حمیدرضا صفا

The demand for electrical energy has sharply increased with the development of industry. However, supplying this demand through fossil fuels leads to problems such as global warming and environmental pollution. Considering the limitations and depletion of fossil fuel resources, finding sustainable alternatives has become essential. Among these alternatives, wind energy stands out as a viable renewable source for electricity generation due to its low cost and lack of pollution. However, to achieve stable power generation from wind farms, accurate information about future wind speed is essential. Predicting wind speed is highly challenging due to its random and intermittent nature. In this paper, a hybrid model combining a Temporal Convolutional Network and Bidirectional Long Short-Term Memory (TCN-BiLSTM) is employed to address this challenge and achieve accurate predictions. First, the hyperparameters of the Variational Mode Decomposition (VMD) algorithm were optimized using the powerful Optuna method. Next, the original wind speed data were normalized to enhance the performance of the hybrid model (TCN-BiLSTM) and then fed into the VMD algorithm to be decomposed into Intrinsic Mode Functions (IMFs). Each IMF is then individually fed into the hybrid model for prediction. Finally, the outputs are denormalized and combined to obtain the final result. Based on the evaluation of the hybrid model using statistical metrics, the results indicate that the proposed model achieves high accuracy. In this evaluation, the coefficient of determination (R²), mean absolute error (MAE), and root mean square error (RMSE) were found to be 99.1%, 0.36, and 0.48, respectively.

The connection of renewable energy-based microgrids in transmission lines has significantly increased recently. The presence of REMs, along with the advantages they provide, also leads to problems from different aspects of operation, control, and protection in transmission lines. The direct connection of REMs in the form of T-off in the transmission lines and without the construction of a substation, causes a severe disturbance in the performance of the protection algorithms of the line protection relays. This paper presents a fault detection method in transmission lines connected to REMs for early detection of Broken Conductor Fault (BCF) based on the information of one side of the line (the sending terminal) and using the teaching-learning artificial neural networks (ANNs). The neural network considered in this study is a combination of convolutional neural network and long short-term memory (CNN-LSTM). The hybrid model includes a Conv1D layer with 64 filters and a kernel size of 3, a MaxPooling1D layer, two LSTM layers with 32 units, a Dropout layer and a Dense layer with one unit and sigmoid activation. The necessary data for training the desired ANN have been extracted from the simulation of the main network and the implementation of various fault scenarios in MATLAB/Simulink software, and finally the considered ANN model has been programmed and modeled in the Python software environment. According to the simulation results, the accuracy of the extracted model in detecting the BCF in this proposed topology is estimated to be about 99.73%. The successful results presented in the test and evaluation results section confirm the optimal performance of the proposed algorithm.