Smart-Meter Big Data for Load Forecasting: An Alternative Approach to Clustering
Smart-Meter Big Data for Load Forecasting: An Alternative Approach to Clustering
复制标题
DOI：
10.1109/access.2022.3142680
复制
发表时间：
2022
期刊：
影响因子：
3.9
通讯作者：
Negin Alemazkoor;M. Tootkaboni;R. Nateghi;A. Louhghalam
中科院分区：
文献类型：
--
作者：
Negin Alemazkoor;M. Tootkaboni;R. Nateghi;A. Louhghalam
准确预测电力需求对于能源系统的弹性管理至关重要。最近在利用智能电表数据提高预测准确性方面的努力主要集中在基于聚类的方法（CBA）上，其中智能电表数据被分组为少量聚类，并且为每个聚类开发单独的预测模型。然后聚合基于聚类的预测以计算总需求。与通常不利于集成智能电表数据的传统方法相比，CBA提供了有希望的结果。然而，CBA在计算上是昂贵的，并且受到维数灾难的影响，特别是在涉及来自数百万客户的智能电表数据的场景下。在这项工作中，我们提出了一种有效的简化模型方法（RMA），利用一种新的分层降维算法，使数百万客户的高分辨率高维智能电表数据集成在负荷预测中。我们证明了我们所提出的方法的适用性，通过使用来自一家公用事业公司的数据，总部设在美国伊利诺伊州，拥有超过370万客户和目前的模型性能的预测精度。所提出的分层降维方法使得能够以不可利用的可扩展方式利用来自智能电表的高分辨率数据。结果显示，与不利用精细分辨率数据或无法扩展到大规模智能电表大数据的现有方法相比，预测准确性显着提高。
Accurate forecasting of electricity demand is vital to the resilient management of energy systems. Recent efforts in harnessing smart-meter data to improve forecasting accuracy have primarily centered around cluster-based approaches (CBAs), where smart-meter data are grouped into a small number of clusters and separate prediction models are developed for each cluster. The cluster-based predictions are then aggregated to compute the total demand. CBAs have provided promising results compared to conventional approaches that are generally not conducive to integrating smart-meter data. However, CBAs are computationally costly and suffer from the curse of dimensionality, especially under scenarios involving smart-meter data from millions of customers. In this work, we propose an efficient reduced model approach (RMA) that leverages a novel hierarchical dimension reduction algorithm to enable the integration of fine-resolution high-dimensional smart-meter data for millions of customers in load prediction. We demonstrate the applicability of our proposed approach by using data from a utility company, based in Illinois, United States, with more than 3.7 million customers and present model performance in-terms of forecast accuracy. The proposed hierarchical dimension reduction approach enables utilizing the high-resolution data from smart-meters in a scalable manner that is not exploitable otherwise. The results shows significant improvements in forecast accuracy compared to the available approaches that either do not harness fine-resolution data or are not scalable to large-scale smart-meter big data.