一种新型量子粒子群算法

本文提出一种基于量子的连续粒子群算法(Quantum Continuous Particle Swarm Optimization-QCPSO),使用量子比特编码粒子,模拟量子粒子坍塌的随机观察方法以生成种群,运用量子旋转门来产生新的种群,引入自适应变异算子保证种群多样性。性能测试表明,对于高维优化问题,本文提出的QCPSO比经典粒子群算法(PSO)和经典量子粒子群算法(AQPSO)具有更高的精度。

A Novel Quantum Continuous Particle Swarm Optimization Algorithm

In this paper, a novel algorithm, called the Quantum Continuous Particle Swarm Optimization algorithm - QCPSO, is proposed, based on the combination of the quantum theory with the evolutionary theory. By adopting the qubit particle as the representation, QCPSO can represent a linear superposition of solutions and bring diverse individuals by imitating the quantum collapse to random observation the new populations. The evolution of quantum particles can also pilot the evolution with better diversity than the classical particle swarm optimization method by adopting adaptive mutation.The performance test indicates that the QCPSO possesses better global search capacity than the basic PSO and QPSO when confronting high dimension problems.