基于长短期记忆网络的新能源电网电量分时计度方法  

New energy grid electricity time⁃sharing calculation method based on Long Short⁃Term Memory network

在线阅读下载全文

作  者:任昱 李飞 陈永富 景苏峰 苏耀枝 REN Yu;LI Fei;CHEN Yongfu;JING Sufeng;SU Yaozhi(South China Branch,Beijing Jingneng Clean Energy Co.,Ltd.,Zhanjiang 524000,China)

机构地区:[1]北京京能清洁能源电力股份有限公司华南分公司,广东湛江524000

出  处:《电子设计工程》2024年第10期115-119,共5页Electronic Design Engineering

摘  要:针对新能源接入电量不稳定,电量分时计度的负荷曲线优化效果较差的问题,设计一种基于长短期记忆网络的新能源电网电量分时计度方法。设计新能源电网的短期电力负荷预测模型,实施短期电力负荷预测。结合接入新能源的特征与用户需求,利用模糊隶属度函数计算新能源接入下负荷曲线上的谷时段隶属度、峰时段隶属度,通过聚类分析的方式归类峰谷时段。基于长短期记忆网络探索新能源电网电量分时计度中的目标函数、约束条件,构建新能源电网电量分时计度模型,实现新能源电网的电量分时计度。在某地区新能源电网测试设计方法的性能,测试结果表明,该方法在较大需求价格弹性、较小单时段响应系数下能够实现更好的负荷曲线优化效果。In order to solve the problem that the connected new energy is unstable and the load curve optimization effect of electricity timesharing is poor,a new energy grid electricity timesharing method based on long⁃term and short⁃term memory network is designed.Design short⁃term power load forecasting model of new energy grid and implement short⁃term power load forecasting.Combined with the charact⁃eristics of new energy access and user demand,the fuzzy membership function is used to calculate the valley period membership and peak period membership on the load curve under new energy access,and the peak and valley periods are classified by cluster analysis.Based on the long⁃term and short⁃term memory network,this paper explores the objective function and constraints in the time⁃sharing metering of new energy power grid,constructs the time⁃sharing metering model of new energy power grid,and realizes the time⁃sharing metering of new energy power grid.The performance of the new energy grid test design method in a certain region shows that the method can achieve better load curve optimization effect under the condition of large demand price elasticity and small single period response coefficient.

关 键 词:长短期记忆网络 模糊隶属度函数 新能源电网 半梯形函数 电量分时计度 

分 类 号:TN91[电子电信—通信与信息系统]

 

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