| 夏 飞,张 洁,张 浩,陆剑峰.基于 BIC 准则和加权皮尔逊距离的居民负荷模式精细识别及预测[J].电子测量与仪器学报,2020,34(11):33-42 |
| 基于 BIC 准则和加权皮尔逊距离的居民负荷模式精细识别及预测 |
| Fine recognition and prediction of resident load pattern based on BIC criterion and weighted Pearson distance |
| |
| DOI： |
| 中文关键词: BIC 特征提取 加权皮尔逊距离 密度峰值法 改进的 LSTM 网络 精细分类 居民负荷预测 |
| 英文关键词:BIC feature extraction weighted Pearson distance CFSFDP algorithm improved LSTM network fine classification resident
load forecast |
| 基金项目:自然科学基金重大项目(71690234)、政府间国际科技创新合作重点专项(2017YFE0100900)、上海市科委创新项目(19DZ1206800)资助 |
|
|
|
|
| 摘要点击次数: 106 |
| 全文下载次数: 360 |
| 中文摘要: |
| 针对居民日用电负荷的聚类分析和预测问题提出了一种基于居民用电负荷模式精细分类的预测框架。 为了提高用于
聚类分析的特征质量,首先基于贝叶斯信息准则(BIC)实现特征筛选。 然后,采用基于加权皮尔逊距离的密度峰值法实现居民
用电负荷曲线形态的准确识别。 接下来,通过融合激活函数的方法对长短期记忆(LSTM)预测网络进行改进。 最后,利用改进
后的 LSTM 网络对精细分类的居民用电负荷模式进行预测。 实验结果表明,根据所提出的方法得到的预测误差指标为平均绝
对百分误差(MAPE),MAPE= 6. 6792%,提高了负荷预测质量,在居民用电负荷预测中具有较好的效果。 |
| 英文摘要: |
| Aiming at the problem of clustering analysis and prediction of residential daily electricity load, a prediction framework based
on the fine classification of residential power load patterns was proposed. In order to improve the quality of features used for cluster
analysis, feature selection was first implemented based on BIC criteria. Then, the CFSFDP algorithm based on weighted pearson distance
is used to realize the accurate identification of the shape of the residential electricity load curve. Next, the LSTM prediction network is
improved by a fusion activation function method. Finally, the improved LSTM network is used to predict the finely classified residential
power load patterns. The experimental results show that the forecast error index obtained by the method proposed is MAPE= 6. 6792%,
which improves the quality of load forecasting and has a good effect in the forecast of residential electricity load. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
