计及季节与趋势因素的综合能源系统负荷预测  被引量:15

Loading forecast for integrated energy system considering season and trend factors

在线阅读下载全文

作  者:张铁岩 孙天贺 ZHANG Tie-yan;SUN Tian-he(Shenyang Ligong University,Shenyang 110159,China;School of Electrical Engineering,Shenyang University of Technology,Shenyang 110870,China)

机构地区:[1]沈阳理工大学,沈阳110159 [2]沈阳工业大学电气学院,沈阳110870

出  处:《沈阳工业大学学报》2020年第5期481-487,共7页Journal of Shenyang University of Technology

基  金:国家重大科技项目重点专项(2012YQ090175).

摘  要:针对复杂影响因素下综合能源系统月度负荷预测精度低的问题,提出基于时间序列特征分解的月度负荷预测模型.利用时间序列分解方法将负荷数据分解为季节分量、趋势分量与随机分量,根据各分量随时间变化的特性,分别采用向量自回归模型、最小二乘支持向量回归与平均值法进行预测.各分量预测结果的投影重构值作为月度负荷的预测值,并考虑了季节拐点与区域经济因素对月度负荷的影响.实例分析证明该方法能够有效提高综合能源系统的月度负荷预测精度.Aiming at the problem of low accuracy of monthly loading forecast for integrated energy system with complex influencing factors,a monthly loading forecast model based on time series feature decomposition was proposed.Using the time series decomposition method,the loading data were decomposed into seasonal component,trend component and random component.According to the time-varying characteristics of each component,the above-mentioned three components were predicted by vector auto regressive model,least square support vector regression(LSSVR)and average value method,respectively.The projection reconstructed value of prediction result for each component was taken as the monthly loading prediction value,and the influence of season inflection points and regional economy factors on monthly loadings was considered.The instance analysis proves that the as-proposed method can effectively improve the monthly loading forecast accuracy for integrated energy system.

关 键 词:综合能源系统 月度负荷预测 时间序列 特征分量分解 季节分量 趋势分量 随机分量 向量自回归 最小二乘支持向量回归 

分 类 号:TM715[电气工程—电力系统及自动化]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象