Non-intrusive load monitoring via online compression and reconstruction
Accurate monitoring of power loads in home scenarios often relies on complex algorithmic models that are difficult to deploy in edge devices.At the same time,massive power data poses a huge challenge to communication of grid.In response to the above issues,this paper proposes a distributed non-intrusive load monitoring method.This method calculates and identifies the operating state of the load by the LSTM load monitoring algorithm based on the attention mechanism,and distributes the load monitoring task in the cloud and the edge with the help of cloud-edge collaboration technology to solve the problem of insufficient edge computing power.Aiming at the high network bandwidth requirements brought about by cloud-side communication,the compressed sensing method based on K-SVD double sparse online dictionary is used to compress and reconstruct the load signal,which effectively alleviates the shortage of communication resources.Comparing the performance of the monitoring algorithm under different load scenarios,the results show that the load monitoring algorithm in this paper can maintain an accuracy rate of more than 95%.Experiments are conducted to verify the effectiveness of the compressed sensing method on the compression of load signals,and determine the maximum compression ratio of load data without distortion.
communication and information systemnon-intrusive load monitoringcompressed sensingdistributed deploymentlong short-term memory
万方数据
维普
