论文部分内容阅读
中长期径流预报是充分利用水资源、发挥电站经济效益的有力手段。以三峡水库为研究对象,分别采用周期外延叠加技术、人工神经网络模型、投影寻踪自回归模型和支持向量机回归模型对三峡水库逐月入库径流进行预报。从不同侧面比较分析了这四种方法优劣,并总结各预报模型计算结果的特征及规律,为三峡水库寻求径流预报规律和制定未来中长期调度计划提供了技术支持。
Medium and long-term runoff forecasting is a powerful tool to make full use of water resources and make full use of power station economic benefits. Taking the Three Gorges Reservoir as the research object, the runoff epitaxial stacking technique, artificial neural network model, projection pursuit auto-regression model and support vector machine regression model were respectively used to forecast the monthly runoff of the Three Gorges Reservoir. The advantages and disadvantages of these four methods are compared and analyzed from different aspects. The characteristics and regularities of the calculation results of each forecast model are summarized, providing technical support for the Three Gorges Reservoir to seek the law of runoff forecasting and formulating the medium and long-term scheduling plans for the future.