Search

Short-term power load forecasting is the basis for ensuring the safe and stable operation of the power system. However, because power load forecasting is affected by weather, economy, geography, and other factors, it has strong instability and nonlinearity, making it difficult to improve the accuracy of short-term power load forecasting. To solve the above problems, a load forecasting method combining empirical modal decomposition (EMD) and long short-term memory neural network (LSTM) has been proposed. The original signal is first decomposed into a series of eigenmode functions and a residual quantity using the EMD algorithm. Subsequently, all the components are fed into the LSTM network. To further improve the load prediction accuracy, a self-attention mechanism is introduced for large component signals to further explore the internal correlation of the data, and the Sparrow Optimisation Algorithm (SSA) is used to optimize the LSTM hyperparameters. Combining EMD, LSTM, self-attention mechanism (SAM), and SSA, the EMD-SSASAM -LSTM method for short-term power load forecasting is further proposed. The results show that the coefficient of determination (R2) of the method is 0.98, the mean absolute error (MAE) is 0.013, the root mean square error (RMSE) is 0.018, and the mean absolute percentage error (MAPE) is 2.57%, which verifies that the proposed model can improve the accuracy of load forecasting, and has a certain application prospect. [ABSTRACT FROM AUTHOR]

In this work, modal decomposition is employed to generate more data for matching scenarios with more complex topography for predicting wind power output in the case of complex terrain. The existing literature shows that a single wind power output forecast model is difficult to cope with complex terrain and thus the accuracy of wind power output forecast is limited. This work combines the advantages of attention mechanism and convolutional neural network for a novel network based on modal decomposition of historical data for wind power output forecast on complex terrain. The proposed novel network can break through the limitations of a single wind power output forecast model. In addition, the signals that are modally decomposed can be predicted more accurately. The presented method is contrasted with various other algorithms for the wind power output prediction problem in complex terrain. Comparative experiments show that the proposed network achieves a higher accuracy rate. [ABSTRACT FROM AUTHOR]

Short-term power load forecasting is the basis for ensuring the safe and stable operation of the power system. However, because power load forecasting is affected by weather, economy, geography, and other factors, it has strong instability and nonlinearity, making it difficult to improve the accuracy of short-term power load forecasting. To solve the above problems, a load forecasting method combining empirical modal decomposition (EMD) and long short-term memory neural network (LSTM) has been proposed. The original signal is first decomposed into a series of eigenmode functions and a residual quantity using the EMD algorithm. Subsequently, all the components are fed into the LSTM network. To further improve the load prediction accuracy, a self-attention mechanism is introduced for large component signals to further explore the internal correlation of the data, and the Sparrow Optimisation Algorithm (SSA) is used to optimize the LSTM hyperparameters. Combining EMD, LSTM, self-attention mechanism (SAM), and SSA, the EMD-SSA- SAM -LSTM method for short-term power load forecasting is further proposed. The results show that the coefficient of determination (R2) of the method is 0.98, the mean absolute error (MAE) is 0.013, the root mean square error (RMSE) is 0.018, and the mean absolute percentage error (MAPE) is 2.57%, which verifies that the proposed model can improve the accuracy of load forecasting, and has a certain application prospect.

In order to improve the accuracy of the short-term prediction of building energy consumption, this study proposes a short-term prediction model of building energy consumption based on the CEEMDAN-BiLSTM method. In this study, the energy consumption data of an office building in 2019 are selected as a sample, and CEEMDAN is used to decompose the energy consumption data into multiple components, and the strong correlation components are selected and sent to the BiLSTM network. The final energy consumption prediction results are obtained by superimposing the prediction results of each sub-component, and five models are built simultaneously to compare the errors with the proposed models. The results showed that the weather type has a great influence on the accuracy of energy consumption prediction. When the weather fluctuates greatly, the prediction error of energy consumption by a single prediction model is large. When the weather suddenly changes, the EMD-LSTM model has a big error in the prediction of air conditioning energy consumption. After CEEMDAN decomposition of energy consumption data, more detailed components can be extracted, which makes the BiLSTM prediction algorithm more accurate. Compared with the CEEMDAN-LSTM model, the CEEMDAN-BiLSTM model reduces eRMSE, eMAPE, and eTIC by 4.1%, 9.441, and 1.3%, respectively. The proposed model can effectively improve the accuracy of short-term prediction of building energy consumption.

The influence of different test methods on the accuracy of mode identification is not clear, and it is necessary to explore the error transfer characteristics in mode decomposition of fan noise. Numerical and experimental research studies are carried out on the advantages and disadvantages of radial rake and axial microphone array and error transmission characteristics in mode decomposition. In the numerical study, the error transmission characteristics of different arrays are investigated by adding random disturbances to the artificial sound field, so as to evaluate the applicability and limitations of the two typical arrays in mode identification based on the error analysis theory. The mode recognition error of the single-stage axial flow fan is investigated experimentally using the designed radial rakes and axial arrays. The results show that although the radial rake can directly measure the radial distribution of the modal amplitude, it has a large error in the mode identification at low frequencies. Compared with the radial rake, axial array will take more priority in practical applications. The accuracy of the axial microphone array in mode recognition strongly depends on the axial spacing of the array measuring sensors. The small deviations in the mode identification when applying the two typical arrays are caused by the different signal-to-noise ratio of the sound pressure signals acquired by the two arrays and their discriminative sensitivities to the duct airflow. Based on the obtained modal identification error characteristics, an effective mode identification method can be proposed to help fan noise reduction design.