Dynamic environmental economic dispatch (DEED) with wind power is an important extension of the classical environmental economic dispatch (EED) problem, which could provide reasonable scheduling scheme to minimize the pollution emission and economic cost at the same time. In this study, the combined dynamic scheduling of thermal power and wind power is carried out with pollutant emission and economic cost as optimization objectives; meanwhile, the valve‐point effect, power balance, ramp rate, and other constraints are taken into consideration. In order to solve the DEED problem, an enhanced multi‐objective differential evolution algorithm (EMODE) is proposed, which adopts the superiority of feasible solution (SF) and nondominated sorting (NDS) two selection strategies to improve the optimization effect. The suggested algorithm combines the total constraint violation and penalty function to deal with various constraints, due to different constraint techniques could be effective during different stages of searching process, and this method could ensure that each individual in the Pareto front (PF) is feasible. The results show that the proposed algorithm can deal with DEED problem with wind power effectively, and provide better dynamic scheduling scheme for power system.
Summary
This article presents a new optimization method to solve dynamic economic emission dispatch (DEED) problem incorporating wind power by using a hybrid nature inspired multi‐objective algorithm based on equilibrium optimizer (EO) and differential evolution (DE). In the proposed algorithm, the EO with a competitive mechanism and an additional exploration strategy is devised to explore the whole search space, while the DE with a ranking mutation operator and an opposition‐based learning strategy (OBL) is suggested to evolve the individuals of the external archive. The Kent chaotic map is adopted to generate a uniformly distributed initial population. The approach based on non‐dominated sort and improved crowding distance is utilized to screen equilibrium particles' leaders and to update the external archive. These strategies attempt to obtain a Pareto optimal front with excellent diversity and good convergence. Moreover, a real‐time constraints adjustment method and a penalty function method are combined to deal with complex constraints. The simulation results on the test system containing 10 thermal power units and one wind farm indicate that the proposed approach has much better performance than other methods for comparison.
Mesoscale convective cloud systems have a small horizontal scale and a short lifetime, which brings great challenges to quantitative precipitation estimation (QPE) by satellite remote sensing. Combining machine learning models and geostationary satellite spectral information is an effective method for the QPE of mesoscale convective cloud, while the interpretability of machine learning model outputs remains unclear. In this study, based on Himawari-8 data, high-density automatic weather station observations, and reanalysis data over the North China Plain, a random forest (RF) machine learning model of satellite-based QPE was established and verified. The interpretation of the output of the RF model of satellite-based QPE was further explored by using the Shapley Additive Explanations (SHAP) algorithm. Results showed that the correlation coefficient between the predicted and observed precipitation intensity of the RF model was .64, with a root-mean-square error of .27 mm/h. The importance ranking obtained by SHAP model is completely consistent with the outputs of random forest importance function. This SHAP method can display the importance ranking of global features with positive/negative contribution values (e.g., current precipitation, column water vapor/black body temperature, cloud base height), and can visualize the marginal contribution values of local features under interaction. Therefore, combining the RF and SHAP methods provides a valuable way to interpret the output of machine learning models for satellite-based QPE, as well as an important basis for the selection of input variables for satellite-based QPE.
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.