Jiang Haoyu, Chen Kai, Ge Quanbo, Xu Jinqiang, Fu Yingying, Li Chunxi
School of Electronics and Information Engineering, Guangdong Ocean University, No. 1 Haida Road, Huguang Town, Machang District, Zhanjiang City, Guangdong, China.
College of Logistics Engineering, Shanghai Maritime University, 1550 Haigang Avenue, Nanhui New Town, Pudong New Area, Shanghai, China.
ISA Trans. 2021 Nov;117:172-179. doi: 10.1016/j.isatra.2021.01.056. Epub 2021 Feb 2.
The data of the power Internet of Things (IOT) system is transferred from the IaaS layer to the SaaS layer. The general data preprocessing method mainly solves the problem of big data anomalies and missing at the PaaS layer, but it still lacks the ability to judge the high error data that meets the timing characteristics, making it difficult to deal with heterogeneous power inconsistent issues. This paper shows this phenomenon and its physical mechanism, showing the difficulty of building a quantitative model forward. A data-driven method is needed to form a hybrid model to correct the data. The research object is the electricity meter data on both sides of a commercial building transformer, which comes from different power IOT systems. The low-voltage side was revised based on the high-voltage side. Compared with the correction method based on purely using neural networks, the combined method, Linear Regression (LS) + Differential Evolution (DE) + Extreme Learning Machine (ELM), further reduces the deviation from approximately 4% to 1%.
电力物联网（IOT）系统的数据从基础设施即服务（IaaS）层传输到软件即服务（SaaS）层。通用数据预处理方法主要解决了平台即服务（PaaS）层的大数据异常和缺失问题，但仍缺乏判断符合时间特性的高误差数据的能力，难以处理异构电力不一致问题。本文展示了这种现象及其物理机制，说明了构建定量模型的困难。需要一种数据驱动方法来形成混合模型以校正数据。研究对象是商业建筑变压器两侧的电表数据，其来自不同的电力物联网系统。低压侧基于高压侧进行修正。与单纯使用神经网络的校正方法相比，线性回归（LS）+差分进化（DE）+极限学习机（ELM）的组合方法进一步将偏差从约4%降低到1%。
