方〓陈1,江兴稳2a,周〓健1,李〓芬2b,曹玄烨1.含分布式能源区域电网月最大净负荷概率预测[J].水电能源科学,2018,36(9):197-200
含分布式能源区域电网月最大净负荷概率预测
Probability Prediction of Monthly Net Load for Regional Power Grid with Distributed Energy Penetration
  
DOI:
中文关键词:  负荷预测  月最大负荷  净负荷  概率预测  区域电网
英文关键词:load forecasting  monthly maximum load  net load  probability prediction  regional power grid
基金项目:国网上海电力公司科研项目(520940160026)
作者单位
方〓陈1,江兴稳2a,周〓健1,李〓芬2b,曹玄烨1 1. 国网上海市电力公司 电力科学研究院上海 2004372. 上海电力学院 a. 数理学院b. 电气工程学院上海 200090 
摘要点击次数: 81
全文下载次数: 
中文摘要:
      负荷预测在电网规划和运行中十分重要,大规模分布式能源接入电网参与能量交换,可使电网用户优化其用电模式,但造成区域电网月最大净负荷特性发生根本性改变,增加了月最大净负荷预测的不确定性。为此,结合BP神经网络算法与分位数回归模型,构建了区域电网月最大净负荷的非线性概率预测模型;并利用核密度估计算法计算得到了月最大净负荷概率预测分布曲线;最后,以上海某含分布式能源区域电网为例,验证了该方法的可行性与可靠性。结果表明,该方法可准确刻画月最大净负荷波动特性,为电网规划与负荷管理提供依据。
英文摘要:
      Load forecasting plays an important role in power grid planning and operation. The massive penetration of distributed energy accessing to power grid to participate in energy exchange enables users to optimize their electrical patterns, but that causing fundamentally change of the monthly maximum load characteristics in regional power grid and increasing the uncertainty of load forecasting. For this reason, the BP neural network model and the quantile regression model are combined to construct a nonlinear probability prediction model for monthly maximum net load of regional power grid. The probability prediction distribution curve of monthly maximum net load is gain by using the kernel density estimation. According to the experiments on a regional power grid with distributed energy of Shanghai, the feasibility and reliability of the method is confirmed. The results show that the proposed method can accurately depict the fluctuation characteristics of the monthly maximum net load and provide support for power grid planning and load management.
查看全文  查看/发表评论  下载PDF阅读器