混合智能算法及其在供水水库群优化调度中的应用

将遗传算法中的进化思想和蚁群算法中的群体智能技术有效地耦合,提出了一种基于两者的混合智能算法,应用于供水水库群系统的优化调度研究中。算法利用蚁群算法的并行性、正反馈性以及良好的全局寻优能力,避免搜索陷入局部最优,同时借鉴遗传算法的进化思想,利用杂交、变异算子来进行局部寻优,使其能快速搜索到全局最优点。在种群随机搜索过程中嵌入确定性的模式搜索,使得算法同时具有随机性和确定性。结合模拟退火思想,构造了罚因子处理约束条件,使该算法对水库优化调度问题以及其他优化问题具有一定的通用性。通过实例验证,并与大系统聚合分解经典算法进行比较,结果表明该算法是可行的和有效的。

Hybrid intelligent algorithm and its application in dispatch optimization for water supply reservoir group

The genetic algorithm is combined with ant colony algorithm to develop a hybrid algorithm for optimizing the dispatch of reservoir group for water supply.The advantages of ant colony technology such as the positive feedback,parallel computation and the global convergence performance are utilized to avoid the localized optimum searching.The evolution idea of genetic algorithm including the crossover and mutation operation can improve the speed of searching for the global optimization.On the other hand,a deterministic searching algorithm is embedded to improve the optimization performance and a penalty function based on the idea of simulated annealing is proposed to handle the non-equated constrains.The application to optimal dispatch of water supply reservoir group in the Shenzhen City shows that the proposed algorithm has the prominent efficiency and high searching performance.