摘要
针对国内外水电站实际调度水平与优化调度理论间差距普遍较大的现状,基于确定性优化调度成果,运用支持向量机理论建立了水库水电站实际运行的中长期调度计划,以提高水电站实际运行调度水平。结合决策变量与相关因子筛选、训练样本与预测样本划分、模型参数优选等技术处理,将调度计划应用于金沙江—长江中游水电站群中的4座月调节性能以上水电站,预测结果表现出了良好的拟合精度。进一步模拟调度计划,指导梯级水电站群长系列调度运行,结果表明,模拟运行较好地继承了确定性优化调度在发电量、发电保证率及发电过程方面的效益,证实了该方法的可行性和有效性,为梯级水电站群实际优化运行提供了有力的技术支撑和决策支撑。
In view of the rather big gap between the actual operation level of hydropower stations and the optimal operation theory at home and abroad,the support vector machine is employed to formulate actual operating rules based on the deterministic optimal operation results so as to improve the actual operating level.By applying the model in cascade hydropower stations on Jinsha River-Yangtze River,combined with decision variable and independent variable selection, division of training data and prediction data,and parameter selection techniques,the prediction results exhibit good fitting accuracy.The simulation of cascade operation guided by operating rules shows that simulated operation has retained the benefits of optimal operation in the electric power generated,the generation guarantee rate and generation process,validating the feasibility and efficiency of the model and providing strong technical support and decision support to actual optimal operation of cascade hydropower stations.
出处
《电力系统自动化》
EI
CSCD
北大核心
2013年第2期56-60,78,共6页
Automation of Electric Power Systems
基金
国家自然科学基金资助项目(51279062)
中央高校基本科研业务费专项资金资助项目(11QX52)~~
关键词
梯级水电站群
中长期调度计划
支持向量机
模拟运行
cascade hydropower stations
medium-long term operating plan
support vector machine
operation simulation
