###
DOI:
本文二维码信息
气象因子对夏季最大电力负荷的敏感性分析
任永建1, 熊守权1, 洪国平2, 程定芳3
(1.湖北省气象服务中心;2.武汉区域气候中心;3.黄冈市气象服务中心)
Sensitivity Analysis of Meteorological Factors to Summer Maximum Power Load
REN Yongjian1, XIONG Shouquan1, HONG Guoping2, chen dingfan3
(1.Hubei Meteorological Service Center,Wuhan;2.Wuhan Regional Climate Center,Wuhan;3.Huanggang Meteorological Service Center)
摘要
相似文献
本文已被:浏览 176次   下载 49
投稿时间:2019-06-13    修订日期:2020-05-14
中文摘要: 利用2016~2018年武汉夏季(6~9月)逐15分钟电力负荷以及同期逐日气象数据,分析最大负荷变化特征及与气象因子的相关关系。利用逐步回归和双隐含层BP神经网络算法,建立了武汉夏季最大电力负荷的预测模型。结果表明,平均温度、平均最高温度、平均最低温度与气象负荷存在显著的正相关,其实是日照时数;而相对湿度和雨量与气象负荷为负相关。前一日最大负荷与当日最大负荷的相关性最好,当日负荷对前两日平均的温度和舒适度指数的变化最为敏感。以历史负荷和气象数据为联合预报因子,逐步回归和BP神经网络算法对武汉夏季最大用电负荷具有较好的模拟效果,尤其是对持续高温造成高位运行的最大负荷模拟。当敏感性在10%以内时,逐步回归算法中气象因子正的贡献要小于负的贡献,BP神经网络算法中气象因子正的贡献要高于负的贡献;当敏感性高于10%时,两钟算法中气象因子均为正的贡献。
Abstract:The summer maximum load variation and its correlation with meteorological factors are analyzed by using the 15-minute power load and the daily meteorological data from 2016 to 2018 in Wuhan. Based on stepwise regression and double hidden layer BP neural network algorithm, the prediction model of summer maximum power load is established. The results show that there is a significant positive correlation between mean temperature, average maximum temperature and average minimum temperature and meteorological load; while relative humidity and rainfall are negatively correlated with meteorological load. The correlation between the today maximum load and the last day load was the best. The today load was most sensitive to the average temperature and comfort index for the last two days. With historical load and meteorological data as joint forecasting factors, stepwise regression and BP neural network algorithm have a good simulation effect on the maximum summer power load in Wuhan, especially the maximum load of high-level operation caused by continuous high temperature in 2018. When the sensitivity is within 10%, the positive contribution of the meteorological factor in the stepwise regression algorithm is less than the negative contribution, and the positive contribution in the BP neural network algorithm is higher than the negative contribution. But when the sensitivity is higher than 10%, the meteorological factors in both algorithms are positive contributions.
文章编号:201906130248     中图分类号:    文献标志码:
基金项目:湖北省气象局科技基金重点项目(2019Z09);中国气象局气候变化专项(CCSF202033,CCSF201821)
引用文本:
任永建,熊守权,洪国平,程定芳,0.[en_title][J].Meteor Mon,():-.
REN Yongjian,XIONG Shouquan,HONG Guoping,chen dingfan,0.Sensitivity Analysis of Meteorological Factors to Summer Maximum Power Load[J].Meteor Mon,():-.