Power quality events are usually associated with more than one disturbance and their recognition is typically based on multi-label learning. In this study, we propose a new method for recognizing multiple disturbances (MPQDs) based on variational mode decomposition (VMD) and a random discriminative projection extreme learning machine for multi-label learning (RDPEML). First, VMD is employed to decompose the MPQDs into several intrinsic mode functions and the standard energy differences of each mode are extracted as features that form the input vectors of the classifier. Second, a novel multi-label classifier called RDPEML is constructed by combining a random discriminative projection multiclass extreme learning machine (ELM) and a thresholding learning method-based kernel ELM. In order to obtain better classification performance, a tenfold cross-validation embedded particle swarm optimization approach is utilized to search for the optimal values of the structural parameters. Finally, a test study was conducted using Matlab synthetic signals and real signals sampled from a three-phase standard source under different noise conditions. Compared with several recent state-of-the-art multi-label learning algorithms, RDPEML achieved better classification performance with superior computational speed.

In this paper, a new classification approach for detection and classification of complex power quality disturbances (PQDs) using a three-level multiply connected Bayesian network is proposed. First, the model consisting of features evidence layer, disturbances state layer, and circumstance evidence layer is established, which represent the features extracted from the sample signal, the state of each single label of PQDs and the circumstance factors that may affect the PQDs, respectively. Second, the parameters of three-level multiply connected Bayesian network (TLBN) are studied from statistical data and Monte Carlo simulations. Finally, the classification is determined by computing the posterior marginal probabilities of each event given observed evidences. The new method not only utilizes the existing features extracting methods, but also takes the historical data, and other surrounding factors into account. Simulation results and real-life PQ signal tests show that the performances of TLBN classification of complex disturbances are better than the other approaches in existing literatures.

This paper proposes an interactive decision-making model for the operations of electric vehicles (EVs) and power grid, in the perspective of energy and reserve. In this model, EVs optimize their energy and reserve plans considering prices set by the power grid. Meanwhile, the power grid aims to obtain the optimal energy and reserve prices for EVs, in order to maximize its benefits. Afterward, we use the generalized Stackelberg game to formulate the interactive decision-making model, and prove the existence and uniqueness of the generalized Stackelberg equilibrium. Finally, simulation results verify that the proposed interactive model can well enhance benefits of EVs while guaranteeing their quality of charging services.

The traditional power quality disturbances classification methods include three stages, i.e., feature extraction, feature selection, classifier training. These methods suffer from low accuracy and a limited improvement margin. Since deep learning can greatly improve the accuracy of classification, a new classification method was designed in this paper by combining three types of deep learning frameworks, including CNN-GRU, ResNet-GRU, and Inception-GRU. The proposed method omits the two steps of feature extraction and feature selection, achieving “end-to-end” PQDs identification. To improve the performance on real signals, “pre-training and re-training” is applied. Then, a voting method was employed to vote the prediction labels by different algorithms, which further improves the accuracy of classification. Simulation experiments show that for the classification of compound PQDs, the proposed method performs better than the triple-stage methods and single deep learning classification method. Finally, real signals from Power source are test by the twice-trained model, and the five metrics are better than the old methods.

This paper presents a day-ahead coordinated scheduling method of hydro and wind power generation systems (HWPGSs) with consideration of uncertainties. In this method, we first formulate the coordinated scheduling model with two-part price and power flow constraints, which can well manifest the fixed and variable economic benefits as well as the secure operation of HWPGS, respectively. Then, the interval analysis is used for studying the effect of uncertain wind power, water inflow, and electricity load on the coordinated scheduling model. Finally, we use a real test system in a western area of China to conduct simulation studies, which verify the effectiveness of the interval analysis and the effect of price mechanism on the day-ahead coordinated scheduling of HWPGS.

This paper proposes a high efficient approach for power disturbance waveform (PDW) compression in the view of Heisenberg uncertainty. The key idea is trying to represent each signal component of PDW by nonzero coeffients as few as possible with the uncertainty principle restriction. PDWs are projected in a union of bases (UB), and each signal component of the PDWs can be represented very sparsely. The UB decomposition is solved by orthogonal matching pursuit (OMP). The features and cross correlation of subbases of the UB guarantee the PDW compression with high compression ratio and recovered accuracy. With various simulated and field PDWs tests, the compressed data size of the new method is proved with good characteristics such as low sensitivity to sampling frequency increment and to types of signal components contained in PDWs. Besides, it is found that the new method and methods which employ wavelet techniques share similar effect of noise for PDW compression. The proposed method is also applied in a 220kV power substation for field PDWs compression from fault recorders. The comparisons, analyses and experiments indicate that the proposed method has a high PDWs compression efficiency for future power grid monitoring.