An efficient dataflow execution method for mobile context monitoring applications

In this paper, we propose a novel efficient dataflow execution method for mobile context monitoring applications. As a key approach to minimize the execution overhead, we propose a new dataflow execution model, producer-oriented model. Compared to the conventional consumer-oriented model adopted in stream processing engines, our model significantly reduces execution overhead to process context monitoring dataflow reflecting unique characteristics of context monitoring. To realize the model, we develop DataBank, an execution container that takes charge of the management and delivery of the output data for the associated operator. We demonstrate the effectiveness of DataBank by implementing three useful applications and their dataflow graphs, i.e., MusicMap, FindMyPhone, and CalorieMonitor. Using the applications, we show that DataBank reduces the CPU utilization by more than 50%, compared to the methods based on the consumer-oriented model; DataBank enables more context monitoring applications to run concurrently.

I. Introduction

Context monitoring applications [4] [5] [6] are increasingly emerging and becoming a major workload of smartphones. The applications continuously monitor contexts of users to provide situation-aware services. Their core is to transform high-rate raw sensing data to context information through a complex series of processing steps. Such a series of processing is commonly represented as a dataflow graph of operators. For example, SoundSense [4] continuously collects audio data from a microphone at 8 kHz, and subsequently applies more than 20 feature extraction and classification operations such as fast Fourier transform (FFT), mel-frequency cepstral coefficients (MFCC), and Gaussian mixture model (GMM).