Energy-Efficient Real-Time Task Scheduling with the Considerations of Hardware and Software Characteristics

• Main Authors: Chuan-Yue Yang, 楊川岳
• Other Authors: Tei-Wei Kuo
• Format: Others
• Language: en_US
• Published: 2010
• Online Access: http://ndltd.ncl.edu.tw/handle/30657814053280620164

博士 === 臺灣大學 === 資訊工程學研究所 === 98 === Energy-aware design for electronic systems has been an important issue in hardware and software implementations. Dynamic voltage scaling (DVS) techniques have been adopted to effectively trade the performance for the energy consumption. However, most existing research for energy-efficient design in DVS systems with real-time constraints focuses on tasks with worst-case execution times. In this dissertation, we propose two types of approaches to efficiently and effectively minimize the energy consumption to schedule a set of periodic real-time tasks with the multiframe property, in which the execution times of task instances are characterized by a vector of elements that are repeated. By assigning an execution speed to each task frame, the proposed frame-based approach can approximate the optimal solutions with limited memory space. As system devices often make a significant contribution to the power consumption of the entire system in reality, effective energy-efficient scheduling algorithms should consider not only the energy consumption of the processor but also the usages of devices. Thus, we propose scheduling algorithms in the management of task preemption to reduce the energy consumption of non-DVS devices. Moreover, leakage power consumption which depends on temperature contributes significantly to the overall power dissipation for systems that are manufactured in advanced deep sub-micron technology. Different from many previous results, we explore leakage-aware energy-efficient scheduling over processors with temperature-dependent leakage power consumption as the conclusion of this dissertation. Since the proposed pattern-based approach leads to a steady state with an equilibrium temperature, we develop a procedure to find the optimal pattern whose energy consumption in steady state is the minimum.