[Zurück]

A. Alexandrescu, F. Li, S. Dustdar, M. Craus:
"Efficient Scheduling for Data Processing in Large-scale Sensory Environments";
Journal of Applied Sciences, Volume 12 (2012), Issue 19; S. 2006 - 2015.

In recent years, there has been an emergence of systems that employ large numbers of sensory devices to collect information from the real-world and to react in observed situations, e.g., smart buildings and smart grids. In such systems, massive amounts of data need to be collected and processed in near real-time. This research proposes an efficient method of processing sensory data by considering that each data transmission and processing is a task which has to be scheduled for execution to a gateway. The proposed heuristic, Weighted Minimum Completion Time (WMCT), was compared against five mapping heuristics by using five efficiency indicators-execution time, makespan, Δ time difference, solution worth and success rate. The experiments have shown that the WMCT heuristic outperforms the other methods in terms of the success rate, the solution´s worth and especially, the execution time of the algorithm, while it obtained good results in regards to the other two efficiency indicators.

http://dx.doi.org/10.3923/jas.2012.2006.2015

Projektleitung Schahram Dustdar:
Cloud computing research lab