摘要
居民小区的用电负荷和用电量预测结果,受到数据分类模型的影响,平均相对误差较大。因此,提出基于数据挖掘的城区居民小区负荷和电量预测方法。构建需求预测库并采集小区历史用电数据,通过异常修正和数据转换方法完成历史数据预处理。利用数据挖掘技术构建聚类分析模型,获取数据分类结果。运用模糊神经网络,计算小区负荷预测值,再根据灰色关联度分析法得到用电量最终预测结果。实验结果表明:所提方法的预测平均相对误差为2.21%,相比文献提出方法平均相对误差降低了11.15%、9.74%。
The prediction results of power load and power consumption in residential areas are affected by the data classification model, and the average relative error is large. Therefore, a load and power forecasting method based on data mining is proposed. Build the demand prediction database and collect the historical power consumption data of the community, and complete the historical data preprocessing through anomaly correction and data conversion methods. The cluster analysis model is constructed by using data mining technology to obtain the data classification results. The fuzzy neural network is used to calculate the community load prediction value, and then the final prediction result of power consumption is obtained according to the grey correlation analysis method. The experimental results show that the average relative error of the proposed method is 2.21%. Compared with the methods proposed in the literature, the average relative error is reduced by 11.15% and 9.74%.
作者
徐鹏鹏
钱凌寒
代克丽
钱天能
XU Pengpeng;QIAN Linghan;DAI Keli;QIAN Tianneng(Nantong Power Supply Branch of Jiangsu Electric Power Co.,Ltd.,Jiangsu Nantong 226000,China)
出处
《自动化与仪器仪表》
2022年第11期175-178,183,共5页
Automation & Instrumentation
基金
2021年南通基于电网发展和投资效益评价的指标维度研究和数据调查(B710802169X3)。
关键词
数据挖掘
城区
负荷预测
电量预测
聚类
灰色关联度分析
data mining
city proper
load forecasting
electricity forecast
clustering
grey correlation analysis
