Non-intrusive load monitoring method based on LMD and KNN algorithm

Non-intrusive load monitoring technology is one of the key technologies for the construction of ubiquitous power Internet of Things, and load identification is the core content of non-intrusive load monitoring technology. When non-invasive load monitoring technology uses low dimensional feature data, the identification accuracy of similar loads is low. This paper designs a local mean decomposition algorithm(LMD) to decompose the low dimensional load features, and uses the load identification model established by k-nearest neighbor algorithm (KNN) to realize the identification of similar feature loads under low dimensional features. After non-intrusive load monitoring public data set simulation verification, the load identification model combined with LMD and KNN can realize accurate identification of similar loads.