应急资源调度问题的改进进化规划算法研究

Research on Improved Evolutionary Programming Algorithm for Solving the Problem of Emergency Resources Scheduling

针对应急资源调度问题,建立一种多资源时间-成本调度模型。设计了进化规划算法的全局变异算子和局部变异算子,根据全局变异前后个体适应度值和分量值的变化趋势,实现定向变异。构建了具有惩罚系数的适应度函数,给出了改进的进化规划算法种群进化策略。计算实验表明,改进的进化规划算法具有较强的局部寻优能力,在收敛速度和求解精度方面优于比较的遗传算法、差分进化算法和进化规划算法,解决了标准进化算法的早熟收敛问题。

A multi-resource time-cost model is proposed for the problem of emergency resources scheduling. Global mutation operator and local mutation operator of evolutionary programming are designed, and local mutation operator can achieve directional mutation according to the trend of fitness and component value of individual before and after global mutation. Then, it constructs the fitness function with penalty coefficient, and gives the strategy of population evolution of improved evolutionary programming（IEP）. An experiment has been done for a set of data in Matlab, and the results show that the model is easy to calculate, and IEP is provided with stronger local search capability, and it is superior to genetic algorithm（GA）, differential evolution （DE）and evolutionary programming（EP） in the aspects of convergence speed and accuracy of solution. IEP solves the problem of premature convergence of standard evolutionary algorithms.