In terms of the problems of high feature dimension and large data redundancy in the wind and solar power prediction method, an improved prediction model is proposed by combining feature selection methods with the long- and short-term time-series network (LSTNet). The long short-term memory (LSTM) unit in the LSTNet model is replaced with the bidirectional long short-term memory (BiLSTM), which enables recursive response training for the states of hidden layers at the start and end of the sequence. For feature selection, both feature screening and dimension reduction methods are considered, including random forest (RF), grey relational analysis (GRA), and principal component analysis (PCA). Finally, based on wind and solar power data, the effectiveness of the proposed methods is verified, where the RF-LSTNet performs the best. For wind power prediction, the mean absolute percentage error is reduced by 29.7% and root mean square error is reduced by 24.1% compared with the traditional LSTNet model, and for solar power prediction, the MAPE is reduced by 12.9% and RMSE is reduced by 3.8%.
Background:
To solve the problem of accurate measurement of nonlinear harmonic electric energy, a method for improving the harmonic electric energy measurement method based on the discrete wavelet packet decomposition and reconstruction algorithm is proposed.
Objectives:
Designs a reactive energy measurement method combined with Hilbert transformation, discusses the frequency characteristics of wavelet function, and points out that too high sampling rate will decrease in harmonic power measurement accuracy. By setting the discrete wavelet packet transformation decomposition, the stepping of the wavelet form brought by the excessively large wavelet packet decomposition scale is eliminated by the moncoband reconstruction algorithm.
Methods:
Experimental results show that the detection error obtained by numerical simulation using the wavelet transform algorithm is close to the standard instrument, with the maximum reference error within 0.013%~0.030%.
Results and Conclusion:
The feasibility and measurement accuracy of the nonlinear harmonic electric energy metering system are proved, providing an effective means for the accurate detection of the harmonic, interharmonic, and time-varying harmonic components of the electric power system.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.