Short-term power load forecasting in China: A Bi-SATCN neural network model based on VMD-SE.

This study focuses on improving short-term power load forecasting, a critical aspect of power system planning, control, and operation, especially within the context of China's "dual-carbon" policy. The integration of renewable energy under this policy has introduced complexities such as nonlinearity and instability. To enhance forecasting accuracy, the VMD-SE-BiSATCN prediction model is proposed. This model improves computational efficiency and reduces prediction errors by analyzing and reconstructing sequence component complexity using sample entropy (SE) following variational mode decomposition (VMD). Additionally, a self-attention mechanism is integrated into the temporal convolutional network (TCN) to overcome the traditional TCN's limitations in capturing long-term dependencies. The model was evaluated using data from the China Ninth Electrical Attribute Modeling Competition and validated with real-world data from a specific county in Shijiazhuang City, Hebei Province, China. Results indicate that the VMD-SE-BiSATCN model outperforms other models, achieving a mean absolute error (MAE) of 92.87, a root mean square error (RMSE) of 126.906, and a mean absolute percentage error (MAPE) of 0.81%.

Functional compressive mechanics and tissue biocompatibility of an injectable SF/PU hydrogel for nucleus pulposus replacement.

In spinal degenerative disease, an injectable liquid hydrogel can fill in defect entirely, lessen the danger of implant relocation and following loss of disc height, minimizing the operative trauma. Here, we propose an injectable in-situ chemically cross-linked hydrogel by a two-component reaction of liquid silk fibroin with liquid polyurethane at physiological temperature conditions. Confined compression tests and fatigue tests were reported to assess physical properties of the hydrogel. Impact of different diameter on the biomechanical behaviours was tested to evaluate the clinical potentiality of the hydrogel for replacing nucleus pulposus. Degradation behaviours in different solutions and animal experiments were also investigated to examine the tissue biocompatibility of the hydrogel. The hydrogel modulus was affected by the hydrogel geometrical (diameter) parameters. SF/PU composite hydrogel can survive a million cycles, unconstrained fatigue resistance. More importantly, in vivo biocompatibility using New Zealand white rabbits, showed good biocompatibility over a three-month period in culture. Particularly, they showed the significant clinical merit of providing stronger axial compressive stiffness on confined compression test. Based on the outcomes of the present research, the SF/PU composite hydrogel may provide significant advantages for use in future clinical application in replacing nucleus pulposus field.