A Load Identification Algorithm of Frequency Domain Filtering Under Current Underdetermined Separation

Abstract

Non-intrusive load identification is important to load monitoring and smart power utilization. In order to effectively identify load status and obtain detailed power data, this paper explained a load identification algorithm based on load decomposition and frequency domain filtering. It realized load decomposition through solving an underdetermined problem of a single current signal under non-intrusive collection mode and then further achieved load identification. The underdetermined problem was optimized into a 1-D underdetermined problem. The solving model was constructed as separating the collecting current into two channels. According to the sparseness of the current frequency domain signal, the optimal solution was obtained by a two-step iterative shrinkage threshold algorithm. Therefore, each operation load can be decomposed independently. The frequency-domain filter group was conducted to filter the decomposition current, and load identification was realized based on the decision of the frequency component after filtering. The algorithm simplified the identification complexity, with a fast convergence rate and high identification accuracy. The performance was validated by the actually measured data. The load decomposition and identification was effective, which could accurately determine the load status, and obtain the current waveform of the independent load.

Keywords

• Frequency-domain filtering
• load decomposition
• load identification
• non-intrusive load monitoring
• solving underdetermined problem