Thermal issues in the cyber part of cyber-physical systems (CPSs) has attracted considerable attention in recent years. Heat generation due to energy consumption results in accelerated thermal damage to the processing units, reducing their lifetime. Fault tolerance contributes to a large fraction of this thermal behavior in CPS since it is implemented using redundant computations. This paper studies the use of dynamic actuator derating (i.e., artificially limiting the maximum actuator output) for reducing the need to apply maximum redundancy. By targeting the use of fault-tolerance, we are able to obtain significant reductions in computer energy expenditure and thermal stress without lowering the reliability. This has beneficial effects on processor lifetime as well as the required energy storage.

近年来，网络物理系统（CPS）的网络部分中的热量问题引起了相当大的关注。由于能量消耗而产生的热量会加速对处理单元的热损伤，从而缩短其使用寿命。由于容错是使用冗余计算实现的，因此它在CPS中的热性能中占很大比例。本文研究了动态执行器降额使用（即人为限制最大执行器输出）以减少应用最大冗余的需求。通过针对容错的使用，我们能够在不降低可靠性的情况下显着减少计算机能耗和热应力。这对处理器寿命以及所需的能量存储有有益的影响。