线性求解器在中长期水量调度中的应用研究

Application of Linear Programming Solver in Mid⁃Long Term Water Dispatch

针对中长期水量调度模型多变量、多约束、求解困难的问题,采用基于线性规划方法的线性求解器对中长期水量调度模型进行求解,以提高模型求解精度和效率。以北方某城市水资源系统中长期水量调度为例,采用Cplex、Lpsolver线性求解器对模型进行求解,并与遗传算法进行对比,结果表明:Cplex、Lpsolver表现出较高的求解精度和效率;当模型规模增大时,遗传算法计算时间明显增加,而Cplex、Lpsolver计算时间变化不大;该市水库从A河引水量的调节能力偏低,改变从A河的引水时机能够充分发挥已有水库的调蓄能力,减小系统总缺水量。

Aiming at the issues of multi variables, multi constraints and difficult solution of mid⁃long term water dispatch model, a linear pro⁃gramming solver based on linear programming method was used to solve the mid⁃long term water dispatch model, so as to improve the modelsolving accuracy and efficiency. Taking the mid⁃long term water dispatch of a some northern city water resources system as an example, themodel was solved by using the linear solvers of Cplex and Lpsolver, and compared with the genetic algorithm. The results show that, Cplexand Lpsolver show higher calculation accuracy and efficiency;when the scale of the model increases, the calculation time of genetic algorithmincreases significantly, while the calculation time of Cplex and Lpsolver changes little;the regulating storage of the city is too low to regulatethe water quantity from River A. Changing the timing of water diversion from River A can give full play to the regulation and storage capacityof the existing reservoirs and reduce the total water shortage of the system.