Efficient Scheduling for Data Processing in Large-scale Sensory Environments

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, Delta 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.