【摘要】 水库调度规则作为指导水库调度运行的重要工具，不仅是水库规划设计时期的决策参考要素，且是运行管理期影响水库综合效益发挥的关键技术之一。为此，以长江上游水库群历史调度运行数据为基础，结合水库调度原理及运行特征，挑选时段数、前期水位、入库、出库及当前时段入库作为影响因子组建输入因子集，综合考虑运行期数据特征及决策树原理确定时段末水位作为模型输出，同时提出相应基于水库调节库容的水位评价指标，并采用相关系数和互信息作为模型输入因子相关性评定指标，引入树形Parzen评估器对输入因子个数和算法超参数进行优化，在此基础上，建立了基于决策树及其集成模型的水库调度规则提取模型，形成了融合历史调度过程和专家经验的水库调度规则。试验结果表明，决策树及其集成模型在水库调度规则提取应用时具有较强的能力和适用性。更多还原

【Abstract】 Reservoir operation rules, as an important tool to guide reservoir operation, are not only the decision-making reference in the reservoir planning and design period, but also one of the key technologies affecting the comprehensive benefits of the reservoir in the operation and management period. Therefore, based on the historical operation data of reservoirs in the upper reaches of the Yangtze River, the number of periods, early water level, inflow, outflow and current inflow were selected as the influence factors to form the input factor set combined with the reservoir operation principle and operation characteristics. Comprehensively considering the characteristics of operation data and the principle of decision tree, the end of period water level was determined as the model output and then the corresponding simulated water level evaluation index was proposed based on the reservoir regulation capacity. The correlation coefficient and mutual information were used as the correlation evaluation index of model input factors, and the tree Parzen evaluator was introduced to optimize the number of input factors and algorithm super parameters. Finally, the reservoir operation rule extraction model based on decision tree and its integrated model was established and the reservoir operation rule integrating historical operation process and expert experience was formed. The experimental results show that the decision tree and its integrated model have strong ability and applicability in the extraction and application of reservoir operation rules.更多还原