论文部分内容阅读
阐述免疫遗传学的基本原理,对传统免疫遗传算法做了改进.模拟抗体两次应答抗原的机理,引入信息熵计算抗原间的亲和力,选择亲和力高且相似度低的抗体遗传到后代,运用细胞记忆机制保存优良抗体,并令记忆细胞参与进化。避免算法陷入局部最优值.在此基础上,提出一种更新的相位配时优化算法对交通信号控制问题进行探讨,并设计相应的仿真实验.对一个四相位单交叉路口的交通流进行建模和分析,实验结果验证该算法处理交通配时优化问题的可行性和有效性.
The basic principles of immune genetics are described and the traditional immune genetic algorithm is improved.Making the mechanism that the antibody responds twice to antigen, introducing information entropy to calculate the affinity between the antigen, selecting the antibody with high affinity and low similarity to the offspring, using the cell Memories preserve excellent antibodies and make memory cells involved in evolution. To avoid falling into the local optimum algorithm.On the base of this, a new phase allocation optimization algorithm is proposed to solve the problem of traffic signal control, and to design the corresponding simulation experiment.Analyze the traffic flow of a four-phase single-intersection The results show that this algorithm is feasible and effective in dealing with traffic timing optimization problems.