首页|基于灰色聚类模型和主动需求管理技术的配电网需求侧多级负荷预测方法

基于灰色聚类模型和主动需求管理技术的配电网需求侧多级负荷预测方法

扫码查看
为了提升配电网需求侧负荷预测精度,提出一种基于灰色聚类模型和主动需求管理技术的配电网需求侧多级负荷预测方法.采用灰色聚类模型对需求侧负荷数据进行特征聚类,计算归一化后的残差平均值获取序列灰色关联度,完成特征聚类;以受限玻尔兹曼机(RBM)作为基本结构进行训练,获取预测最优参数,利用长短期记忆(LSTM)网络设计预测流程,对配电网需求侧完成多级负荷预测.算例分析结果表明,应用所提方法下获得的7日内负荷预测结果平均绝对百分比误差(MAPE)为 201.8 MW,均方根误差(RMSE)为 2.1020%.
Multi-level Load Forecasting Method for Distribution Network Demand Side Based on Grey Clustering Model and Active Demand Management Technology
In order to improve the accuracy of load forecasting in distribution network demand side,a multi-level load forecas-ting method based on grey clustering model and active demand management technology is proposed.A grey clustering model is used to perform feature clustering on demand side load data,the normalized average residual value is calculated to obtain se-quence grey correlation degree,and the feature clustering is completed.The restricted Boltzmann machine(RBM)is used as the basic structure for training to obtain the optimal prediction parameters.The prediction process is designed by using long and short-term memory(LSTM)network to complete multi-level load forecasting on the distribution network demand side.The ex-ample analysis results show that the mean absolute percentage error(MAPE)of the 7-day load prediction results obtained un-der the application of the load prediction method is 201.8 MW,and the root mean square error(RMSE)is 2.1020%.

grey clustering modelactive demand management technologymulti-level load forecastingfeature clusteringun-supervised training

杨敏、赵轩、赵敏、董少峤、赵一男

展开 >

国网冀北电力有限公司经济技术研究院,北京 100034

灰色聚类模型 主动需求管理技术 多级负荷预测 特征聚类 无监督训练

2024

微型电脑应用
上海市微型电脑应用学会

微型电脑应用

CSTPCD
影响因子:0.359
ISSN:1007-757X
年,卷(期):2024.40(12)