In order to improve the accuracy of spatial load forecasting in power grid planning stage, a spatial load forecasting method based on density-based spatial clustering of applications with noise (DBSCAN) clustering algorithm and nonlinear auto regressive (NAR) neural network is proposed. This method consists of three stages: cell division, clustering, and forecasting. At first, zones are divided into cellules that are taken as the basic unit of spatial load forecasting. Historical yearly load profiles, along with geographic information and land use types, are extracted from cells as features. Furthermore, similar cells are classified into several clusters according to these features. Finally, a NAR neural network is established to forecasting load one year ahead for each cluster, where the historical load profiles are taken as input. Experiments reveal that our proposed model decreases MAE by 45.95%, 42.04% and 47.49% respectively compared with linear regression, grey theory and exponential smoothing, showing great improvements in accuracy.
Global climate change and sea level rise have led to increased losses from flooding. Accurate prediction of floods is essential to mitigating flood losses in coastal cities. Physically based models cannot satisfy the demand for real-time prediction for urban flooding due to their computational complexity. In this study, we proposed a hybrid modeling approach for rapid prediction of urban floods, coupling the physically based model with the light gradient boosting machine (LightGBM) model. A hydrological–hydraulic model was used to provide sufficient data for the LightGBM model based on the personal computer storm water management model (PCSWMM). The variables related to rainfall, tide level, and the location of flood points were used as the input for the LightGBM model. To improve the prediction accuracy, the hyperparameters of the LightGBM model are optimized by grid search algorithm and K-fold cross-validation. Taking Haidian Island, Hainan Province, China as a case study, the optimum values of the learning rate, number of estimators, and number of leaves of the LightGBM model are 0.11, 450, and 12, respectively. The Nash-Sutcliffe efficiency coefficient (NSE) of the LightGBM model on the test set is 0.9896, indicating that the LightGBM model has reliable predictions and outperforms random forest (RF), extreme gradient boosting (XGBoost), and k-nearest neighbor (KNN). From the LightGBM model, the variables related to tide level were analyzed as the dominant variables for predicting the inundation depth based on the Gini index in the study area. The proposed LightGBM model provides a scientific reference for flood control in coastal cities considering its superior performance and computational efficiency.
The rapid growth of distributed generation (DG) and load has highlighted the necessity of optimizing their ways of integration, as their siting and sizing significantly impact distribution networks. However, little attention has been paid to the siting and sizing of new substations which are to be installed. This paper proposes deep learning-aided joint DG-substation siting and sizing in distribution network stochastic expansion planning. First, as the model depends on an accurate forecast, Long Short-Term Memory (LSTM) deep neural network is used to forecast DG output and load, where electricity growth rate, bidding capacity of the electric expansion, and industrial difference are all considered. Then, a two-stage stochastic mixed integer bilinear programming model was established for joint DG-substation siting and sizing under uncertainties, where multiple objective functions are comprehensively addressed. By using the Fortuny-Amat McCarl Linearization, the resultant bilinear model is equivalently transformed into a mixed integer linear program, which can be efficiently solved. Finally, stochastic power flow calculation in the IEEE 69-node system is conducted to analyze the influence of electric expansion and DG integration on the node voltage and power flow distribution of the power system. The effectiveness of the proposed method is also verified by simulation tests.
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.