Construction of the RSRP Map Using Sparse MDT Measurements by Regression Clustering

Radio environment map (REM) which is a geological map with overlay of performance information of a radio communication can be considered as one of the key enablers of the selforganizing networks (SON). Conventionally, operators generate the REMs using the measurement data of the extensive drive/walk test which requires extensive human efforts and further it has some performance limitations. But after the introduction of minimization of drive tests (MDT) to the standards, operators are interested to generate REMs based on the sparse sets of MDT measurements obtained from the user side. In this paper, we consider the construction of the reference signal received power (RSRP) map (which is an example of REM) using the sparse sets of MDT measurements from user equipments (UEs). In particular, we propose a two-step algorithm for RSRP map generation which is shown to achieve a better performance as compared to some of the existing baseline methods.