An optimized hybrid methodology for short-term traffic forecasting in telecommunication networks

被引:23
作者
Alizadeh, Mousa [1 ]
Beheshti, Mohammad T. H. [2 ]
Ramezani, Amin [2 ]
Bolouki, Sadegh [3 ]
机构
[1] RMIT Univ, Sch Engn, Melbourne, Vic, Australia
[2] Tarbiat Modares Univ, Dept Elect Comp Engn, Tehran, Iran
[3] Polytech Montreal, Dept Mech Engn, Montreal, PQ, Canada
关键词
BAT ALGORITHM; TIME-SERIES;
D O I
10.1002/ett.4860
中图分类号
TN [电子技术、通信技术];
学科分类号
0809 ;
摘要
With the rapid development of telecommunication networks, the predictability of network traffic is of significant interest in network analysis and optimization, bandwidth allocation, and load balancing adjustment. Consequently, in recent years, significant research attention has been paid to forecasting telecommunication network traffic. Telecommunication traffic forecasting problems can be considered a time-series problem, wherein periodic historical data is fed as the input to a model. Time-series forecasting approaches are broadly categorized as statistical machine learning (ML) methods and their combinations. Statistical approaches forecast linear characteristics of time-series data, unable to capture nonlinear and complex patterns. ML-based approaches can model nonlinear characteristics of data. In recent years, hybrid approaches combining statistical and ML-based approaches have been widely used to model linear and nonlinear data characteristics. However, the performance of these approaches highly depends on feature selection techniques and hyper-parameter tuning of ML methods. A novel hybrid method is proposed for short-term traffic forecasting based on feature selection and hyperparameter optimization to address this problem. It combines statistical and ML methods to model linear and nonlinear components of data. First, a novel feature selection technique, modified mutual information based on a linear combination of targets, is proposed to find the candidate input variables. Next, a combination of vector auto regressive moving average (VARMA), long short-term memory (LSTM), and multilayer perceptron (MLP), called VARMA-LSTM-MLP forecaster, is suggested to forecast short-term traffic. A hybrid metaheuristic algorithm, composed of firefly and BAT, is employed to find the optimal set of hyper-parameter values. The proposed method is assessed by a real-world dataset containing Tehran city's daily telecommunication data in IRAN. The evaluation results demonstrate that the proposed method outperforms the existing methods in terms of mean squared error and mean absolute error.
引用
收藏
页数:25
相关论文
共 64 条
[1]  
Akaike H., 1998, Selected Papers of Hirotugu Akaike, P199, DOI DOI 10.1007/978-1-4612-1694-015
[2]   An optimized neuro-fuzzy system using advance nature-inspired Aquila and Salp swarm algorithms for smart predictive residual and solubility carbon trapping efficiency in underground storage formations [J].
Al-qaness, Mohammed A. A. ;
Ewees, Ahmed A. ;
Thanh, Hung Vo ;
AlRassas, Ayman Mutahar ;
Abd Elaziz, Mohamed .
JOURNAL OF ENERGY STORAGE, 2022, 56
[3]   Wind Power Forecasting Using Optimized Dendritic Neural Model Based on Seagull Optimization Algorithm and Aquila Optimizer [J].
Al-qaness, Mohammed A. A. ;
Ewees, Ahmed A. A. ;
Abd Elaziz, Mohamed ;
Samak, Ahmed H. H. .
ENERGIES, 2022, 15 (24)
[4]   Predicting CO2 trapping in deep saline aquifers using optimized long short-term memory [J].
Al-qaness, Mohammed A. A. ;
Ewees, Ahmed A. ;
Hung Vo Thanh ;
AlRassas, Ayman Mutahar ;
Dahou, Abdelghani ;
Abd Elaziz, Mohamed .
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH, 2023, 30 (12) :33780-33794
[5]   Evaluating the Applications of Dendritic Neuron Model with Metaheuristic Optimization Algorithms for Crude-Oil-Production Forecasting [J].
Al-qaness, Mohammed A. A. ;
Ewees, Ahmed A. ;
Abualigah, Laith ;
AlRassas, Ayman Mutahar ;
Thanh, Hung Vo ;
Abd Elaziz, Mohamed .
ENTROPY, 2022, 24 (11)
[6]   Improving Traffic Forecasting for 5G Core Network Scalability: A Machine Learning Approach [J].
Alawe, Imad ;
Ksentini, Adlen ;
Hadjadj-Aoul, Yassine ;
Bertin, Philippe .
IEEE NETWORK, 2018, 32 (06) :42-49
[7]  
Alizadeh M., 2021, 2021 7 INT C SIGN PR, P1, DOI [10.1109/ICSPIS54653.2021.9729365, DOI 10.1109/ICSPIS54653.2021.9729365]
[8]   Network Traffic Forecasting Based on Fixed Telecommunication Data Using Deep Learning [J].
Alizadeh, Mousa ;
Beheshti, Mohammad T. H. ;
Ramezani, Amin ;
Saadatinezhad, Hadis .
2020 6TH IRANIAN CONFERENCE ON SIGNAL PROCESSING AND INTELLIGENT SYSTEMS (ICSPIS), 2020,
[9]   Time Series ARIMA Model for Prediction of Daily and Monthly Average Global Solar Radiation: The Case Study of Seoul, South Korea [J].
Alsharif, Mohammed H. ;
Younes, Mohammad K. ;
Kim, Jeong .
SYMMETRY-BASEL, 2019, 11 (02)
[10]  
Aufa B. Z., 2020, 2020 INT C DAT SCI I, DOI [DOI 10.1109/ICODSA50139.2020.9213031, 10.1109/ICoDSA50139.2020.9213031]