Mitigating The Latency-Accuracy Trade-off In Mobile Data Analytics Systems

Authors:
Anand Padmanabha Iyer UC Berkeley
Li Erran Li Uber
Mosharaf Chowdhury University of Michigan
Ion Stoica UC Berkeley

Introduction:

An increasing amount of mobile analytics is performed on data that is procured in a real-time fashion to make real-time decisions. the authors present CellScope, a system that applies a domain specific formulation and application of Multi-task Learning (MTL) to RAN performance analysis.

Abstract:

An increasing amount of mobile 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 these analyses are impeded in several domains because they are faced with a fundamental trade-of between data collection latency and analysis accuracy. In this paper, we first study this trade-of in the context of a specific domain, Cellular Radio Access Networks (RAN). We find that the trade-of 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 applies a domain specific formulation and application of Multi-task Learning (MTL) to RAN performance analysis. It uses three techniques: feature engineering to transform raw data into efective features, a PCA inspired similarity metric to group data from geographically nearby base stations sharing performance commonalities, and a hybrid online-ofline model for eficient model updates. Our evaluation shows that CellScope's 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 an LTE network of over 2 million subscribers, where it reduced troubleshooting eforts by several magnitudes.

You may want to know: