期刊文献+

基于混合交叉算子改进NSGA-Ⅱ算法的董铺—大房郢水库优化调度研究

Optimal Scheduling of Dongpu-Dafangying Reservoir Based on Hybrid Crossover Operator Improved NSGA-Ⅱ Algorithm
在线阅读 下载PDF
导出
摘要 以安徽省董铺—大房郢水库为例,以水库缺水率最小和补水量最少为最优准则,考虑董铺—大房郢水库水源连通工程水量补偿式调节和接受上游淠河灌区水库群补水的特殊机制,构建董铺—大房郢水库双目标优化供水调度模型,并采用基于混合交叉算子改进的NSGA-Ⅱ算法求解模型。结果表明,算数交叉算子(ACO)混合模拟二进制交叉算子(SBX)的收敛时间较单一SBX算子缩短11.48%,较单一ACO算子缩短2.58%;其中混合算子SBX-ACO求得的解集质量更好,对应评价指标世代距离(GD)值(8.13×10^(-4))、反世代距离(IGD)值(3.1×10^(-4))为所有计算方案中最小。优化调度模型求解的供水方案中两库补水量比不优化条件下的补水量减少11.5%。在计算效率及解集质量上综合验证了所提出的改进算法的有效性,同时为区域水资源优化调度提供科学依据。 This paper takes the Dongpu-Dafangying reservoir in Anhui Province as the research object.Optimal crite-rias are the minimum water shortage rate and the minimum water replenishment of the reservoir.The dual-objective opti-mal water supply scheduling model of the Dongpu-Dafangying Reservoir is established considering the compensatory ad-justment of the water volume of the Dongpu-Dafangying Reservoir water source connection project and the special mecha-nism of accepting the water supply of the reservoir group in the upstream Pihe irrigation area.The improved NSGA-Ⅱalgorithm based on the hybrid cross operator is used to solve the model.The results show that the convergence time of a-rithmetic cross operators(ACO)mixed simulated binary crossover(SBX)is shortened by 11.48%compared with the single SBX operator,and 2.58% shorter than that of the single ACO operator.Among them,the solution set obtained by the hybrid operator SBX-ACO is of better quality.Its corresponding evaluation index generational distance(GD)value(8.13×10^(-4))and inverted generational distance(IGD)value(3.1×10^(-4))are the lowest among all calculation schemes.In the water supply scheme solved by the optimal scheduling model,the water replenishment of the two reservoirs is re-duced by 11.5%compared with that of the non-optimal condition.This paper comprehensively verifies the effectiveness of the improved algorithm in terms of computational efficiency and solution set quality.It provides a scientific basis for the optimal scheduling of regional water resources.
作者 陈虎 郭园 祝雪萍 霍云超 刘晓东 高学睿 牛鑫 CHEN Hu;GUO Yuan;ZHU Xue-ping;HUO Yun-chao;LIU Xiao-dong;GAO Xue-rui;NIU Xin(College of Water Resources Science and Engineering,Taiyuan University of Technology,Taiyuan 030024,China;PowerChina Northwest Engineering Corporation Limited,Xi'an 710065,China;Institute of Soil and Water Conservation,Northwest A&F University,Yangling 712100,China)
出处 《水电能源科学》 北大核心 2025年第1期197-201,共5页 Water Resources and Power
基金 国家自然科学基金项目(52379018) 山西省科技创新人才团队专项(202204051002027)。
关键词 改进NSGA-Ⅱ 混合交叉算子 优化供水调度 IGD评价指标 improved NSGA-Ⅱ hybrid crossover operators optimal water supply scheduling IGD evaluation index
作者简介 陈虎(1998-),男,硕士研究生,研究方向为水文水资源,E-mail:2935040027@qq.com;通讯作者:祝雪萍(1985-),女,博士、副教授,研究方向为水文水资源,E-mail:xpzhu01@163.com。
  • 相关文献

参考文献4

二级参考文献34

  • 1Wang Z G, Chen X Q, Luo W C, et al. Research on the theory and application of multidisciplinary design optimization of flight vehicles. Beijing: National Defence Industry Press, 2006.
  • 2Rao S S, Dhingra A K. Applications of fuzzy theories to multiobjective system optimization. NASA CR 177573, 1991.
  • 3Soland R M. Multicriteria optimization: a general characterization of efficient solutions. Decision Sciences 1979; 10(1): 26-38.
  • 4Cui X X. Multiobjective evolutionary algorithm and their application. Beijing: National Defence Industry Press, 2006.
  • 5Coello C A C. An updated survey of evolutionary multiobjective optimization techniques: state of the art and future trends. Proceedings of the 1999 Congress on Evolutionary Computation. 1999; 1: 3-13.
  • 6Schaffer J D. Some experiments in machine learning using vector evaluated genetic algorithms. PhD thesis, Vanderbilt University, 1984.
  • 7Horn J, Nafpliotis N, Goldberg D E. A niched Pareto genetic algorithm for multiobjective optimization. Proc of the 1st IEEE Conf on Evolutionary Computation. 1994; 82-87.
  • 8Zitzler E, Thiele L. Multiobjective evolutionary algorithms: a comparative case study and the strength pareto approach. IEEE Trans on Evolutionary Computation 1999; 3(4): 257-271.
  • 9Zitzler E, Marco L, Lothar T. SPEA2: improving the strength Pareto evolutionary algorithm. Computer Engineering and Networks Laboratory, Swiss Federal Institute of Technology Technical Report 103, 2001.
  • 10Srinivas N, Deb K. Multi-objective function optimization using non-dominated sorting genetic algorithms. Evolutionary Computation 1995; 2(3): 221-248.

共引文献11

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部