Learning Methods of Minimization of Drive Test (Signal Fingerprinting Method)

Please enable javascript in your browser.

Sabati, Monther | 2021

331 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 53682 (05)
University: Sharif University of Technology
Department: Electrical Engineering
Advisor(s): Hossein Khalaj, Babak
Abstract:
Drive Test is a known technique witch network operators use to optimize and evaluate their mobile network infra in terms of capacity, coverage, and quality of service. Conducting Drive tests in outdoor areas is time-consuming and increases CAPEX and OPEX. Also, in areas with many giant physical obstacles, like towers and buildings in cities, Drive test is nearly impossible. In this paper, based on data and measurements provided by various Drive tests and TEMS MDT solution, we use an advanced processing algorithm in our database to bring signal coverage map practically to the users' cellphones. By taking advantage of grid-based signal fingerprinting technique, and filtering geo-tagged fingerprints by diversity and number of BSs, we trained a model, that geolocates UEs for 2G, 3G, and 4G with best 2D mean error of 18 meters, expanding network coverage map with these new geolocated points. Finally, for a better user experience, we developed a graphical user interface app based on Pyhton Tkinter. Addressing future challenges, the study can go further, and estimates other network parameters for near futures, like call handovers and status
Keywords:
Localization ; Filtering ; Coverage Map ; Drive Test ; Fingerprinting

No TOC