This paper intends to investigate the sensitivity of Differential Evolution (DE) algorithm towards Pseudo Random Number Generator (PRNG) quality. Towards this, the impact of six PRNGs on the performance quality of 14 DE variants in solving nineteen 10-Dimensional benchmark functions has been studied. The results suggest that DE algorithm is insensitive to the quality of PRNG used.
L. Rajashekharan and Dr. Shunmuga Velayutham C., “Is Differential Evolution Sensitive to Pseudo Random Number Generator Quality? – An Investigation”, in Intelligent Systems Technologies and Applications: Volume 1, S. Berretti, Thampi, S. M., and Srivastava, P. Ranjan, Eds. Cham: Springer International Publishing, 2016, pp. 305–313.