摘要：Pervasive computing applications, such as video surveillance and robot control, involve diversified op- erations on physical devices. We call a sequence of operations on a device an action and study how to schedule real-time actions on the devices in pervasive computing. We identify a number of novel charac- teristics of this pervasive action scheduling problem and develop a dynamic, heuristic algorithm for the problem. The algorithm performs priority-based action scheduling whenever some device becomes free and does not reply on any system-defined scheduling interval. We have implemented our proposed ac- tion scheduling algorithm in a pervasive query processing system named Aorta and evaluated its per- formance using actions in a pervasive lab monitoring application. Our simulation results demonstrate the algorithm ensures small dropping rate of actions and has tiny computation cost.
