Non-intrusive load identification can infer the operating status of various electrical appliances in a user’s household based on the electrical parameters collected by the overall household electricity meter. It helps users utilize electrical energy more scientifically and rationally. Due to significant differences in the working principles of appliances and their energy consumption, the effectiveness of load identification has not yet met practical application requirements. This paper proposes a load identification method based on a dual-branch attention GRU fusion network structure, the network integrates GRU, Temporal Convolution Network (TCN), and attention mechanisms. It overcomes the limitation of GRU networks in extracting ultra-long-term temporal dependencies and compensates for TCN’s less effective exploration of medium and short-term temporal dependencies compared to GRU. As a result, it achieves better identification performance. Experiments on public datasets indicate that the proposed method achieves better load state identification performance compared to other methods.

Traditional wildfire detection methods are of low efficiency and cannot meet user needs, a novel method based on deep time and space features along transmission line is proposed in this paper, which...

It is very important to extract discriminative electrical signal features in lean management of power grid. In this paper, we develop a new current signal waveform feature. Firstly, the electronic signal waveform is segmented into different segments with different property, and then the synthetic features including shape feature, harmonic feature and statistic features are extracted. To illustrate the effectiveness of the synthetic features, we use them in non-invasive load monitoring (NILM). The similarity measurement is defined and calculated between each pairs of segments based on the synthetic features, and the maximum clique searching algorithm is proposed to identify the consistent segments as state categories. The experimental results show that our method can significantly enhance the precision and recall while identifying states in a more fine-grain style compared with state-of-the-art NILM methods.