Abstract:

Based on the randomness, fuzziness and stability  of cloud model,  an adaptive quantum particle swarm optimization algorithm CMAQPSO based on normal cloud model is proposed. The algorithm uses X conditional cloud generator to control the contraction expansion coefficient of QPSO algorithm, and uses Y condition cloud generator to construct the mutation operator of QPSO algorithm. A quantum well center adjustment strategy and boundary correction strategy are proposed. The experimental results show that the average optimization effect of the CMAQPSO algorithm on the five test functions is significantly better than the other three algorithms (SPSO, OPSO,CVCPSO).

Key words: normal cloud model, self-adaptive, quantum particle swarm, quantum-behaved particle swarm optimization algorithm