Multivariate Analysis of LTE Radio-Layer Parameters based on a Partitional Clustering Approach

One of the challenging tasks for Long Term Evolution (LTE) with Multiple Input Multiple Output (MIMO) configuration is to improve network performance. To efficiently optimize radio layer functionalities, quality characterization of physical parameters is performed with an experimental multivariate analysis. Partitional clustering techniques are used, in particular K-means is implemented to experiment with a non-overviewed, non-hierarchical algorithm. The analysis is carried out adopting R and its interface R study. Data are retrieved with a smart-phone based methodology during a drive test campaign. Measurements are eventually compared to 3rd Generation Partnership Project (3GPP) standard to evaluate the network and its behaviour.

[1]  Rudolf Mathar,et al.  Min-cut based partitioning for urban LTE cell site planning , 2013, 2013 IEEE 10th Consumer Communications and Networking Conference (CCNC).

[2]  Marco Donald Migliore,et al.  Development of the measurement method for challenging NLOS conditions in mobile networks , 2017, 2017 IEEE International Workshop on Measurement and Networking (M&N).

[3]  Stefano Avallone,et al.  Experimental Characterization of Long Term Evolution Multiple Input Multiple Output Performance in Urban Propagation Scenarios , 2018, 2018 Workshop on Metrology for Industry 4.0 and IoT.

[4]  Malika Charrad,et al.  NbClust: An R Package for Determining the Relevant Number of Clusters in a Data Set , 2014 .

[5]  Yue Chen,et al.  An intelligent scheduling architecture for mixed traffic in LTE-Advanced , 2012, 2012 IEEE 23rd International Symposium on Personal, Indoor and Mobile Radio Communications - (PIMRC).

[6]  Hano Wang,et al.  Pilotless Channel Estimation Scheme using Clustering-based Unsupervised Learning , 2018, 2018 15th International Symposium on Wireless Communication Systems (ISWCS).

[7]  Stefano Avallone,et al.  Smartphone-based measurements of LTE network performance , 2017, 2017 IEEE International Instrumentation and Measurement Technology Conference (I2MTC).

[8]  Purnendu Karmakar,et al.  Performance evaluation of LTE network: An energy saving and capacity gain perspective , 2016, 2016 International Conference on Advances in Computing, Communications and Informatics (ICACCI).

[9]  Nikos Dimitriou,et al.  Using clustering techniques to improve capacity of LTE networks , 2015, 2015 21st Asia-Pacific Conference on Communications (APCC).

[10]  David M. Mount,et al.  A local search approximation algorithm for k-means clustering , 2002, SCG '02.

[11]  Louay M. A. Jalloul,et al.  A Low-Complexity Detection Algorithm for the Primary Synchronization Signal in LTE , 2015, IEEE Transactions on Vehicular Technology.

[12]  Sunghyun Choi,et al.  COALA: Collision-Aware Link Adaptation for LTE in Unlicensed Band , 2018, 2018 15th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON).

[13]  David Grace,et al.  Using k-means clustering with transfer and Q learning for spectrum, load and energy optimization in opportunistic mobile broadband networks , 2015, 2015 International Symposium on Wireless Communication Systems (ISWCS).

[14]  Thuong Le-Tien,et al.  LTE indoor MIMO performances field measurements , 2014, 2014 International Conference on Advanced Technologies for Communications (ATC 2014).

[15]  Saeid Homayouni,et al.  AN EFFICIENT INITIALIZATION METHOD FOR K-MEANS CLUSTERING OF HYPERSPECTRAL DATA , 2014 .

[16]  Oskars Ozolins,et al.  K-means Clustering based Multi-Dimensional Quantization Scheme for Digital Mobile Fronthaul , 2018, 2018 Optical Fiber Communications Conference and Exposition (OFC).

[17]  David R. Hunter,et al.  mixtools: An R Package for Analyzing Mixture Models , 2009 .

[18]  Stefano Avallone,et al.  Experimental characterization of lte adaptive modulation and coding scheme under actual operating conditions , 2017, 2017 IEEE International Workshop on Measurement and Networking (M&N).

[19]  Kumbesan Sandrasegaran,et al.  Sinr , Rsrp , Rssi and Rsrq Measurements in Long Term Evolution , 2015 .