Energy-Aware Modeling and Scheduling of Real-Time Tasks for Dynamic Voltage Scaling

Abstract— Dynamic voltage scaling (DVS) is a promising technique for battery-powered systems to conserve energy consumption. Most existing DVS algorithms assume information about task periodicity or a priori knowledge about the scheduled task set. This paper presents an analytical model of general tasks for DVS assuming job timing information is known only after task releases. The voltage scaling process is modeled as a transfer function-based filter system. The filtering model facilitates the design of two efficient scaling algorithms. The first is a timeinvariant scaling policy with a constant time complexity based on a voltage scaling function independent of input jobs over time. Several existing approaches are special cases of the policy with respect to energy savings. A time-variant policy is derived for more energy savings with a time complexity of O(N), where N is the number of distinct deadlines. It can be not only applied to scheduling based on worst case execution times...

• Type: Conference
• Year: 2005
• Where: RTSS
• Authors: Xiliang Zhong, Cheng-Zhong Xu
• Keywords: Applied Computing, Dynamic Voltage Scaling, RTSS 2005, Voltage Scaling, Voltage Scaling Process