摘要
提出了一种新的求解约束优化问题的演化算法——基于混合策略求解约束优化问题的演化规划算法(CMSEP).借鉴了Mezura-Montes的算法中直接比较的约束处理方法,为求解位于边界附近的全局最优解采用多样性保护机制,允许一定比例最好不可行解进入下一代种群,混合策略变异机制用于指导算法快速搜索过程.标准测试函数的实验结果验证了算法的通用性和有效性.
A mixed strategies evolutionary programming to solve constrained optimization problems is presented in this paper. The approach does not require the use of a penalty function. Instead, it uses a diversity conservation mechanism based on allowing infeasible solutions to remain in the population. A mixed mutation strategy and feasibility-based comparison mechanism is used to guide the process fast toward the feasible region of the search space. This new evolutionary programming has been tested on 13 benchmark functions. The results obtained show that the new approach is a general and effective method.
出处
《计算机研究与发展》
EI
CSCD
北大核心
2006年第5期841-850,共10页
Journal of Computer Research and Development
基金
国家自然科学基金项目(60443003)
北京交通大学科技基金项目(2003SZ003)~~
关键词
约束优化
混合策略
多样性保护机制
演化规划
constrained optimization
mixed strategy
diversity conservation mechanism
evolutionary programming
