In this paper, a novel signal processing method combining mathematical morphology (MM) and Walsh theory is proposed, which uses Walsh functions to control the structuring element (SE) and MM operators. Based on the Walsh-MM method, a scheme for power quality disturbances detection and classification is developed, which involves three steps: denoising, feature extraction and morphological clustering. First, various evolution rules of Walsh function are used to generate groups of SEs for the multiscale Walsh-ordered morphological operation, so the original signal can be denoised. Next, the fundamental wave of the denoised signal is suppressed by Hadamard matrix; thus, disturbances can be extracted. Finally, the Walsh power spectrum of the waveform extracted in the previous step is calculated, and the parameters of which are taken by morphological clustering to classify the disturbances. Simulation results reveal the proposed scheme can effectively detect and classify disturbances, and the Walsh-MM method is less affected by noise and only involves simple calculation, which has a potential to be implemented in hardware and more suitable for real-time application.

Energy disaggregation or non-intrusive load monitoring (NILM) aims to identify the operating state of every single appliance from given aggregate energy. Many methods are only based on time information, which have difficulties in identifying multi-state processes of an appliance as important information may be lost when the sequence is too long. Considering frequency domain features offer additional information and have the advantage of data compression, this paper proposes to make full use of time-frequency information. First, a time series of aggregated power is reshaped into a sequence of 2D images, and then wavelet decomposition (WD) is employed to extract time-frequency information in horizontal, vertical, and diagonal directions. Afterwards, information is processed by a bidirectional long-short term memory (BiLSTM) network, which is designed to obtain more comprehensive and accurate predictions through bi-directional information capture, to identify which appliances are in operation. Finally, the prob-sparse attention mechanism is implemented to identify the multi-state processes of appliances by assigning different weights to the hidden layer units of the BiLSTM network. Throughout the network, convolution neural network (CNN) with different strides is introduced as down-sampling to ensure identical image sizes and concatenation layers are used for single-branch reconstruction of WD. In simulation studies, the model is trained and validated with low-frequency data in the UK-DALE and REDD datasets, and results show that compared with some state-of-the-art methods, the proposed method has a remarkable improvement in disaggregation performance.

With the integration of alternative energy and renewables, the issue of stability and resilience of the power network has received considerable attention. The basic necessity for fault diagnosis and isolation is fault identification and location. The conventional intelligent fault identification method needs supervision, manual labelling of characteristics, and requires large amounts of labelled data. To enhance the ability of intelligent methods and get rid of the dependence on a large amount of labelled data, a novel fault identification method based on deep reinforcement learning (DRL), which has not received enough attention in the field of fault identification, is investigated in this paper. The proposed method uses different faults as parameters of the model to expand the scope of fault identification. In addition, the DRL algorithm can intelligently modify the fault parameters according to the observations obtained from the power network environment, rather than requiring manual and mechanical tuning of parameters. The methodology was tested on the IEEE 14 bus for several scenarios and the performance of the proposed method was compared with that of population-based optimization methods and supervised learning methods. The obtained results have confirmed the feasibility and effectiveness of the proposed method.

Wind farms usually cluster in areas with abundant wind resources. Therefore, spatial dependence of wind speeds among nearby wind farms should be taken into account when modeling a power system with large-scale wind power penetration. This paper proposes a novel non-parametric copula method, multivariate Gaussian kernel copula (MGKC), to describe the dependence structure of wind speeds among multiple wind farms. Wind speed scenarios considering the dependence among different wind farms are sampled from the MGKC by the quasi-Monte Carlo (QMC) method, so as to solve the stochastic economic dispatch (SED) problem, for which an improved mean-variance (MV) model is established, which targets at minimizing the expectation and risk of fuel cost simultaneously. In this model, confidence interval is applied in the wind speed to obtain more practical dispatch solutions by excluding extreme scenarios, for which the quantile-copula is proposed to construct the confidence interval constraint. Simulation studies are carried out on a modified IEEE 30-bus power system with wind farms integrated in two areas, and the results prove the superiority of the MGKC in formulating the dependence among different wind farms and the superiority of the improved MV model based on quantile-copula in determining a better dispatch solution.