Supporting health smart system applications in Scientific Gateway environment

Smart system applications are spreading worldwide, specifically health monitoring has gained outstanding interest and importance over the last years. Data captured from sensors arrive continuously and only efficient large scale data handling using data stream processing can cope with the transport requirements. Stream processing means that without intermediate storage the data should be processed as they are received from the sensors. In this paper we have developed a simulation environment and we have investigated the influencing factors of the time needed to execute the jobs. Our goal was to optimize the overall time needed to submit the smart system application. With the help of statistical tools we have also performed computations and in case of different middlewares and storages we have carried out measurements. The results show that the job submission time is minimal for applications that use Direct Cloud access in Pgrade/gUSE/DCI-Bridge environment. We have also investigated the effects of the parallelization degree on the system efficiency and the results show that until a certain degree the parallelization also positively effects the system's throughput.

I. Introduction

Smart systems are targeted to collect data from sensors positioned into the observed process, and from the collected data to analyze, operate and control the system in order to gain better efficiency. These systems incorporate functions of sensing, actuation, and control in order to describe and analyze the environment/situation, and make decisions based on the available data in a predictive or adaptive manner, thereby performing smart actions.