考虑特征值细分的广义加性短期负荷预测模型

准确的负荷预测是保障电力市场有序运行的关键,针对单一因素预测环境受限、综合模型对变量的拆分及交互作用考虑欠周的问题,提出建立考虑温度、节假日、负荷等细分特征变量的广义加性短期负荷预测模型。首先,细分并测算了不同因素与负荷的相关系数,依据相关度筛选特征变量;其次,确定负荷波动基函数,针对细分特征变量分别建模,形成整体预测模型;最后,利用广州实际运行数据测算分析。实例表明,基于特征值细分的广义加性模型预测效果更佳,是短期负荷预测的一种有效方法。

Two-order Hermite vector-interpolating subdivision schemes

A family of two-order Hermite vector-interpolating subdivision schemes is proposed and its convergence and con- tinuity are analyzed. The iterative level can be estimated for given error. The sufficient conditions of C2 continuity are proved. Geometric features of subdivision curves, such as line segments, cusps and inflection points, are obtained by appending some conditions to initial vectorial Hermite sequence. An algorithm is presented for generating geometric features. For an initial se- quence of two-order Hermite elements from unit circle, the numerical error of the 4th subdivided level is O(10?4).