CNN based non-intrusive power consumption load decomposition method

Abstract

The invention relates to a CNN based non-intrusive power consumption load decomposition method. The method comprises the steps of firstly, collecting the total power of power consumption loads and thepower of each load, and expanding the selected load consumption data by using a data expansion technology so as to generate sufficient data for training and improving the generalization performance of a load data deep learning network; and secondly, constructing a CNN model, training the CNN model by the preprocessed data, automatically extracting load features, and finally performing load decomposition on data to be decomposed by using the trained CNN model so as to obtain utilization and consumption power information of each load. Compared with the prior art, the method has the advantages that the decomposition stability and accuracy are improved, and the robustness and the generalization performance of the network are facilitated to be improved.

Description

technical field [0001] The invention relates to the technical field of power metering, in particular to a CNN-based non-invasive power load decomposition method. Background technique [0002] Traditional load monitoring adopts an intrusive method, that is, sensors are installed on each user's electrical equipment to record its usage. The advantage of this method is that the monitoring data is accurate and reliable, but the disadvantages are poor practical operability, high implementation cost, and low user acceptance. [0003] The earliest research on load decomposition was proposed by Hart, characterized by steady-state active power and reactive power, and proposed the original NILM (non-intrusive load monitoring, non-intrusive load monitoring) method framework relative to intrusive load monitoring , NILM can only obtain load data from the user's power entrance to realize load monitoring, without disturbing power users, and has the advantages of simplicity, economy, reliab...

AI Technical Summary

Problems solved by technology

[0005] Due to the complex relationship between the total power data of residential power loads and the power data of different loads, for example, in an ordinary house, there may be more than 20 kinds of loads working a day, which will interfere with the decomposition of target load data and increase the load unpredictability

On the other hand, power inlets may be affected by other factors, such as voltage anomalies and measurement errors; in addition, lack of knowledge of specific load energy level levels, multiple loads with similar energy consumption characteristics, simultaneous switching of switching states, and certain The use of infrequently used loads, etc. will make real-time load decomposition more difficult

Images