Supporting fault-tolerant on-board evolution in aerospace reconfigurable platform

Due to long distance and terrible environment, it is difficult to maintain spacecrafts once they were launched. Traditional on-board software maintenance (OBSM) often fails because of broken communication and unexpected situation. This has generated a pressing need for self-adaptive, self-repairing and self-upgrading capabilities in On-Board Maintenance (OBM) applications. In this paper, we propose a fault-tolerant onboard evolutionary platform which implements relocation of hardware and software tasks in spaceborne computing systems. Tasks can either run in software space or be put into hardware task slots according to energy-efficient or real-time requirements. The allocation of hardware and software tasks will evolve in terms of current condition to meet real-time, energy-efficient or environment requirements. Sleeping tasks, redundant FPGAs and version switching control are combined together to achieve fault-tolerance in the on-board evolutionary platform. The design theories and strategies of proposed prototype are described in detail. Simulation and experiment results are discussed as well.