Minimization of Drive Tests using measurement reports from user equipment

In this paper we describe the design and implementation of the Minimization of Drive Tests (MDT) system in which user equipments (UEs) upload the measurement reports periodically or upon requests. Based on the collected measurement reports, the MDT system learns the knowledge about the communication environment. We also propose a signal strength forecast method, which is an interesting and promising application of the MDT system, based on the Classification and Regression Trees (CART) algorithm. Experiment results show that the proposed system and method could forecast the signal strength given the locations of base stations and UEs within acceptable error.