基于遗传规划的径流预测新方法

应用遗传规划方法进行中长期径流预测,将预测模型视为遗传规划中的个体加以处理,依据生物界“优胜劣汰”的原则,运用复制、交叉和变异等遗传操作算子;根据历史样本数据自动生成最佳的径流预测模型,包括模型的函数形式以及模型参数;最后运用得到的预测模型对某水文站的年径流进行预测。仿真结果表明,基于遗传规划的径流预测模型可以明显提高径流预测精度,为解决中长期径流预测问题提供了一种行之有效的新方法。

Application of Genetic Programming to Runoff Forecasting

In this paper, genetic programming(GP) is introduced to solve mid-long term runoff forecasting. Forecasting models are taken as the individuals of GP, which searches the optimal forecasting model by reproduction?mutation and crossover operator according to the principle of good kept and bad eliminated.It can generate automatically runoff forecasted model from history sample data including the function types and the numerical coefficients. Application of obtained optimal model to prediction annual runoff of hydrology station, the simulation results demonstrate that runoff forecasting model based GP can improve precision obviously. Thus, it provides an effective new method to solve mid-long term runoff forecasting problem.