Abstract
Existing methods in predicting short-term photovoltaic (PV) power have low accuracy and cannot satisfy actual demand. Thus, a prediction model based on similar days and seagull optimization algorithm (SOA) is proposed to optimize a deep belief network (DBN). Fast correlation-based filter (FCBF) method is used to select a meteorological feature set with the best correlation with PV output and avoid redundancy among meteorological factors affecting PV output. In addition, a comprehensive similarity index combining European distance and gray correlation degree is proposed to select the similar day. Then, SOA is used to optimize the number of neurons and the learning rate parameters in DBN. Based on the nonuniform mutation and opposition-based learning method, an improved seagull optimization algorithm (ISOA) with higher optimization accuracy is proposed. Finally, the ISOA-DBN prediction model is established, and the experimental analysis is conducted using the actual data of PV power stations in Australia. Results show that compared with DBN, support vector machine (SVM), extreme learning machine (ELM), radial basis function (RBF), Elman, and back propagation (BP), the mean absolute percentage error indicator of ISOA-DBN is only 1.512% on a sunny day, 5.975 on a rainy day, 3.359 on a cloudy to sunny day, and 1.911% on a sunny to cloudy day. Therefore, the good accuracy of the proposed model is verified.
Highlights
The development and utilization of renewable energy has become an important measure for all countries to solve energy and environmental problems [1]
Fast correlation-based filter (FCBF) method is put forward, combining similar day and improved seagull optimization algorithm (ISOA)-deep belief network (DBN) PV power prediction model. It is compared with radial basis function (RBF), back propagation (BP), support vector machine (SVM), Elman, extreme learning machine (ELM), DBN, and other prediction models to show its superiority in prediction accuracy
By analyzing the experimental results of the model under different weather types and seasons, the following conclusions were drawn: 1) A scheme of using FCBF algorithm to screen forecast model input meteorological feature set is proposed. This approach effectively determines the most relevant meteorological features corresponding to PV power generation power, and avoids the redundancy problem among selected meteorological features
Summary
The development and utilization of renewable energy has become an important measure for all countries to solve energy and environmental problems [1]. Fast correlation-based filter (FCBF) method is put forward, combining similar day and ISOA (improved seagull optimization algorithm)-DBN PV power prediction model. It is compared with radial basis function (RBF), BP, SVM, Elman, ELM, DBN, and other prediction models to show its superiority in prediction accuracy. FCBF is a typical feature selection method, which can measure the correlation between meteorological factors and PV power generation, but can effectively avoid the redundancy among meteorological factors. The correlation between temperature and PV power is poor in the declining stage This analysis indicates that the model input meteorological feature set selected in the subsequent establishment of the prediction model includes GR and DR. DBN algorithm pretrains RBM layer by layer, and uses the supervised BP algorithm to fine-adjust and optimize the initial weight obtained from pretraining layer by layer, so that the model can obtain the optimal solution, and can represent the complex nonlinear relationship in the PV data
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
