TY - GEN
T1 - Understanding the complexity of 3G UMTS network performance
AU - Chen, Yingying
AU - Duffield, Nick
AU - Haffner, Patrick
AU - Hsu, Wen Ling
AU - Jacobson, Guy
AU - Jin, Yu
AU - Sen, Subhabrata
AU - Venkataraman, Shobha
AU - Zhang, Zhi-Li
PY - 2013/12/26
Y1 - 2013/12/26
N2 - With rapid growth in smart phones and mobile data, effectively managing cellular data networks is important in meeting user performance expectations. However, the scale, complexity and dynamics of a large 3G cellular network make it a challenging task to understand the diverse factors that affect its performance. In this paper we study the RNC (Radio Network Controller)-level performance in one of the largest cellular network carriers in US. Using large amount of datasets collected from various sources across the network and over time, we investigate the key factors that influence the network performance in terms of the round-trip times and loss rates (averaged over an hourly time scale). We start by performing the 'first-order' property analysis to analyze the correlation and impact of each factor on the network performance. We then apply RuleFit - a powerful supervised machine learning tool that combines linear regression and decision trees - to develop models and analyze the relative importance of various factors in estimating and predicting the network performance. Our analysis culminates with the detection and diagnosis of both 'transient' and 'persistent' performance anomalies, with discussion on the complex interactions and differing effects of the various factors that may influence the 3G UMTS (Universal Mobile Telecommunications System) network performance.
AB - With rapid growth in smart phones and mobile data, effectively managing cellular data networks is important in meeting user performance expectations. However, the scale, complexity and dynamics of a large 3G cellular network make it a challenging task to understand the diverse factors that affect its performance. In this paper we study the RNC (Radio Network Controller)-level performance in one of the largest cellular network carriers in US. Using large amount of datasets collected from various sources across the network and over time, we investigate the key factors that influence the network performance in terms of the round-trip times and loss rates (averaged over an hourly time scale). We start by performing the 'first-order' property analysis to analyze the correlation and impact of each factor on the network performance. We then apply RuleFit - a powerful supervised machine learning tool that combines linear regression and decision trees - to develop models and analyze the relative importance of various factors in estimating and predicting the network performance. Our analysis culminates with the detection and diagnosis of both 'transient' and 'persistent' performance anomalies, with discussion on the complex interactions and differing effects of the various factors that may influence the 3G UMTS (Universal Mobile Telecommunications System) network performance.
UR - http://www.scopus.com/inward/record.url?scp=84890821726&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84890821726&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84890821726
SN - 9783901882555
T3 - 2013 IFIP Networking Conference, IFIP Networking 2013
BT - 2013 IFIP Networking Conference, IFIP Networking 2013
T2 - 2013 IFIP Networking Conference, IFIP Networking 2013
Y2 - 22 May 2013 through 24 May 2013
ER -