Thermal aware overall energy minimization scheduling for hard real-time systems

As the semiconductor technology proceeds into the deep sub-micron era, the leakage and its dependency with the temperature become critical in dealing with power/energy minimization problems. In this paper, we study the problem on how to schedule a hard real-time system to achieve the minimal overall energy, including both dynamic and leakage energy consumption. We first develop an energy estimation method that can be used to accurately and efficiently calculate the overall energy consumption of a candidate schedule. Based on the proposed energy equation, we then develop two scheduling methods, i.e. an off-line and an on-line method, to minimize the overall energy consumption for real-time systems. Our experimental results demonstrate that the proposed energy estimation method can achieve up to two orders of magnitude speedup compared with an existing approach while maintaining good accuracy. In addition, with a large number of different test cases, both our off-line and on-line approaches can significantly outperform existing related works.