The comparison of Self-organized map and k-means algorithms used for 4G
network performance evaluation
Abstract
With the increasing complexity of mobile networks, it has become more
and more difficult to perform effective management of mobile networks,
which has led to more data to be evaluated and optimized. This article
focuses on the performance evaluation of Long Term Evolution(LTE)
networks by using two unsupervised learning techniques. Besides, this
paper aims to identify the pros and cons of these two clustering
algorithms as well. To achieve the above goals, different dimensional
datasets for learning a process based on two classic unsupervised
clustering methodsare introduced to this work. A Self-organized map
(SOM) neural network and k-means are a comparison algorithm and the
sample data with three different degree correlation coefficients
features with 63 LTE cells, which is from a major European city. The
purpose behind using these two methods is to see how different
dimensions of the datasets can be used for testing clustering effec
tiveness and we propose a method based on the features extracted from
key performance indicators (KPIs) and Euclidean distance is used as the
evaluation standard for the distance between different clusters and
samples within clusters. The comparing results show that k-means has a
better cluster performance in low dimension data set, whereas the SOM’s
performance unsatisfactory. On the other hand, the SOM’s clustering
performance is better than k-means in high dimension and big data set
and it could visualize results. It was verified that there is a
significant difference in the obtained results using different
clustering algorithms.