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.

The optimal planning of grid-connected microgrids (MGs) has been extensively studied in recent years. While most of the previous studies have used fixed or time-of-use (TOU) prices for the optimal sizing of MGs, this work introduces real-time pricing (RTP) for implementing a demand response (DR) program according to the national grid prices of Iran. In addition to the long-term planning of MG, the day-ahead operation of MG is also analyzed to get a better understanding of the DR program for daily electricity dispatch. For this purpose, four different days corresponding to the four seasons are selected for further analysis. In addition, various impacts of the proposed DR program on the MG planning results, including sizing and best configuration, net present cost (NPC) and cost of energy (COE), and emission generation by the utility grid, are investigated. The optimization results show that the implementation of the DR program has a positive impact on the technical, economic, and environmental aspects of MG. The NPC and COE are reduced by about USD 3700 and USD 0.0025/kWh, respectively. The component size is also reduced, resulting in a reduction in the initial cost. Carbon emissions are also reduced by 185 kg/year.

Due to the growing penetration of renewable energies (REs) in integrated energy system (IES), it is imperative to assess and reduce the negative impacts caused by the uncertain REs. In this paper, an unscented transformation-based mean-standard (UT-MS) deviation model is proposed for the stochastic optimization of cost-risk for IES operation considering wind and solar power correlated. The unscented transformation (UT) sampling method is adopted to characterize the uncertainties of wind and solar power considering the correlated relationship between them. Based on the UT, a mean-standard (MS) deviation model is formulated to depict the trade-off between the cost and risk of stochastic optimization for the IES optimal operation problem. Then the UT-MS model is tackled by a multi-objective group search optimizer with adaptive covariance and Lévy flights embedded with a multiple constraints handling technique (MGSO-ACL-CHT) to ensure the feasibility of Perato-optimal solutions. Furthermore, a decision making method, improve entropy weight (IEW), is developed to select a final operation point from the set of Perato-optimal solutions. In order to verify the feasibility and efficiency of the proposed UT-MS model in dealing with the uncertainties of correlative wind and solar power, simulation studies are conducted on a test IES. Simulation results show that the UT-MS model is capable of handling the uncertainties of correlative wind and solar power within much less samples and less computational burden. Moreover, the MGSO-ACL-CHT and IEW are also demonstrated to be effective in solving the multi-objective UT-MS model of the IES optimal operation problem.

Effective fault detection and isolation can improve the safety, reliability and efficiency of the district heating system. In order to detect and locate the sensor, actuator and component faults in the district heating system with faster response speed and higher accuracy, a two-level fault detection and isolation scheme, consisting of upper-level classifier for system faults and lower-level classifier for sub-faults, is developed based on convolutional neural networks. In consideration of the difficulty of obtaining the operation data of a real district heating system under various faulty states, a test benchmark model of an integrated energy based district heating system is built from the system level, which contains the renewable energy based water boilers, transmission networks, and heat load substations to examine the effectiveness of the proposed scheme. To improve the model reality, the dynamics of sensors and actuators, models of heat exchangers, and thermal inertia are considered in the district heating system, and Gaussian noises are added in the raw data signals. Nine kinds of system faults including sensor, actuator, component faults, along with three sub-fault types of bias, drift, complete failure, are investigated in the benchmark system. The performance of the proposed two-level fault detection and isolation scheme is evaluated under different data windows and Gaussian noises in the district heating system, and is compared with other data-driven methods including k-nearest neighbor, random forest and back propagation neural networks. Experimental results show that the two-level fault detection and isolation scheme can detect the faults in the district heating system accurately and robustly, and the proposed scheme has the potential to become an effective solution to real-time monitoring of faults in the district heating system.

Conventional strategies are not effective in addressing the complex protection challenges in medium-voltage DC distribution networks (MVDCDN). The main challenge in MVDCDN is the high-rising DC fault current, requiring a robust and fast protection strategy. This paper proposes the use of an Extended Kalman filter (EKF) to detect various types of DC faults using only the current signal in the MVDCDN. In the first stage, current signals from the positive and negative poles corresponding bus are obtained. The EKF is then applied to the measured DC-current signals to generate two fault detection indices. The first index is the cumulative residuals (CR), calculated using the EKF iterative differencing process with updated current estimated state and noisy measurement. The second index is the modified DC version of total harmonic distortion, known as DC distortion factor (DCDF). The fault classification/zone identification (FCZI) unit is activated if changes in CR and DCDF are detected within the observation window of the relay. In the second stage, the FCZI unit calculates the Extended Kalman filter-based predicted energy (EKFBPE) for the faulty DC line section at both ends. The polarity of EKFBPE is used for fault classification and localization decisions. The proposed protection strategy requires low-band wireless communication capability in the smart grid. Extensive simulations using MATLAB® Simulink 2022b are conducted on a ±2.5 kV MVDCDN with three feeders, considering various fault scenarios. The results demonstrate that the proposed scheme achieves 99.9% accuracy, under radial, looped, and meshed topology and is highly resilient to different types of faults with time of operation 1 msec. The scalability of proposed method and its effectiveness in handling higher voltage levels and associated fault uncertainty will investigate in future research.