基于设备运行状态挖掘的非侵入式负荷分解方法

随着非侵入式负荷监测与用户侧智能电表的结合，基于低频电力数据实现负荷分解成为了最新的研究趋势。考虑到低频电力数据的特征，文章提出一种基于设备运行状态挖掘的非侵入式负荷分解方法。该方法首先进行负荷事件检测，并在负荷事件处提取功率特征；接着在特征平面内通过聚类算法获取表征不同类型负荷事件的聚类簇；最终采用图信号处理算法在聚类簇间挖掘设备运行状态并与数据库中的模板进行匹配实现负荷分解。算例验证了该方法事件检测和负荷分解的准确率，同时验证了在状态挖掘过程中引入设备运行周期能耗对额定功率相似设备的负荷分解具有优化效果。因此，为基于低频电力数据的非侵入式负荷分解技术研究提供了新思路。

Non-intrusive Load Disaggregation Method Based on the Mining of Equipment Operating States

With the combination of users smart meter and non-intrusive load monitoring, research on load disaggregation based on low-rate power data has become the latest trend. On the basis of this, a non-intrusive load disaggregation method based on the mining of operating states is proposed in this paper. Firstly, this method detects load events and extracts power characteristic around load events. In the characteristic plane, a clustering algorithm is used to obtain clusters that represent different types of load events. Finally, among clusters, the GSP algorithm is used to mine equipment operation states that are matched with load templates stored in database to realize load disaggregation. The results of example in this paper verifies the accuracy of event detection and load disaggregation, and also verifies that the introduction of circle operation energy consumption in state mining process has an optimized effect on load disaggregation of devices with similar rated power. Accordingly, it provides a novel idea for the research of non-intrusive load disaggregation technology based on low-rate power data.