KPI analysis of 4G/5G networks

• Autorzy: AL-nasrawi Mahdi , AL-Din Makki Seyed Vahab , Al-Sabbagh Ali

Identyfikatory

DOI

10.15199/48.2024.07.15

Warianty tytułu

PL

Analiza KPI sieci 4G/5G

• Języki publikacji: EN

Abstrakty

EN

The development of mobile networks, especially after the 5G network service entered into implementation and deployment in the world, the increase in demand for broadband, and the increase in the number of subscribers. This created complexity in the networks and difficulty in managing them. Therefore, it has become necessary to study and analyze the key performance indicators (KPI) that provide the potential information needed to successfully deploy the network and study the performance and improved networks. This work therefore describes LTE-4G and NR-5G data measurements and KPI performance analysis of data collected via a drive test (DT) process for two operators in Austria. Data measurements focused on parameters that directly affect network strength and quality, such as Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), Signal to Interference and Noise Ratio (SINR), Received Signal Strength Index (RSSI), and downlink uplink data transfer rate (DL/UL throughput). Through the results of analyzing these parameters, it is possible to know the strength and quality of the network and to know the locations of weak points so that a specialist can maintain and address network errors. Finally, analyzing the parameters of key performance indicators provides high flexibility and simplicity in managing and monitoring the performance of mobile networks, reducing complexity, reducing maintenance time and cost, and gaining customer satisfaction.

PL

Rozwój sieci mobilnych, zwłaszcza po wejściu w życie i wdrożeniu usługi sieci 5G na świecie, wzrost zapotrzebowania na łącze szerokopasmowe oraz wzrost liczby abonentów. Spowodowało to złożoność sieci i trudności w zarządzaniu nimi. Dlatego konieczne stało się badanie i analizowanie kluczowych wskaźników wydajności (KPI), które dostarczają potencjalnych informacji potrzebnych do pomyślnego wdrożenia sieci oraz badania wydajności i ulepszonych sieci. Dlatego też w niniejszej pracy opisano pomiary danych LTE-4G i NR-5G oraz analizę wydajności KPI danych zebranych w procesie testu jazdy (DT) dla dwóch operatorów w Austrii. Pomiary danych skupiały się na parametrach, które bezpośrednio wpływają na siłę i jakość sieci, takich jak moc odebrana sygnału odniesienia (RSRP), jakość odebranego sygnału odniesienia (RSRQ), stosunek sygnału do zakłóceń i szumu (SINR), wskaźnik siły odebranego sygnału (RSSI) oraz szybkość przesyłania danych w łączu w dół i w górę (przepustowość DL/UL). Dzięki wynikom analizy tych parametrów można poznać siłę i jakość sieci oraz poznać lokalizacje słabych punktów, aby specjalista mógł konserwować i eliminować błędy sieci. Wreszcie, analiza parametrów kluczowych wskaźników wydajności zapewnia dużą elastyczność i prostotę w zarządzaniu i monitorowaniu wydajności sieci komórkowych, zmniejszając złożoność, skracając czas i koszty konserwacji oraz zdobywając satysfakcję klienta.

Słowa kluczowe

EN

drive test; KPI; 4G; 5G

PL

sieć 5G; test KPI; 4G

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2024
• Tom: R. 100, nr 7
• Strony: 67--71
• Opis fizyczny: Bibliogr. 32 poz., rys., tab.

Twórcy

autor

AL-nasrawi Mahdi

• Razi University, Kermanshah, Iran
• Ministry of communication, ITPC, Iraq

• https://orcid.org/0009-0002-2596-4685

autor

AL-Din Makki Seyed Vahab

• Razi University, Kermanshah, Iran

autor

Al-Sabbagh Ali

• Al Taff University College, Kerbala, Iraq
• Ministry of communication, ITPC , Iraq

