Sodium (Na) metal anodes suffer from poor processability, severe volume fluctuation, unstable interfacial chemistry, and uncontrolled dendrite growth during cycling, which significantly hinder their practical application. Herein, a Na/Na₂In composite foil is fabricated through an in situ spontaneous alloying reaction enabled by a simple rolling–folding process using Na and indium (In) foils as precursors. Structural characterizations confirm the complete conversion of metallic In into the Na₂In alloy phase, forming a continuous architecture with uniformly distributed Na₂In networks embedded within the Na matrix. Owing to the sodiophilic and mechanically robust Na₂In framework, the Na/Na₂In composite anode effectively regulates Na plating/stripping behavior and suppresses dendritic growth, thereby maintaining a dense and stable electrode morphology during repeated charge/discharge processes. As a result, the Na/Na₂In symmetric cell exhibits stable cycling for over 900 h at 0.5 mA cm⁻² and 1 mAh cm⁻² with low polarization hysteresis, whereas the pure Na counterpart fails after only 143 h. Moreover, full cells paired with NaFe_1/3Ni_1/3Mn_1/3O₂ cathodes deliver enhanced cycling stability, retaining 87% of the initial capacity after 100 cycles at 0.5 C, together with improved rate capability. This work demonstrates a scalable mechanical fabrication strategy for high-stability Na metal composite anodes and provides new insights into the practical development of high-energy-density Na metal batteries.

To fully understand the energy consumption characteristics of 5G base-station, a DBSCAN-based energy consumption pattern clustering identification method is proposed for 5G base-station. Firstly, this paper analyzes the daily-curve characteristics of power consumption behavior in typical application scenarios of 5G base-station for further pattern clustering identification. Then, the proposed pattern clustering identification method is depicted based on DBSCAN (Density-Based Spatial Clustering of Applications with Noise) clustering decision, which is composed of the feature extraction for power consumption daily-curve of 5G base-station. Finally, the experiment is implemented using actual operation data of 5G base-station as data source. The experiment results illustrate that the proposed method can effectively identify the clustering characteristics of the energy consumption behavior for 5G base-station.

An accurate forecast of the state of charge (SOC) of lithium-ion batteries is vital to ensure the safe use of lithium-ion batteries. The accurate estimation method of lithium-ion battery (BAT) SOC is realized by optimizing the neural network parameter method and stable and fast transverse filtering algorithm (SFTA).The backtracking search algorithm (BSA) is used to optimize the output weight and threshold of Radial basis function neural network(RBFNN), to realize the SOC prediction of ternary lithium polymer battery. Experimental results show that the proposed algorithm can achieve reliable SOC estimation and parameter identification of a combined empirical model. The adaptive voltage estimation error is controlled within 2%, and the SOC prediction accuracy under the different temperatures of the RBFNN-BSA algorithm is controlled within 2.5%, which meets the actual requirements.