基于双目标免疫粒子群算法的水资源优化配置  

Optimized Allocation of Water Resources Based on Double Objective Immune Particle Swarm Algorithm

作　　者：邹琳 蔡欣 郝矿荣[2,1] 

机构地区：[1]东华大学信息科学与技术学院,上海201620 [2]数字化纺织服装技术教育部工程研究中心,上海201620

出　　处：《计算机仿真》2018年第12期296-301,共6页Computer Simulation

基　　金：国家自然科学基金(61473077;61473078;61503075);上海市科学技术委员会重点基础研究项目(13JC1407500);上海市浦江人才计划(15PJ1400100);中央高校基本科研业务费专项资金资助(15D110423;2232015D3-32);上海科学技术委员会农业项目(16391902800)

摘　　要：为解决非充分灌溉过程中怎样合理分配生育期水量使作物产量达到最大的问题。将农作物产量和生育期灌溉总水量作为两个优化目标,提出一种双目标免疫粒子群算法,实现作物生长过程中水量的合理分配,达到在非充分灌溉情况下农作物产量最大和生育期灌溉总水量最小的目的。上述算法在标准的粒子群算法中加入拥挤距离来评价粒子,进而选择合适的粒子作为抗体,对全体粒子进行交叉变异操作,从而避免了粒子群算法容易陷入局部最优的问题,有效地加快了收敛速度。实验结果表明,与NSGAII和PSO等算法相比,上述算法能够得到更好的非劣解集。In order to solve the problem of how to rationally allocate the amount of water to make the crop yield reach the maximum during the period of insufficient irrigation,taking the crop yield and the total amount of irrigation water during the growing period as two optimization objectives,this paper proposes a double objective immune particle swarm algorithm.This algorithm can achieve the rational allocation of water under deficit irrigation in order to get maximum output and minimum irrigation water while crop growth.The algorithm added crowding distance to PSO to evalue the paritcle,and selected the appropriate particle as antibodies,then the operations of crossover and mutation were performed on all particles,so that the new algorithm can avoid the problem that PSO is easy to fall into local optimum,and accelerate the convergence speed.Experimental results show that,compared with NSGA-Ⅱ and PSO algorithms,the proposed algorithm can obtain better non-inferior solutions.

关 键 词：粒子群算法 拥挤距离 双目标优化 作物灌溉 免疫算法 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]