Leakage Conscious DVS Scheduling for Peak Temperature Minimization

In this paper, we incorporate the dependencies among the leakage, the temperature and the supply voltage into the theoretical analysis and explore the fundamental characteristics on how to employ dynamic voltage scaling (DVS) to reduce the peak operating temperature. We find that, for a specific interval, a real-time schedule using the lowest constant speed is not necessarily the optimal choice any more in minimizing the peak temperature. We identify the scenarios when a schedule using two different speeds can outperform the one using the constant speed. In addition, we find that the constant speed schedule is still the optimal one to minimize the peak temperature at the temperature stable status when scheduling a periodic task set. We formulate our conclusions into several theorems with formal proofs.