摘要
用电负荷预测受到冗余数据影响,负荷预测值与实际值相差较大,因此提出基于多维关联规则的用电负荷智能预测方法。使用多维关联规则挖掘用电负荷频繁项集,获取全部用电负荷待预测数据,根据挖掘结果划分用电负荷种类。计算多维关联规则提升度,预处理冗余数据,生成待预测目标集。根据获取的用电序列,整合全部频繁项集,构建预测模型,并进行强关联学习。通过调整负荷数据训练收敛程度,获取用电负荷的最大、最小值。在用电设备节点中注入用电负荷预测多维关联规则修正数值,避免噪声数据影响预测结果。实验结果表明,该方法最大、最小负荷与实际数据,分别在9月30日和6月15日存在5 MW和0.3 MW的误差,说明该方法预测结果精准。
Electricity load prediction is affected by redundant data,and the load prediction value is different from the actual value.For this reason,an intelligent prediction method of electricity consumption based on multi-dimensional association rules is proposed.Use multi-dimensional association rules to mine frequent itemsets of electricity load,obtain all the data to be predicted of electricity load,and divide the type of electricity load according to the mining results.Calculate the lifting degree of multi-dimensional association rules,preprocess redundant data,and generate target sets to be predicted.According to the obtained electricity consumption sequence,integrate all frequent itemsets,build a prediction model,and perform strong association learning.By adjusting the training convergence degree of the load data,the maximum and minimum values of the electricity load are obtained.The correction value of multi-dimensional association rules for electricity load forecasting is injected into the electrical equipment nodes to avoid noise data affecting the forecasting results.The experimental results show that the maximum and minimum loads of this method and the actual data have errors of 5 MW and 0.3 MW on September 30 and June 15,respectively,indicating that the prediction results of this method are accurate.
作者
邹晖
李金灿
卢万平
ZOU Hui;LI Jincan;LU Wanping(Guangxi Power Grid Co.,Ltd.,Nanning 530000,China;Hechi Power Supply Bureau of Guangxi Power Grid Co.,Ltd.,Hechi 547000,China)
出处
《电子设计工程》
2024年第5期122-126,共5页
Electronic Design Engineering
关键词
多维关联规则
用电负荷
智能预测
数据修正
multi-dimensional association rules
electricity load
intelligent prediction
data correction
