The accurate forecast of wind power is crucial for the stable operation and economic dispatch of renewable energy power systems. To improve the accuracy of ultra-short-term wind-power forecast, we propose an improved model combining a convolutional neural network (CNN), bidirectional long short-term memory, and an attention mechanism network. First, the basic principle of the proposed model is introduced along with its merits in ultra-short-term wind-power forecast. Then, relevant data are processed based on the Pearson similarity criterion, and relevant feature parameters for wind-power forecast are optimized. Finally, the proposed model is analyzed based on the public dataset of the Baidu KDD Cup 2022 wind-power forecast competition and actual data from a wind farm in Shandong. Results show that the proposed model can effectively overcome the shortcomings of traditional forecast methods in terms of overfitting, feature extraction, and parameter tuning. Furthermore, the model exhibits higher forecast accuracy and stability.

This paper presents an optimization model for the location and capacity of electric vehicle (EV) charging stations. The model takes the multiple factors of the “vehicle–station–grid” system into account. Then, ArcScene is used to couple the road and power grid models and ensure that the coupling system is strictly under the goal of minimizing the total social cost, which includes the operator cost, user charging cost, and power grid loss. An immune particle swarm optimization algorithm (IPSOA) is proposed in this paper to obtain the optimal coupling strategy. The simulation results show that the algorithm has good convergence and performs well in solving multi-modal problems. It also balances the interests of users, operators, and the power grid. Compared with other schemes, the grid loss cost is reduced by 11.1% and 17.8%, and the total social cost decreases by 9.96% and 3.22%.

Accurate prediction of electric vehicle (EV) charging loads is a foundational step in the establishment of expressway charging infrastructures. This study introduces an approach to enhance the precision of expressway EV charging load predictions. The method considers both the battery dynamic state-of-charge (SOC) and user charging decisions. Expressway network nodes were first extracted using the open Gaode Map API to establish a model that incorporates the expressway network and traffic flow features. A Gaussian mixture model is then employed to construct a SOC distribution model for mixed traffic flow. An innovative SOC dynamic translation model is then introduced to capture the dynamic characteristics of traffic flow SOC values. Based on this foundation, an EV charging decision model was developed which considers expressway node distinctions. EV travel characteristics are extracted from the NHTS2017 datasets to assist in constructing the model. Differentiated decision-making is achieved by utilizing improved Lognormal and Sigmoid functions. Finally, the proposed method is applied to a case study of the Lian-Huo expressway. An analysis of EV charging power converges with historical data and shows that the method accurately predicts the charging loads of EVs on expressways, thus revealing the efficacy of the proposed approach in predicting EV charging dynamics under expressway scenarios.

To accurately diagnose the aging condition of the vehicle-mounted high-voltage cable terminals under the combined electro-thermal stress, this paper proposes a terahertz frequency spectrum technology-based method. First, an electro-thermal aging platform is established in the laboratory to obtain the test samples of ethylene-propylene rubber (EPR) cable terminals with different aging gradients. Then, the degree of electro-thermal aging is characterized by frequency spectrum, absorption coefficient spectrum, absorption spectrum, refractive index and dielectric constant in the terahertz domain. Moreover, the micro-morphology and micro-area structure of the test samples under different aging gradients are also observed by scanning electron microscopy, and both the material and chemical properties are analyzed. The findings demonstrate that terahertz frequency spectra offer significant benefits in non-destructively detecting and identifying the insulation condition of vehicle cable terminals during electro-thermal aging. Laboratory tests confirm the feasibility of utilizing the terahertz frequency spectrum to assess the insulation aging state of EPR cable terminals, making it potentially applicable for on-site purposes.