Aiming at the problems of poor performance and slow convergence of existing symbiotic organisms search(SOS) algorithm in solving discrete optimization problems such as path planning, this paper proposed the virtual multi-task SOS(VMTSOS). Firstly, according to the bidirectional mapping decoding strategy, it realized the transformation between individual continuous spatial position and discrete city sequence. Secondly, it introduced the idea of multi-task optimization to construct a virtual multi-task environment, designed multiple populations to optimize the same task simultaneously, and the stagnation threshold controlled the frequency of information transfer between populations. Once the main population reached the stagnation threshold, it replaced some excellent individuals in the auxiliary population with inferior individuals in the main population. Finally, it analyzed the time and space complexity of VMTSOS. Experiment results show that VMTSOS converges rapidly to the current optimal solution of each test case when solving most TSP problems, while VMTSOS with multiple groups assistance mechanisms can greatly reduce the optimal total cost when solving cold chain logistics distribution problems.

[2023-06-26] Accepted Paper /doc/2023.04.0152/v1

[2023-12-05] Printed Article /doc/2023.04.0152/v2