Anand Padmanabha Iyer, Ion Stoica, Mosharaf Chowdhury and Li Erran Li
EECS Department
University of California, Berkeley
Technical Report No. UCB/EECS-2016-114
May 17, 2016
http://www2.eecs.berkeley.edu/Pubs/TechRpts/2016/EECS-2016-114.pdf
An increasing amount of analytics is performed on data that is procured in a real-time fashion to make real-time decisions. Such tasks include simple reporting on streams to sophisticated model building. However, the practicality of such analyses are impeded in several domains because they are faced with a fundamental trade-off between data collection latency and analysis accuracy.
In this paper, we study this trade-off in the context of a specific domain, Cellular Radio Access Networks (RAN). Our choice of this domain is influenced by its commonalities with several other domains that produce real-time data, our access to a large live dataset, and their real-time nature and dimensionality which makes it a natural fit for a popular analysis technique, machine learning (ML). We find that the latency accuracy trade-off can be resolved using two broad, general techniques: intelligent data grouping and task formulations that leverage domain characteristics. Based on this, we present CellScope, a system that addresses this challenge by applying a domain specific formulation and application of Multi-task Learning (MTL) to RAN performance analysis. It achieves this goal using three techniques: feature engineering to transform raw data into effective features, a PCA inspired similarity metric to group data from geographically nearby base stations sharing performance commonalities, and a hybrid online-offline model for efficient model updates. Our evaluation of CellScope shows that its accuracy improvements over direct application of ML range from 2.5× to 4.4× while reducing the model update overhead by up to 4.8×. We have also used CellScope to analyze a live LTE consisting of over 2 million subscribers for a period of over 10 months, where it uncovered several problems and insights, some of them previously unknown.
BibTeX citation:
@techreport{Padmanabha Iyer:EECS-2016-114, Author = {Padmanabha Iyer, Anand and Stoica, Ion and Chowdhury, Mosharaf and Erran Li, Li}, Title = {Fast and Accurate Performance Analysis of LTE Radio Access Networks}, Institution = {EECS Department, University of California, Berkeley}, Year = {2016}, Month = {May}, URL = {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2016/EECS-2016-114.html}, Number = {UCB/EECS-2016-114}, Abstract = {An increasing amount of analytics is performed on data that is procured in a real-time fashion to make real-time decisions. Such tasks include simple reporting on streams to sophisticated model building. However, the practicality of such analyses are impeded in several domains because they are faced with a fundamental trade-off between data collection latency and analysis accuracy. In this paper, we study this trade-off in the context of a specific domain, Cellular Radio Access Networks (RAN). Our choice of this domain is influenced by its commonalities with several other domains that produce real-time data, our access to a large live dataset, and their real-time nature and dimensionality which makes it a natural fit for a popular analysis technique, machine learning (ML). We find that the latency accuracy trade-off can be resolved using two broad, general techniques: intelligent data grouping and task formulations that leverage domain characteristics. Based on this, we present CellScope, a system that addresses this challenge by applying a domain specific formulation and application of Multi-task Learning (MTL) to RAN performance analysis. It achieves this goal using three techniques: feature engineering to transform raw data into effective features, a PCA inspired similarity metric to group data from geographically nearby base stations sharing performance commonalities, and a hybrid online-offline model for efficient model updates. Our evaluation of CellScope shows that its accuracy improvements over direct application of ML range from 2.5× to 4.4× while reducing the model update overhead by up to 4.8×. We have also used CellScope to analyze a live LTE consisting of over 2 million subscribers for a period of over 10 months, where it uncovered several problems and insights, some of them previously unknown.} }
EndNote citation:
%0 Report %A Padmanabha Iyer, Anand %A Stoica, Ion %A Chowdhury, Mosharaf %A Erran Li, Li %T Fast and Accurate Performance Analysis of LTE Radio Access Networks %I EECS Department, University of California, Berkeley %D 2016 %8 May 17 %@ UCB/EECS-2016-114 %U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2016/EECS-2016-114.html %F Padmanabha Iyer:EECS-2016-114