Online Fault Tolerant Energy-Aware Algorithm for CubeSats

International audienceEnergy and reliability constraints play an important role in performances of embedded multiprocessor systems. This paper proposes an online fault tolerant energy-aware scheduling algorithm called OneOffEnergy. It is designed for energy-constrained applications, such as CubeSats, with aim to make these small satellites more robust and to reduce energy consumption. We propose to take advantage of multiprocessor architecture and put together all CubeSat processors on one board. This multiprocessor system makes use of our devised algorithm, which schedules all tasks aboard a CubeSat, detects faults and takes appropriate measures in order to deliver correct results subject to limited energy resources.OneOffEnergy operates in two processor modes (Run and Standby) to save energy and considers three system modes (normal, safe and critical) related to the task priorities depending on the current energy stored in the battery. In order to show the wide algorithm usability, OneOffEnergy was not only evaluated for CubeSats but also in the context of another energy-constrained application.It is shown that the implementation of OneOffEnergy aboard a CubeSat reduces energy consumption. The results demonstrate that putting processors in Standby mode brings energy savings and OneOffEnergy exhibits better performances in terms of the system operation under energy constraints when compared to simpler algorithms. Finally, it was found that OneOffEnergy also performs well in a harsh environment