Differential Evolution with Taguchi Crossover Using Polar Coordinates
Lecture Notes in Networks and Systems
First page number:
Last page number:
© 2021, Springer Nature Switzerland AG. This paper compares the performance of two differential evolution algorithms. The algorithms are identical except that one of the algorithms is implemented in rectangular coordinates and the other algorithm is implemented using both rectangular and a cascade of terms in polar coordinates. Both algorithms use an elitist, ranking, random selection method and both two and three level Taguchi crossover. To compare the performance of the algorithms, both algorithms are applied to 13 commonly used global numerical optimization test functions, including a spherical, three hyper-ellipsoid, the sum of different powers, Rastrigin’s, Schwefel’s, Griewank’s, Rosenbrock’s valley, Styblinski-Tang, Ackley’s Path, Price-Rosenbrock, and Eggholder’s functions. The test results show that the algorithm that is implemented using both rectangular and polar coordinates performed better than the algorithm implemented using only rectangular coordinates.
Averaging crossover; Compare; Differential evolution; Elitist selection; Genetic algorithm; Polar coordinates; Random selection; Ranking selection; Rectangular coordinates; Taguchi crossover
Computer Engineering | Systems and Communications
Differential Evolution with Taguchi Crossover Using Polar Coordinates.
Lecture Notes in Networks and Systems, 182