Wind farms commonly cluster in regions rich in wind resources. Thus, correlation of wind speeds from different wind farms should not be ignored when modeling a power system with large wind energy penetration. This paper proposes a probabilistic optimal power flow (POPF) technique based on the quasi-Monte Carlo simulation (QMCS) considering the correlation of wind speeds using copula functions. In this paper, a copula function is used to model the dependent structure of random wind speeds and their forecast errors. QMCS is employed in the sampling procedure to reduce computation burden. The proposed method is applied in probabilistic power flow (PPF). Furthermore, the PPF is used in the POPF problem that aims at minimizing the expectation and downside risk of fuel cost simultaneously. Simulation studies are conducted on a modified IEEE 118-bus power system with wind farms integrated in two areas, and the results show that the accuracy and efficiency are improved by the proposed method.

Effective fault diagnosis for power electronic converters is an essential and mandatory operation to reduce failures and unscheduled shutdowns. This paper presents a datadriven fault diagnosis method, using long short-term memory (LSTM) network, to detect multiple open-circuit switch faults of the back-to-back converter in doubly-fed induction generator (DFIG)-based wind turbine systems. Twelve sensor signals of the back-to-back converter for different fault types are measured. Wind speed fluctuation and sensor bias faults are considered as interference factors. The method has been evaluated in a grid-connected DFIG simulink model. Simulation results have demonstrated that, compared with least squares support vector machine (LS-SVM), back-propagation artificial neural network (BPANN) and recurrent neural network (RNN), the proposed method excavates the deep information of the fault signal with the highest diagnosis accuracy and strongest robustness with short time delay. Experimental tests undertaken on a hardware-in-theloop testing platform further validate the effectiveness of the LSTM-bsed network.

In order to improve the reliability of wind turbines, avoid serious accidents and reduce operation and maintenance costs, it is important to effectively detect early faults of wind turbines operating in harsh environment. This paper proposes a data-driven fault diagnosis and isolation (FDI) method for wind turbines, which implements Long Short-Term Memory (LSTM) networks for residual generator and applies the random forest (RF) algorithm for decision making. The method has been evaluated in a wind turbine benchmark simulink model proposed in the literature, in comparison with four model-based algorithms and four data-driven methods, and the results have shown that the proposed method achieves the highest accuracy. Moreover, extensive evaluation has been conducted to analyse the robustness of proposed method, and the experimental results have verified the stability of the proposed method in diagnosis of wind turbine faults.

As power to gas (P2G) technology gradually matures, the coupling between electricity networks and natural gas networks should ideally evolve synergistically. With the intent of characterizing market behaviors of integrated electric power and natural gas networks (IPGNs) with P2G facilities, this paper establishes a steady-state model of P2G and constructs optimal dispatch models of an electricity network and a natural gas network separately. In addition, a concept of slack energy flow (SEF) is proposed as a tool for coordinated optimal dispatch between the two networks. To study how the market pricing mechanism affects coordinated optimal dispatch in an IPGN, a market equilibrium-solving model for an IPGN is constructed according to game theory, with a solution based on the Nikaido-Isoda function. Case studies are conducted on a joint model that combines the modified IEEE 118-node electricity network and the Belgian 20-node gas network. The results show that if the game between an electric power company and a natural gas company reaches market equilibrium, not only can both companies maximize their profits, but also the coordinated operation of the coupling units, i.e., gas turbines and P2G facilities, will contribute more to renewable energy utilization and carbon emission reduction.

With the promotion and application of smart grid, the technology of non-intrusive load monitoring (NILM) has gained more and more attention in recent years. Different from direct device monitoring, it identifies the type of appliances using the aggregated load profile measured at a single metering point, which is more convenient and flexible, and thus has the potential to be extended to all households equipped with smart meters. This paper proposes an extensible and comprehensive model to solve the load disaggregation problem, which employs the additive factorial approximate maximum a posteriori (AFAMAP) based on iterative fuzzy ${c}$ -means (IFCM). To make sure that the model is adaptive to other households, the hidden Markov models (HMMs) are applied to obtain the independent load model of each appliance, and the IFCM is used to determine the number of hidden states adaptively. Finally, the AFAMAP is utilized to decompose the aggregated power consumption based on the independent load models built by HMM. Simulation studies are conducted on the open database of Almanac of Minutely Power dataset (AMPds), and the results have demonstrated that the proposed model is more accurate in comparison with the other models.

This study proposes a novel scheme using mathematical morphology to effectively discriminate between the internal fault and inrush currents of power transformers. The proposed scheme consists of two parts. The first part is based on morphological gradient (MG), for discrimination of currents occurring without considering the current transformer (CT) saturation. The second one uses a symmetrical criterion involving MG to identify internal fault current under CT saturation. To demonstrate its compatibility and efficiency, the scheme is verified employing the data simulated using PSCAD/EMTDC and data collected from laboratory experiment, respectively. The simulation and experimental results indicate that the proposed scheme can improve the accuracy of inrush current identification, even under certain extreme conditions.