免疫粒子群优化算法在农业水资源优化配置中的应用

The Application of Immune Particle Swarm Optimization in Irrigated Agriculture Optimal Allocation of Water Resources

求解农业水资源优化配置模型(高维非线性优化模型),较常采用大系统分解协调原理和动态规划相结合的方法,这样减少了变量个数,便于优化求解,但协调的过程需要多次从低阶模型中返回信息,而且对于每层的寻优求解过程存在难以克服的矛盾.采用标准的粒子群优化算法则优化程度不易保证并容易陷入局部最优,优化结果对初始种群依赖性较强.因此应用免疫进化算法对标准粒子群优化算法进行改进并应用于灌区农业水资源优化配置模型的求解.算例分析表明,免疫粒子群算法为求解高维复杂的优化配置问题提供了新思路.

The method of combining of coordination of large-scale system decomposition and dynamic programming principle of the method of combining is usually applicated in solving the optimal allocation of water resources in irrigated agriculture, which is easy to solve the optimization problem reducing the number of variables. But it has its own flaws： The process requires coordination of multiple return information from the low-end model But it is difficult to ensure the optimal level and easy to fall into local optimum using the standard particle swarm optimization. Moreover, the application of the standard particle swarm optimization has strong dependence on the initial population. Therefore, evolutionary algorithm is to be used to improve particle swarm optimization. The improved method is applied to solve the optimization model for optimal allocation of water resources. An example shows that immune particle swarm optimization algorithm has strong capability and optimization of high efficiency and provides a new idea to solve high dimensional complex optimization problems.