Abstract: Aiming at traditional quantum particle swarm algorithm in solving the database query optimization problems has slow convergence speed and premature convergence, a novel query optimization method of database based on Gauss Mutation Quantum behaved Particle Swarm Optimization algorithm（GM-QPSO）. Firstly, the mutation operator of the genetic algorithm is introduced into quantum particle swarm optimization algorithm to improve the global search ability, the particle position changes in a small range of the approximate optimal solution, and then it is applied to solve the query optimization problem of database, and the performance of GM-PSO is tested by simulation experiments. The results show that, GM-QPSO accelerates the convergence speed of database query optimization and can obtain higher quality query optimization scheme.

Key words: database, optimization query, particle swarm optimization algorithm, quantum behaved, Gauss mutation

摘要： 针对量子粒子群算法解决数据库查询优化问题存在缺陷，提出一种高斯变异量子粒子群算法的数据库查询优化方法（GM-QPSO）。首先将遗传算法的变异算子引进量子粒子群优化算法，使得粒子在近似最优解附近变动提高全局搜索能力，然后将其应用于数据库查询优化问题求解，最后通过仿真实验对GM-QPSO的性能进行测试。结果表明，GM-QPSO加快了数据库查询优化求解的收敛速度，获得了质量更高的查询优化方案。

关键词: 数据库, 查询优化, 粒子群优化算法, 量子行为, 高斯变异