Autonomous Distribution Architecture on Progressing Topologies and Optimization of Resources

Computing resources available at or nearby a Cyber-physical system have much slower upgrade cycles than the algorithms they serve. This makes maintenance very expensive as physical access by experts becomes necessary for upgrades or complete replacements. ADAPTOR extends the autonomy of these systems by building an intelligent fog/edge solution able to aggregate all resources of interconnected devices into a single distributed pool and assign tasks to it. At the core of the solution is an adaptive distributed scheduler of tasks to resources able to detect emerging patterns and serve unforeseen applications, hardware performance and usage patterns. The distributed scheduler tries to accurately predict the availability of resources at the moment of resource commissioning to maximize resource utilization and task throughput. Both our diverse use cases, electron-microscopy and space-based radio telescope swarms, bring challenges on time-sensitivity, tight resource constraints and scalability.