8, pp. 1656–1659, August 2018.
[54] C. Qiu, Y. Zhang, Z. Feng, P. Zhang, and S. Cui, “Spatial-temporal wireless traffic prediction with recurrent neural network,” IEEE Wireless Communications Letters, pp. 1-1, January 2018.
[55] J. Wang, J. Tang, Z. Xu, Y. Wang, G. Xue, X. Zhang, and D. Yang, “Spatiotemporal modeling and prediction in cellular networks: A big data enabled deep learning approach,” in IEEE Conference on Computer Communications (INFOCOM), pp. 1-9, May 2017.
[56] C. Zhang and P. Patras, “Long-term mobile traffic forecasting using deep spatial-temporal neural networks,” in Proceedings of the Eighteenth ACM International Symposium on Mobile Ad Hoc Networking and Computing, pp. 231-240, June 2018.
[57] C. T. Zhang, H. X. Zhang, J. P. Qiao, D. F. Yuan, and M. G. Zhang, “Deep transfer learning for intelligent cellular traffic prediction based on cross-domain big data,” IEEE Journal on Selected Areas in Communications, vol. 37, no. 6, pp. 1389-1401, June 2019.
[58] F. Ding, D. Zhang, A. Song, J. Li, "A Coverage and Repair Optimization Algorithm for Hybrid Sensor Networks," Journal of Internet Technology, vol. 19, no. 3, pp. 909 - 917, May 2018.
[59] T. G. Nguyen, C. So-In, N. G. Nguyen, "Barrier Coverage Deployment Algorithms for Mobile Sensor Networks," Journal of Internet Technology, vol. 18, no. 7, pp. 1689 - 1699, December 2017.
[60] C. Wang, F. Haider, X. Gao, X. You, Y. Yang, D. Yuan, H. M. Aggoune, H. Haas, S. Fletcher and E. Hepsaydir, "Cellular architecture and key technologies for 5G wireless communication networks," IEEE Communications Magazine, vol. 52, no. 2, pp. 122 - 130, February 2014.
[61] O. Zorlu and O. K. Sahingoz, "Increasing the coverage of homogeneous wireless sensor network by genetic algorithm based deployment," 2016 Sixth International Conference on Digital Information and Communication Technology and its Applications (DICTAP), Konya, 2016, pp. 109 - 114.
[62] E. Amaldi, A. Capone and F. Malucelli, "Planning UMTS base station location: Optimization models with power control and algorithms," IEEE Transactions on wireless communications, vol. 2, no. 5, pp. 939 - 952, September 2003.
[63] W. Zhao, S. Wang, C. Wang and X. Wu, "Approximation algorithms for cell planning in heterogeneous networks," IEEE Transactions on Vehicular Technology, vol. 66, no. 2, pp. 1561 - 1572, February 2017.
[64] H. Ghazzai, E. Yaacoub, M. Alouini, Z. Dawy and A. Abu-Dayya, "Optimized LTE cell planning with varying spatial and temporal user densities," IEEE Transactions on Vehicular Technology, vol. 65, no. 3, pp. 1575 - 1589, March 2016.
[65] F.-H. Tseng, "Network Planning for Type 1 and 1a Relay Nodes in LTE Network Planning for Type 1 and 1a Relay Nodes in LTE," doctoral dissertation, Department of Computer Science & Information Engineering, National Central University. Available: https://hdl.handle.net/11296/2dmg77
[66] A.Santoro, V. Latora, G. Nicosia, and V. Nicosia, "Pareto optimality in multilayer network growth," Physical review letters, vol. 121, no.12, pp. 128302.
[67] A. Basta, A. Blenk, K. Hoffmann, H. J. Morper, M. Hoffmann, and W. Kellerer, "Towards a cost optimal design for a 5G mobile core network based on SDN and NFV," IEEE Transactions on Network and Service Management, vol. 14, no.4, pp.1061-1075, July 2017.
[68] M. Vilgelm, S. R. Linares, and W. Kellerer,"On the Resource Consumption of M2M Random Access: Efficiency and Pareto Optimality. IEEE Wireless Communications Letters, vol. 8, no. 3, pp.709-712, December 2018.
[69] K. Deb, A. Pratap, S. Agarwal and T. Meyarivan, "A fast and elitist multiobjective genetic algorithm: NSGA-II," IEEE Transactions on Evolutionary Computation, vol. 6, no. 2, pp. 182 - 197, April 2002.
[70] G. Barlacchi et al., “A multi-source dataset of urban life in the city of Milan and the Province of Trentino,” Sci. Data, vol. 2, Oct. 2015,Art. no. 150055.
[71] T. Tieleman, and G. Hinton, "Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude," COURSERA: Neural networks for machine learning, vol.4, no.2, pp.26-31, 2012.
[72] A. T. Hadgu, A. Nigam, and E. Diaz-Aviles, "Large-scale learning with AdaGrad on Spark," In 2015 IEEE International Conference on Big Data (Big Data), October 2015, pp. 2828-2830.
[73] I. Hubara, M. Courbariaux, D. Soudry, R. El-Yaniv, and Y. Bengio, "Binarized neural networks," In Advances in neural information processing systems ,pp. 4107-4115, 2016.
[74] T. Chilimbi, Y. Suzue, J. Apacible, and K. Kalyanaraman, "Project adam: Building an efficient and scalable deep learning training system. In 11th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 14), pp. 571-582, 2014.
[75] B. Xu, N. Wang, T. Chen, and M. Li, "Empirical evaluation of rectified activations in convolutional network," arXiv preprint arXiv:1505.00853, 2015.
[76] "tf.nn.relu6,"[Online]Available: https://www.tensorflow.org/api_docs/python/tf/nn/relu6
[77] A. Howard, et al., "Searching for mobilenetv3," Proceedings of the IEEE International Conference on Computer Vision, 2019, pp. 1314-1324.
[78] "Spectrum for Terrestrial 5G Networks: Licensing Developments Worldwide," [Online]. Available: https://gsacom.com/paper/5g-spectrum-for-terrestrial-networks-june-2019/
[79] "Small Cell Networks and the Evolution of 5G (Part 1)," [Online]. Available: https://www.qorvo.com/design-hub/blog/small-cell-networks-and-the-evolution-of-5g
[80] D. Wu, X. Gu, J. Gu, W. Liao, L. Zhang, and Y. Liu, "Cost optimization based network deployment strategies for future dense networks," 2016 19th International Symposium on Wireless Personal Multimedia Communications (WPMC), Shenzhen, 2016, pp. 19 - 24.