Self-aware sensing and attention-based data collection in Multi-Processor System-on-Chips

Self-awareness is the foundation for many of the nowadays desired system characteristics, such as self-optimization and self-adaption. This awareness is rooted in observation and sensory data obtained by the system regarding itself and its environment. Given the important role which data collection plays in creating this awareness, we believe that it merits more attention than it has so far received. For example, increasing the amount of collected data can overload the system with increased computational cost, communication load, and power consumption. Self-awareness can help the system by making data collection smarter and better oriented. In this paper, we propose an attention-based data collection method, inspired by self-awareness, and exploit its potential in the context of Multi-Processor System-on-Chips (MPSoCs). Our case study shows that this method can reduce the computation and communication load related to processing sensory data up to 95%, at the cost of a negligible overhead at the sensor node.