الفهرس | Only 14 pages are availabe for public view |
Abstract In the design of embedded systems, it is very important to reduce energy consumption, and thus prolong battery life in ubiquitous battery- powered embedded systems which are involved in all details of our everyday life. Dy~ic voltage scaling (DVS) processors, which support many operating voltages/speeds, can efficiently reduce energy consumption by making appropriate decisions on the processor speed/voltage during the scheduling of the real time tasks provided that each task has to meet its deadline. This thesis addresses the problem of energy efficient real time task scheduling over earliest deadline first (EDF) scheduling policy where the tasks are dependent due to exclusive access shared resources. Furthermore, the thesis proposes enhancements over two existing algorithms; dual speed (DS) algorithm and multi speed (MS) algorithm, where the proposed algorithms; enhanced DS (EDS) and improved MS (lMS), achieve more energy saving and have the capability to function with both stack resource policy (SRP) and dynamic priority ceiling protocol (DPCP) as resource access protocols. KEYWORDS: Energy efficient scheduling, dynamic voltage scaling, embedded systems, real time systems, shared resources, dependent tasks. |