一种求解最优机组组合问题的随机扰动蚁群优化算法

针对蚁群优化算法中易出现的停滞现象，设计出一种新颖的随机扰动蚁群优化算法。该算法包含了两个重要方面：一是提出了采用倒指数曲线来描述的扰动因子；二是设计出了相应的随机选择策略和扰动策略。此外，还对该算法中参数的选取方法及取值范围进行了研究和探讨。利用该算法求解最优机组组合问题，并在模型的转化、约束项的处理等方面进行了深入的分析。通过对两个测试系统进行计算，并与基本蚁群算法进行比较，证明了该算法可以有效地克服基本蚁群算法计算时间较长和容易出现停滞现象的缺陷，具有更好的全局优化能力。

AN ANT COLONY OPTIMIZATION ALGORITHM WITH RANDOM PERTURBATION BEHAVIOR FOR UNIT COMMITMENT PROBLEM

Based on the basic ant colony optimization algorithm, a novel ant colony optimization algorithm with random perturbation behavior (RPACO) is presented. The new algorithm includes two important aspects: a perturbation factor formulated by inverse exponent function is developed, on the other hand, corresponding transition strategy with random selection and perturbation behavior is designed. Furthermore, numeric areas and selection method of parameters in the new algorithm are exploringly studied. The optimal unit commitment problem is firstly solved via RPACO in this paper. Some corresponding technical problems such as equality and inequality constrains handling and model transferring, are investigated. Numerical simulation demonstrates that the new algorithm possesses more strong global optimization capability, and it brings about some good results on reducing CPU time, preventing search from being in stagnation behavior.