Mobile Network Traffic Prediction Based on User Behavior and Machine Learning

Document Type : Research Paper


1 Faculty of Electrical and Computer Engineering, Semnan University, Semnan, Iran.

2 Faculty of Electrical and Computer Engineering (ECE), Semnan University, Semnan, Iran.


One of the challenges of any network is user traffic analysis and prediction. Mobile networks have achieved notable growth in recent years. Traffic information on these networks play a crucial role in service quality control, user access control, and optimization. There are various methods for traffic prediction, including harmonic analysis and mathematical transformations, time series methods, and machine learning. Due to the increasing volume of user data on mobile networks, machine learning methods have gained popularity in recent decades. In this paper, we introduce a probabilistic behavioral model and propose a new method that focuses on human behavior by categorizing users through clustering and utilizing their similarities. Assuming a history of past user data is available, users with similar behavior are grouped into categories using clustering methods, and each category is assigned a label. The average of each cluster represents the traffic in that category. To predict the traffic of new users, our proposed method utilizes classification functions to determine the most appropriate category. Subsequently, weighted averages are used to calculate the overall network traffic. We compare our proposed method with time series and Fourier transform methods through three different scenarios. The results indicate that our method exhibits significant superiority over the other methods.


Main Subjects

[1]    Navarro-Ortiz J, Romero-Diaz P, Sendra S, Ameigeiras P, Ramos-Munoz JJ, Lopez-Soler JM (2020) A Survey on 5G Usage Scenarios and Traffic Models. IEEE Commun Surv Tutorials 22, pp. 905–929.
[2]    Walelgne EA, Asrese AS, Manner J, Bajpai V, Ott J (2021) Clustering and predicting the data usage patterns of geographically diverse mobile users. Comput Networks 187, pp. 107737.
[3]    Qiao Y, Xing Z, Fadlullah ZM, Yang J, Kato N (2018) Characterizing Flow, Application, and User Behavior in Mobile Networks: A Framework for Mobile Big Data. IEEE Wirel Commun 25, pp. 40–49.
[4]    Wang W, Harari GM, Wang R, Müller SR, Mirjafari S, Masaba K, Campbell AT (2018) Sensing Behavioral Change over Time. Proc ACM Interactive, Mobile, Wearable Ubiquitous Technol 2, pp. 1–21.
[5]    Mokhtari A, Sadighi L, Bahrak B, Eshghie M (2020) Hybrid Model for Anomaly Detection on Call Detail Records by Time Series Forecasting. arXiv pp. 1–12.
[6]    Truong Dinh K, Kukliński S, Osiński T, Wytrębowicz J (2020) Heuristic traffic engineering for SDN. J Inf Telecommun 4, pp. 251–266.
[7]    Zhang J, Ye M, Guo Z, Yen CY, Chao HJ (2020) CFR-RL: Traffic Engineering with Reinforcement Learning in SDN. IEEE J Sel Areas Commun 38, pp. 2249–2259.
[8]    Shinkuma R, Tanaka Y, Yamada Y, Takahashi E, Onishi T (2018) User instruction mechanism for temporal traffic smoothing in mobile networks. Comput Networks 137, pp. 17–26.
[9]    Shin H, Jung J, Koo Y (2020) Forecasting the video data traffic of 5 G services in south korea. Technol Forecast Soc Change 153, pp. 119948.
[10] Passas V, Miliotis V, Makris N, Korakis T (2020) Pricing Based Distributed Traffic Allocation for 5G Heterogeneous Networks. IEEE Trans Veh Technol 69, pp. 12111–12123.
[11] Peng J (2020) Impact of the Arrival Distribution of Primary User Traffic in Dynamic Spectrum Access. Procedia Comput Sci 170, pp. 325–332.
[12] Shruti, Kulshrestha R (2020) Channel allocation and ultra-reliable communication in CRNs with heterogeneous traffic and retrials: A dependability theory-based analysis. Comput Commun 158, pp. 51–63.
[13] Jiang W (2022) Cellular traffic prediction with machine learning: A survey. Expert Syst Appl 201, pp. 117163.
[14] Khedkar SP, Canessane RA, Najafi ML (2021) Prediction of Traffic Generated by IoT Devices Using Statistical Learning Time Series Algorithms. Wirel Commun Mob Comput 2021, pp. 1–12.
