Due to the excellent wind power probabilistic prediction performance, Mixture Density Network (MDN) is used in short-term wind power forecasting, but the density leakage problem the Not a Number (NaN) loss problem and the choice of hyperparameters in the MDN seriously affect the model performance. GA-TDMDN is proposed in this paper for wind power probabilistic forecasting. GA-TDMDN uses truncated distribution as kernel function to solve density leakage. For the NaN loss problem that occurs during model training, different output layer activation methods and improved loss function are used for different mixture component parameters, so that the shape of the truncated normal distribution can be better controlled. Genetic Algorithms (GA) is used to optimize key hyperparameters in the MDN structure. The experimental results show that it is feasible to use truncated distribution to solve the density leakage problem, and using the GA algorithm to optimize the model structure can improve the model performance
In the process of traditional weapon-target assignment, there are two critical issues that have not been well-studied: (1) the waste of firepower resources and (2) the lack of description of the relationship between targets. Towards this end, we propose an improved weapon-target assignment model, which combines the damage probability, the weapon resource consumption and the relationship coefficient between the targets. On this basic, we design a multi-objective whale optimization algorithm based on grid division (GDMOWOA). Specifically, the algorithm uses the grid partitioning method to sort the population non-dominated, selects the optimal individual by calculating the grid number and density, and introduces an external Pareto archive to maintain the population diversity. Simulation experiments are conducted to verify the rationality and effectiveness of our solution. The results show that our algorithm has better effectiveness and superiority compared with other classical algorithms, and can effectively solve the problem of weapon-target assignment.
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.