Haowen Li

In order to address the challenge of achieving optimal prediction accuracy when a single prediction model faced with changes in meteorological conditions of different weather types, this paper proposes a photovoltaic (PV) power prediction method based on the combination of similar day clustering and convolutional neural network (CNN)-gated recurrent unit (GRU). The Pearson correlation coefficient and Spearman’s correlation coefficient are used to filter out the key features such as total solar radiation and module temperature to construct a new input dataset; the K-means algorithm is used to perform clustering analysis on the data, and the data are classified into sunny, cloudy, and rainy days; the spatial correlation features of the meteorological factors are extracted by using the convolutional neural network (CNN), and the CNN-GRU model is established by combining with the gated recurrent units (GRUs). The PV output power is predicted based on the PV power data and the corresponding meteorological data from a place in Ningxia, collected during June to August 2020, and the method proposed in the article is tested. Validation results show that, compared to other models, the model proposed in this paper reduces MAE and RMSE by 66.1% and 65.7% on average under three different weather type scenarios, and improves R² by 19.8% on average. This verifies that the model has high prediction accuracy and generalization ability, achieving better results in PV output power prediction. The CNN-GRU model demonstrates superior capability in modeling short- and long-term dependencies compared to other deep learning hybrid approaches, while also achieving higher computational efficiency and faster training convergence.

Currently, the layout planning of power exchange facilities in urban areas is not perfect, which cannot effectively meet the power exchange demand of urban operating vehicles and restricts the operation of urban operating vehicles. The article proposes a vehicle power exchange demand-oriented power exchange station siting planning scheme to meet the rapid replenishment demand of operating vehicles in urban areas. The spatial and temporal distribution of power exchange demand is predicted by considering the operation law, driving law, and charging decision of drivers; the candidate sites of power exchange stations are determined based on the data of power exchange demand; the optimization model of the site selection of power exchange stations with the lowest loss time of vehicle power exchange and the lowest cost of the planning and construction of power exchange stations is established and solved by using the joint algorithm of MLP-NSGA-II; and the optimization model is compared with the traditional genetic algorithm (GA) and the Density Peak. The results show that the MLP-NSGA-II joint algorithm has the lowest cost of optimizing the location of switching stations. The results show that the MLP-NSGA-II algorithm improves the convergence efficiency by about 30.23%, and the service coverage of the optimal solution reaches 94.30%; the service utilization rate is 85.35%, which is 6.25% and 19.69% higher than that of the GA and DPC, respectively. The research content of the article can provide a design basis for the future configuration of the number and location of power exchange stations in urban areas.