免疫模糊算法在电网规划中的应用

Application of immune fuzzy algorithm to transmission network planning

分析了标准遗传算法由于早熟收敛而无法快速有效地得到全局最优解的缺点,并以电网规划为应用背景,提出了一种免疫模糊算法.该算法借鉴信息熵概念对抗体浓度进行免疫调节,同时考虑亲和度概率和浓度抑制概率,在保留抗体特异性的同时有效维持解群分布的多样性;采用模糊控制规则来确定免疫算法的变异率,通过观察2个输入量的数值变化自适应调整高频变异的变异率,在增加群体多样性的同时进行局部搜索.通过仿真算例证明了该算法具有避免早熟、搜索速度快的特点,与同类优化方法相比具有明显的优越性,是求解电网规划问题行之有效的方法.

The cause of premature convergence of the standard genetic algorithm was summarized, and an immune fuzzy algorithm which taking transmission network planning as application background was presented. The algorithm adjusts the antibody concentration based on the conception of informative entropy of the gene. Considering both the probability of affinity and the probability of concentration suppression, the algorithm can keep the antibody specificity and maintain the population diversity at the same time. The algorithm adaptively sets the mutation rate of somatic hypermutation according to the changes of two input values of fuzzy control, thus increases the population diversity and searches the local optima simultaneously. The simulation demonstrated that the proposed algorithm could escape the premature convergence with better performance compared with other methods, and its feasibility and effectiveness for transmission net- work planning were also proved.