It is well known that when the fitness function is relatively complex, the optimization time cost of the genetic algorithm will be extremely large. To address this issue, the surrogate model was employed to predict the fitness value of the optimization problem in order to reduce the number of actual calculated fitness values. In this project, the tSNE(t-Stochastic neighbour Embedding), the least-square method, and Affinity Propagation were fused in the genetic algorithm to evaluate partial individuals’ fitness. Sufficient benchmark numerical experiments were conducted, and the results proved that the strategy could reduce the number of calculations of the fitness function with similar accuracy to that of a simple genetic algorithm.
JLU-Neal/ModifiedGA
It is well known that when the fitness function is relatively complex, the optimization time cost of the genetic algorithm will be extremely large. To address this issue, the surrogate model was employed to predict the fitness value of the optimization problem in order to reduce the number of actual calculated fitness values. In this project, the tSNE(t-Stochastic neighbour Embedding), the least-square method, and Affinity Propagation were fused in the genetic algorithm to evaluate partial individuals’ fitness. Sufficient benchmark numerical experiments were conducted, and the results proved that the strategy could reduce the number of calculations of the fitness function with similar accuracy to that of a simple genetic algorithm.
Python