An overhead-aware optimal energy-efficient real-time scheduling algorithm on multiprocessors

作者：Zhang Dong Song^*; Wu Fei; Chen Fang Yuan; Wu Tong; Guo De Ke; Jin Shi Yao

来源：Chinese Journal of Computers, 2012, 35(6): 1297-1312.

DOI：10.3724/SP.J.1016.2012.01297

• Dynamic power management
• Dynamic voltage frequency scaling
• Energy-Efficient Scheduling
• Green computing
• Multiprocessor

As the energy consumption of embedded multiprocessor systems becomes increasingly prominent, the energy-efficient real-time scheduling in multiprocessor systems becomes an urgent problem. Most research efforts are based on the critical speed to reduce frequencies of processors for reducing the dynamic power consumption. Meanwhile, off-processor approach is also used to reduce the static power consumption. However, such approaches cannot achieve the minimum energy savings. In the other hand, the optimal energy-efficient real-time scheduling ignores the time and energy overhead of switching the processor state and thus is not optimal in actual platforms. For multiprocessors with the independent dynamic voltage frequency and dynamic power management, this paper proposes an optimal energy-efficient real-time scheduling algorithm for the frame-based tasks. The proposed optimal algorithm determines the system workload cases and the number of active processor cores in terms of the critical speed. Then we can obtain the optimal scheduling according to the switching overhead. The algorithm allows tasks to arbitrarily migrate across processors during their executions at the cost of the small computational complexity. Furthermore, it is easy to be implemented. Mathematical analysis shows that the algorithm is optimal.

• 出版日期2012