Mining Radio Environment Maps from Measurements in SDR Based Self-Organizing Networks

Radio environment maps (REMs) demonstrate the geo-located information of radio performance, which is critical to coverage enhancement in self-organizing networks (SONs). However, due to the limited number of user equipments available to measurement report, constructing REMs accurately is still a crucial challenge. In this paper, an effective algorithm is proposed to construct REMs based on both historical and current measurements of Reference Signal Received Power (RSRP). Specifically, given the differentiated propagation properties across different zones, historical measurements are utilized to group concerned zones into multiple clusters, in each of which all the zones share the same large-scale propagation parameters. In this way, more accurate REMs can be built. In addition, when new measurements come, the shadowing effect parameters in each cluster are further updated via the Expectation Maximization algorithm, making REMs adaptive to time-varying changes. After implementing the proposed algorithm on an OpenAirInterface based SON platform, experiments are conducted and corresponding results show its superiority compared to other interpolation methods.

[1]  Joseph Gaeddert,et al.  RADIO ENVIRONMENT MAP ENABLED SITUATION-AWARE COGNITIVE RADIO LEARNING ALGORITHMS , 2006 .

[2]  Robert J. Renka,et al.  Multivariate interpolation of large sets of scattered data , 1988, TOMS.

[3]  Mugen Peng,et al.  Deep Reinforcement Learning-Based Mode Selection and Resource Management for Green Fog Radio Access Networks , 2018, IEEE Internet of Things Journal.

[4]  Abdullah Konak.  Estimating path loss in wireless local area networks using ordinary kriging , 2010, Proceedings of the 2010 Winter Simulation Conference.

[5]  Mugen Peng,et al.  Application of Machine Learning in Wireless Networks: Key Techniques and Open Issues , 2018, IEEE Communications Surveys & Tutorials.

[6]  Mugen Peng,et al.  Testbed Design and Performance Emulation in Fog Radio Access Networks , 2019, IEEE Network.

[7]  Mugen Peng,et al.  A Game-Theoretic Approach to Cache and Radio Resource Management in Fog Radio Access Networks , 2019, IEEE Transactions on Vehicular Technology.

[8]  Petri Mähönen,et al.  Improving coverage estimation for cellular networks with spatial bayesian prediction based on measurements , 2012, CellNet '12.

[9]  Berna Sayraç,et al.  Fixed Rank Kriging for Cellular Coverage Analysis , 2015, IEEE Transactions on Vehicular Technology.

[10]  Dong Liang,et al.  Self-configuration and self-optimization in LTE-advanced heterogeneous networks , 2013, IEEE Communications Magazine.

[11]  Foad Sohrabi,et al.  Construction of the RSRP map using sparse MDT measurements by regression clustering , 2017, 2017 IEEE International Conference on Communications (ICC).