• https://orcid.org/0000-0003-3270-980x

Bibliografia

• 1- Shakir, Z., Mjhool, A.Y., Al-Thaedan, A. et al. Key performance indicators analysis for 4 G-LTE cellular networks based on real measurements. Int. j. inf. tecnol. (2023).
• 2- Santos, R. "Machine learning techniques using key performance indicators for the configuration optimization of 4G networks." (2018).
• 3- Eyceyurt, Engin, and Josko Zec. "Uplink throughput prediction in cellular mobile networks." International Journal of Electronics and Communication Engineering 14.6 (2020): 149-153.
• 4- El-Saleh, Ayman A., et al. "Measurements and Analyses of 4G/5G Mobile Broadband Networks: An Overview and a Case Study." Wireless Communications and Mobile Computing 2023 (2023).
• 5- Mostafa, Ali, Mustafa A. Elattar, and Tawfik Ismail. "Downlink Throughput Prediction in LTE Cellular Networks Using Time Series Forecasting." 2022 International Conference on Broadband Communications for Next Generation Networks and Multimedia Applications (CoBCom). IEEE, 2022.
• 6- Fernandez, Gustavo A. "Machine Learning for Wireless Network Throughput Prediction." (2023).
• 7- Eyceyurt, Engin, Yunus Egi, and Josko Zec. "Machine Learning-Based Uplink Throughput Prediction from Physical Layer Measurements." Electronics 11.8 (2022): 1227.
• 8- Al-Thaedan, Abbas, et al. "Downlink throughput prediction using machine learning models on 4G-LTE networks." International Journal of Information Technology (2023):1-7.
• 9- Shakir, Zaenab, Abbas Al-Thaedan, Ruaa Alsabah, Ali Al Sabbagh, Monera Elhashmi M. Salah, and Josko Zec. "Performance evaluation for RF propagation models based on data measurement for LTE networks." International Journal of Information Technology 14, no. 5 (2022): 2423-2428.
• 10- Raida, Vaclav, Philipp Svoboda, and Markus Rupp. "Constant rate ultra short probing (CRUSP) measurements in LTE networks." 2018 IEEE 88th Vehicular Technology Conference (VTC-Fall). IEEE, 2018.
• 11- Raida, Vaclav, et al. "Deriving cell load from RSRQ measurements." 2018 Network Traffic Measurement and Analysis Conference (TMA). IEEE, 2018.
• 12- Raida, Vaclav, et al. "Repeatability for spatiotemporal throughput measurements in LTE." 2019 IEEE 89th Vehicular Technology Conference (VTC2019-Spring). IEEE, 2019.
• 13- Alho, Lauri, et al. "Machine learning based mobile network throughput classification." 2021 IEEE Wireless Communications and Networking Conference (WCNC). IEEE, 2021.
• 14- Motlagh, Naser Hossein, et al. "Quality of Monitoring for Cellular Networks." IEEE Transactions on Network and Service Management 19.1 (2021): 381-391.
• 15- Krasniqi, Fidel, Liljana Gavrilovska, and Arianit Maraj. "The analysis of key performance indicators (KPI) in 4G/LTE networks." International Conference on Future Access Enablers of Ubiquitous and Intelligent Infrastructures. Springer, Cham, 2019.
• 16- Egi, Yunus, et al. "An efficient approach for evaluating performance in LTE wireless networks." Proceedings of the International Conference on Wireless Networks (ICWN). The Steering Committee of The World Congress in Computer Science, Computer Engineering and Applied Computing (WorldComp), 2017.
• 17- Elsherbiny, Habiba, et al. "4g lte network throughput modelling and prediction." GLOBECOM 2020-2020 IEEE Global Communications Conference. IEEE, 2020.
• 18- Skocaj, Marco, et al. "A KPI-Based Self-Optimization Algorithm for Inter-Frequency Handover in 4G/5G Networks." 2021 Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit). IEEE, 2021.
• 19- Imoize, Agbotiname Lucky, Kehinde Orolu, and Aderemi Aaron-Anthony Atayero. "Analysis of key performance indicators of a 4G LTE network based on experimental data obtained from a densely populated smart city." Data in brief 29 (2020): 105304.
• 20- Oje, A. A., and S. O. Edeki. "KPI measurement on the 4G network within the University of Ilorin." Journal of Physics: Conference Series. Vol. 1734. No. 1. IOP Publishing, 2021.
• 21- Raida, Vaclav, et al. "On the stability of rsrp and variability of other kpis in lte downlink-an open dataset." GLOBECOM 2020 2020 IEEE Global Communications Conference. IEEE, 2020.
• 22- Imoize, Agbotiname Lucky, et al. "Updating analysis of key performance indicators of 4G LTE network with the prediction of missing values of critical network parameters based on experimental data from a dense urban environment." Data in Brief 42 (2022): 108240.
• 23- Maposa, Darlington. "Evolving 4G KPIs to improve end user QoE for 4G LTE broadband systems." (2016).
• 24- Song, Guochao, et al. "KPI/KQI-driven coordinated multipoint in 5G: Measurements, field trials, and technical solutions." IEEE Wireless Communications 25.5 (2018): 23-29.
• 25- Zhang, Yan, et al. "Path loss prediction based on machine learning: Principle, method, and data expansion." Applied Sciences 9.9 (2019): 1908.
• 26- Cho, Yeon-Jea, et al. "AI-enabled wireless KPI monitoring and DiagnosisSystem for 5G cellular networks." 2019 International Conference on Information and Communication Technology Convergence (ICTC). IEEE, 2019.
• 27- Alshamsi, Hazza Saif Saeed. UE Based Performance Evaluation of 4G LTE Network. Diss. Florida Institute of Technology, 2019.
• 28- Jung, Alexander. Machine Learning: The Basics. Springer Nature, 2022.
• 29- Ericsson training student book, "LTE Mobility and Throughput - KPI Analysis & Optimization Workshop”, Ericsson AB, LZT1381950 R1A ,2017.
• 30- Raida, Dipl-Ing Vaclav. Data-Driven Estimation of Spatiotemporal Performance Maps in Cellular Networks. Diss. University of Bologna Vienna, 2021.
• 31- Soós, Gábor, et al. "Practical 5G KPI measurement results on a non-standalone architecture." Noms 2020-2020 IEEE/IFIP network operations and management symposium. IEEE, 2020.
• 32- Trinh, Hoang Duy. "Data analytics for mobile traffic in 5G networks using machine learning techniques." (2020).

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki i promocja sportu (2025).