| Summary: | The design of radiofrequency circuits and systems lends itself to multi-objective optimization and the bottom-up composition of Pareto-optimal fronts. Conventional multi-objective optimization algorithms can effectively attain these fronts, which maximize or minimize a set of competing objective functions of interest. However, some of these real-life optimization problems reveal a non-conventional feature: there is one objective function that calls neither for minimization nor maximization. Instead, using the Pareto front demands this objective function to be swept across so that all its feasible values are available. Such a non-conventional feature, as shown here, emerges in the case of inductor optimization. The problem thus turns into a non-conventional one: determining how to find uniformly distributed feasible values of this function over the broadest possible range (typically unknown) while minimizing or maximizing the remaining competing objective functions. An NSGA-II-inspired algorithm is proposed that, based on the dynamic allocation of objective function slots and a modified dominance definition, can successfully return sets of solutions for inductor optimization problems with one sweeping objective. Furthermore, a mathematical benchmark function modeling this kind of problem is presented, which is also used to exhaustively test the proposed algorithm and obtain insight into its parameter settings.
|
|---|