An empirical comparison of evolutionary algorithms for evolvable with minimum time-to-reconfigure requirements

Reconfigurability allows systems to adapt to changing operational environments. However, the time it takes to reconfigure cannot be ignored. Indeed, some critical systems must finish any reconfiguration within tight timeframes. This raises an important question: can an evolutionary algorithm designed to quickly search for the best initial configuration also be able to quickly search for a good reconfiguration? This paper reports the results of a study designed to identify those evolutionary algorithm features that help minimize the search time for reconfigurations of previously configured hardware. An active, analog filter reconfiguration problem is used as a test case.