基于模拟退火的果蝇优化算法

针对果蝇算法（FOA）寻优精度不高且易陷入局部最优的缺陷，提出了一种基于模拟退火思想的果蝇优化算法（SA-FOA）。所提算法对解的接收机制和寻优步长进行了改进：以广义的Gibbs分布产生的概率为接收概率，解的接收满足Metropolis准则；参考非均匀变异的思想，使步长随迭代次数的增加逐渐减小。通过对几种典型测试函数的仿真表明，改进算法具有较强的全局搜索能力，同时寻优精度和收敛速度比果蝇算法也有较大的提高。因此，可以用改进算法对神经网络和服务调度问题的参数进行优化。

Fruit fly optimization algorithm based on simulated annealing

Concerning the defects of low optimization precision and easy to fall into local optimum in Fruit Fly Optimization Algorithm (FOA), a Fruit Fly Optimization Algorithm based on Simulated Annealing (SA-FOA) was proposed. The receiving mechanism of solution and the optimal step size were improved in SA-FOA. The receiving probability was based on the generalized Gibbs distribution and the receiving of solution met Metropolis criterion. The step length decreased with the increasing iteration according to non-uniform variation idea. The simulation result using several typical test functions show that the improved algorithm has high capability of global searching. Meanwhile, the optimization accuracy and convergence rate are also improved greatly. Therefore, it can be used to optimize the parameters of neural network and service scheduling models.