The widespread adoption of electric vehicles (EVs) has posed significant challenges to the security of distribution grid loads. To address issues such as increased grid load fluctuations, rising user charging costs, and rapid load surges around midnight caused by uncoordinated nighttime charging of household electric vehicles in communities, this paper first models electric vehicle charging behavior as a Markov Decision Process (MDP). By improving the state-space sampling mechanism, a continuous space mapping and a priority mechanism are designed to transform the charging scheduling problem into a continuous decision-making framework while optimizing the dynamic adjustment between state and action spaces. On this basis, to achieve synergistic load forecasting and charging scheduling decisions, a forecast-augmented deep reinforcement learning method integrating Gated Recurrent Unit and Twin Delayed Deep Deterministic Policy Gradient (GRU-TD3) is proposed. This method constructs a multi-objective reward function that comprehensively considers time-of-use electricity pricing, load stability, and user demands. The method also applies a single-objective pre-training phase and a model-specific importance-sampling strategy to improve learning efficiency and policy stability. Its effectiveness is verified through extensive comparative and ablation validation. The results show that our method outperforms several benchmarks. Specifically, compared to the Deep Deterministic Policy Gradient (DDPG) and Particle Swarm Optimization (PSO) algorithms, it reduces user costs by 11.7% and the load standard deviation by 12.9%. In contrast to uncoordinated charging strategies, it achieves a 42.5% reduction in user costs and a 20.3% decrease in load standard deviation. Moreover, relative to single-objective cost optimization approaches, the proposed algorithm effectively suppresses short-term load growth rates and mitigates the “midnight peak” phenomenon.
With the continuous development of society and the advancement of science and technology, information technology has been fully popularized and promoted in various fields. At present, artificial intelligence technology has been further applied in the educational sector, and its application in the architectural design major is driving the transformation of teaching towards intelligence and integration. This paper first analyzes the value of generative artificial intelligence in empowering teaching for the architectural design major, and on this basis, extracts the paths for teaching reform in this major empowered by generative artificial intelligence. It is hoped that this paper can provide teaching inspiration and practical references for frontline teachers, and promote the reform and innovation of the architectural design major.
In the field of contemporary textile pattern design, floral patterns are widely favored due to their diversity and aesthetic appeal. However, due to the wide variety of flowers and their complex morphological structures, accurately presenting their characteristics and aesthetic appeal through computer-aided design techniques, such as 3D modeling, poses certain challenges. Based on this, the study proposes a graphic editing algorithm that combines 3D data with a directional bounding box method. On this basis, a textile pattern design system is established. The results show that the proposed algorithm performs exceptionally well. Experimental results on the Oxford 102 Flower Dataset indicate that the proposed algorithm achieves a mean squared error of 0.25, a root mean squared error of 0.001, and a mean absolute error of 0.0017. In addition, the method for extracting contour sampling points based on the front and side angles of flowers maintains flower contour integrity over 85% throughout the experimental process, reaching 100% at most. These findings suggest that the proposed method can comprehensively capture flower-contour information and generate two-dimensional design drawings with high accuracy, thereby improving the efficiency of textile pattern design.