欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
针对目前常用负荷分析方法多依赖主观经验，而经典经验模式分解有时出现混频现象的问题，提出了一种基于因散经验模式分解的电力负荷混合预测方法。首先，采用经验模式分解的改进算法——因散经验模式分解将负荷序列分解，这样可以自适应地将目标序列分解为若干个独立的内在模式，因此能够克服依赖主观经验的缺点。然后，将这些内在模式基于fine-to-coarse重构为高频、低频和趋势3个分量。在对各分量特性进行分析的基础上，分别采用支持向量机、自回归移动平均和线性回归模型对其进行预测。最后，将3个分量的预测结果叠加作为最终的预测值。利用上述方法对某电网进行24点负荷预测，结果表明该方法可以有效地提高负荷预测精度。
英文摘要：
To solve the problem that at present commonused load analyzing methods mostly rely on subjective experiences and in classical empirical mode decomposition the mode mixing frequently appears, an ensemble empirical mode decomposition （EEMD） based hybrid power load forecasting method is proposed. At first, by use of the improved algorithm of empirical mode decomposition （EMD）, i.e., the EEMD, the power load series is decomposed, this way the objective series can be decomposed to several independent intrinsic modes adaptively, therefore the disadvantage of relying on subjective experiences can be overcome. Then, based on fine-to-coarse, these intrinsic modes are reconstructed as three components, i.e., the high frequency component, low frequency component and trend component. On the basis of analyzing the features of these components, which are forecasted by support vector machines, auto-regressive and moving average （ARMA） and linear regression model respectively. Finally, the superposition of forecasting results ,of the three components is taken as the ultimate forecasting value. The hourly load forecasting results of a certain power network show that the proposed method can improve forecasting accuracy effectively.
同期刊论文项目
同项目期刊论文
Multi-objective coordination optimal model for new power intelligence center based on hybrid algorit
Research on the wavelet neural networks based on data mining and its application in daily load forec
期刊信息
位置：