会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 5. 发明公开
    • ENERGY DEMAND PREDICTING SYSTEM AND ENERGY DEMAND PREDICTING METHOD
    • 能源需求预测系统和能源需求预测方法
    • EP3300205A1
    • 2018-03-28
    • EP16796313.1
    • 2016-05-09
    • Hitachi, Ltd.
    • UTSUMI, MasatoWATANABE, TohruIKEMOTO, YuSAKIKUBO, YoukoSHIGEMORI, IkuoOGAWA, Hiroaki
    • H02J3/00
    • G01R21/008G06Q30/0202G06Q50/06H02J3/008H02J2003/003Y04S50/10Y04S50/14
    • [Problem] To predict demand under circumstances in which continuous total contracted demand characteristics vary within a short time period.
      [Solution] This energy demand predicting method is configured in such a way that: sets of demand pattern generation data for each of one or more preset combinations of a contracted demand granularity and a time granularity are generated on the basis of actual energy demand information for a default historical period; a demand type is generated for each set of demand pattern generation data; an energy demand at a default historical date and time is calculated as a predicted value for evaluation, for each demand type; a contracted demand granularity and a time granularity are determined on the basis of the predicted value for evaluation for each demand type and the actual energy demand information, in such a way as to minimize an error between an estimated value or a predicted value of energy demand at a historical date and time, and the actual observed value at said date and time; and the energy demand value at an arbitrarily defined date and time is estimated or predicted on the basis of the determined results.
    • [问题]预测在持续总需求特征在短时间内变化的情况下的需求。 该能量需求预测方法被配置为:基于实际的能量需求信息,生成针对缩小的需求粒度和时间粒度的一个或多个预设组合中的每一个组的需求模式生成数据 默认历史时期; 针对每组需求模式生成数据生成需求类型; 对于每种需求类型,将默认历史日期和时间处的能量需求计算为用于评估的预测值; 基于用于每种需求类型的评估的预测值和实际能量需求信息来确定约定的需求粒度和时间粒度,以使得能量需求的估计值或预测值之间的误差最小化 在历史日期和时间以及在所述日期和时间的实际观测值; 并且基于确定的结果来估计或预测在任意定义的日期和时间的能量需求值。