Cellular traffic prediction on blockchain-based mobile networks using LSTM model in 4G LTE network

AbstractWireless cellular traffic prediction is a critical issue for researchers and practitioners in the 5G/B5G field. However, it is very challenging since the wireless cellular traffic usually shows high nonlinearities and complex patterns. Most existing wireless cellular traffic prediction methods lack the abilities of modeling the dynamic spatial–temporal correlations of wireless cellular traffic data, thus cannot yield satisfactory prediction results. In order to improve the accuracy of 5G/B5G cellular network traffic prediction, an attention-based multi-component spatiotemporal cross-domain neural network model (att-MCSTCNet) is proposed, which uses Conv-LSTM or Conv-GRU for neighbor data, daily cycle data, and weekly cycle data modeling, and then assigns different weights to the three kinds of feature data through the attention layer, improves their feature extraction ability, and suppresses the feature information that interferes with the prediction time. Finally, the model is combined with timestamp feature embedding, multiple cross-domain data fusion, and jointly with other models to assist the model in traffic prediction. Experimental results show that compared with the existing models, the prediction performance of the proposed model is better. Among them, the RMSE performance of the att-MCSTCNet (Conv-LSTM) model on Sms, Call, and Internet datasets is improved by 13.70 ~ 54.96%, 10.50 ~ 28.15%, and 35.85 ~ 100.23%, respectively, compared with other existing models. The RMSE performance of the att-MCSTCNet (Conv-GRU) model on Sms, Call, and Internet datasets is about 14.56 ~ 55.82%, 12.24 ~ 29.89%, and 38.79 ~ 103.17% higher than other existing models, respectively.

Download Full-text

Cellular Traffic Prediction using Recurrent Neural Networks

2020 IEEE 5th International Symposium on Telecommunication Technologies (ISTT) ◽

10.1109/istt50966.2020.9279373 ◽

2020 ◽

Author(s):

Shan Jaffry ◽

Syed Faraz Hasan

Keyword(s):

Neural Networks ◽

Recurrent Neural Networks ◽

Traffic Prediction ◽

Cellular Traffic

Download Full-text

DeepTP: An End-to-End Neural Network for Mobile Cellular Traffic Prediction

IEEE Network ◽

10.1109/mnet.2018.1800127 ◽

2018 ◽

Vol 32 (6) ◽

pp. 108-115 ◽

Cited By ~ 24

Author(s):

Jie Feng ◽

Xinlei Chen ◽

Rundong Gao ◽

Ming Zeng ◽

Yong Li

Keyword(s):

Neural Network ◽

Traffic Prediction ◽

Mobile Cellular ◽

End To End ◽

Cellular Traffic

Download Full-text

Analysis of the Effect of Tilting Antenna on the Coverage Area of ??the 4G LTE Network (Case Study of Trenggalek District)

Jurnal Jartel Jurnal Jaringan Telekomunikasi ◽

10.33795/jartel.v9i4.154 ◽

2019 ◽

Vol 9 (4) ◽

pp. 43-48

Author(s):

Rizal Aji Istantowi

Keyword(s):

Base Station ◽

Base Stations ◽

Optimal Conditions ◽

Coverage Area ◽

Lte Networks ◽

Lte Network ◽

Big Cities ◽

4G Lte ◽

4G Lte Networks

4G LTE networks in big cities are already well available. Meanwhile, on small to medium-sized cities, the 4G LTE network is not evenly distributed and maximized. This study chooses the variable tilting antenna to the coverage area, because in sending information from a base station using an antenna. The average RSRP value (dBm) of the existing base station in the calculation with a distance of 200 m is -122.90 dBm, a distance of 500 m is -136.79 dBm, and a distance of 1000 m -147.30 dBm. Meanwhile, in the simulation with a distance of 200 m of -108.22 dBm, a distance of 500 m of -121.81 dBm, and a distance of 1000 m of -132.69 dBm. The coverage area value of the existing base station in the calculation is 5.29%, while in the simulation it is 11.18%. The average RSRP value (dBm) at optimal conditions for calculations at a distance of 200 m is -80.13 dBm, at a distance of 500 m is -94.03 dBm and at a distance of 1000 m is -104.56 dBm. Meanwhile, the simulation at a distance of 200 m is -98.09 dBm, at a distance of 500 m is -112.79 dBm and at a distance of 1000 m is -123.31 dBm. The value of the coverage area for the calculation is 20.32%, while for the simulation it is 15.01%. The current need for base stations in Trenggalek District that has been met is 68%.

Download Full-text

Traffic Prediction with Reservoir Computing for Mobile Networks

2009 Fifth International Conference on Natural Computation ◽

10.1109/icnc.2009.685 ◽

2009 ◽

Author(s):

Peng Yu ◽

Wang Jian-min ◽

Peng Xi-yuan

Keyword(s):

Mobile Networks ◽

Traffic Prediction ◽

Reservoir Computing

Download Full-text

Penerapan Metode ACP untuk Optimasi Physical Tuning Antena Sektoral pada Jaringan 4G LTE di Kota Purwokerto

ELKOMIKA Jurnal Teknik Energi Elektrik Teknik Telekomunikasi & Teknik Elektronika ◽

10.26760/elkomika.v8i1.138 ◽

2020 ◽

Vol 8 (1) ◽

pp. 138

Author(s):

AFATAH PURNAMA ◽

EKA SETIA NUGRAHA ◽

MUNTAQO ALFIN AMANAF

Keyword(s):

Cell Planning ◽

Lte Network ◽

Physical Optimization ◽

4G Lte

ABSTRAK Kualitas jaringan 4G (LTE) yang masih tidak stabil sehingga menyebabkan bad coverage. Untuk meningkatkan kualitas jarigan 4G (LTE) dapat dilakukan dengan optimasi physical tuning antena sektoral. Physical tuning antena sektoral meliputi perubahan tinggi antena, azimuth dan tilting antena. Pada penelitian ini dilakukan optimasi physical tuning antena sektoral menggunakan metode Automatic Cell Planning (ACP) untuk memenuhi kebutuhan coverage di daerah Purwokerto Barat dan Purwokerto Utara. Perolehan persentase coverage site existing belum memenuhi standar KPI Operator untuk RSRP sebesar 78,491% ≥ (100) dBm dan CINR sebesar 65,698% ≥ (0) dB. Hasil optimasi physical tuninng antena sektoral menggunakan metode ACP sudah memenuhi standar KPI Operator untuk RSRP sebesar 90,037% ≥ (100) dBm dan CINR sebesar 94,868% ≥ (0) dB. Kata kunci: LTE, optimasi, physical tuning, Automatic Cell Planning, Atoll ABSTRACT The quality of the 4G (LTE) network is still unstable, causing bad coverage. To improve the quality of 4G network (LTE) can be done by sectoral antenna tuning optimization. Physical tuning of sectoral antennas includes changes in antenna height, azimuth and tilting antenna. In this study a sectoral antenna tuning physical optimization was carried out using the Automatic Cell Planning (ACP) method to meet coverage needs in West Purwokerto and North Purwokerto areas. The percentage of existing coverage sites has not met the KPI Operator standard for RSRP of 78.491% 100 (100) dBm and CINR of 65.669% ≥ (0) dB. The results of sectoral antenna tuning optimization using the ACP method have met the KPI Operator standard for RSRP of 90.037% ≥ (100) dBm and CINR of 94.868% ≥ (0) dB. Keywords: LTE, optimization, physical tuning, Automatic Cell Planning, Atoll

Download Full-text