[15] Nie L, Ning Z, Obaidat MS, Sadoun B, Wang H, Li S, Guo L, Wang G (2021) A Reinforcement Learning-Based Network Traffic Prediction Mechanism in Intelligent Internet of Things. IEEE Trans Ind Informatics 17, pp. 2169–2180.
[16] Long P, Li J, Liu N, Pan Z, You X (2022) Antenna On/Off Strategy for Massive MIMO Based on User Behavior Prediction. In 2022 3rd International Conference on Computing, Networks and Internet of Things (CNIOT) IEEE, pp. pp. pp. 113–119.
[17] Alqudah N, Yaseen Q (2020) Machine Learning for Traffic Analysis: A Review. In Procedia Computer Science Elsevier B.V., pp. pp. pp. 911–916.
[18] Morocho-Cayamcela ME, Lee H, Lim W (2019) Machine Learning for 5G/B5G Mobile and Wireless Communications: Potential, Limitations, and Future Directions. IEEE Access 7, pp. 137184–137206.
[19] Alekseeva D, Stepanov N, Veprev A, Sharapova A, Lohan ES, Ometov A (2021) Comparison of Machine Learning Techniques Applied to Traffic Prediction of Real Wireless Network. IEEE Access 9, pp. 159495–159514.
[20] Yang Y, Geng S, Zhang B, Zhang J, Wang Z, Zhang Y, Doermann D (2023) Long term 5G network traffic forecasting via modeling non-stationarity with deep learning. Commun Eng 2, pp. 33.
[21] Xu F, Li Y, Wang H, Zhang P, Jin D (2017) Understanding Mobile Traffic Patterns of Large Scale Cellular Towers in Urban Environment. IEEE/ACM Trans Netw 25, pp. 1147–1161.
[22] Iqbal MF, Zahid M, Habib D, John LK (2019) Efficient Prediction of Network Traffic for Real-Time Applications. J Comput Networks Commun 2019, pp. 1–11.
[23] Xu F, Lin Y, Huang J, Wu D, Shi H, Song J, Li Y (2016) Big Data Driven Mobile Traffic Understanding and Forecasting: A Time Series Approach. IEEE Trans Serv Comput 9, pp. 796–805.
[24] Theerthagiri P (2022) Mobility prediction for random walk mobility model using ARIMA in mobile ad hoc networks. J Supercomput 78, pp. 16453–16484.
[25] Albeladi K, Zafar B, Mueen A (2023) Time Series Forecasting using LSTM and ARIMA. Int J Adv Comput Sci Appl 14, pp. 2023.
[26] Walelgne EA, Asrese AS, Manner J, Bajpai V, Ott J (2020) Understanding Data Usage Patterns of Geographically Diverse Mobile Users. IEEE Trans Netw Serv Manag pp. 1–1.
[27] Camacho J, McDonald C, Peterson R, Zhou X, Kotz D (2020) Longitudinal analysis of a campus Wi-Fi network. Comput Networks 170, pp. 107103.
[28] Jiang D, Wang Y, Lv Z, Qi S, Singh S (2020) Big Data Analysis Based Network Behavior Insight of Cellular Networks for Industry 4.0 Applications. IEEE Trans Ind Informatics 16, pp. 1310–1320.
[29] Lo Schiavo L, Fiore M, Gramaglia M, Banchs A, Costa-Perez X (2022) Forecasting for Network Management with Joint Statistical Modelling and Machine Learning. In 2022 IEEE 23rd International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM) IEEE, pp. pp. pp. 60–69.
[30] Sun F, Wang P, Zhao J, Xu N, Zeng J, Tao J, Song K, Deng C, Lui JCS, Guan X (2021) Mobile Data Traffic Prediction by Exploiting Time-Evolving User Mobility Patterns. IEEE Trans Mob Comput 14, pp. 1–1.
[31] Ma H, Yang K, Pun M-O (2023) Cellular traffic prediction via deep state space models with attention mechanism. Comput Commun 197, pp. 276–283.
[32] Fu Y, Wang X (2022) Traffic Prediction-Enabled Energy-Efficient Dynamic Computing Resource Allocation in CRAN Based on Deep Learning. IEEE Open J Commun Soc 3, pp. 159–175.
[33] Zhao N, Wu A, Pei Y, Liang Y-C, Niyato D (2022) Spatial-Temporal Aggregation Graph Convolution Network for Efficient Mobile Cellular Traffic Prediction. IEEE Commun Lett 26, pp. 587–591.
[34] Liu M, Liu G, Sun L (2023) Spatial–temporal dependence and similarity aware traffic flow forecasting. Inf Sci (Ny) 625, pp. 81–96.
[35] Lee J-M, Kim J-D (2022) A Generative Model for Traffic Demand with Heterogeneous and Spatiotemporal Characteristics in Massive Wi-Fi Systems. Electronics 11, pp. 1848.
[36] Cisco (2020) Cisco Annual Internet Report - Cisco Annual Internet Report (2018 - 2023) White Paper. pp. 1–41.
[37] Pimpinella A, Giusto F Di, Redondi AEC, Venturini L, Pavon A (2022) Forecasting Busy-Hour Downlink Traffic in Cellular Networks. In ICC 2022 - IEEE International Conference on Communications IEEE, pp. 4336–4341.