The highlighted energy consumption of Internet data center (IDC) in China has become a pressing issue with the implementation of the Chinese dual carbon strategic goal. This paper provides a comprehensive review of cooling technologies for IDC, including air cooling, free cooling, liquid cooling, thermal energy storage cooling and building envelope. Firstly, the environmental requirements for the computer room and the main energy consumption items for IDC are analyzed. The evaluation indicators and government policies for promoting green IDC are also summarized. Next, the traditional cooling technology is compared to four new cooling technologies to find effective methods to maximize energy efficiency in IDC. The results show that traditional cooling consumes a significant amount of energy and has low energy efficiency. The application of free cooling can greatly improve the energy efficiency of IDC, but its actual implementation is highly dependent on geographical and climatic conditions. Liquid cooling, on the other hand, has higher energy efficiency and lower PUE compared to other cooling technologies, especially for high heat density servers. However, it is not yet mature and its engineering application is not widespread. In addition, thermal energy storage (TES) based cooling offers higher energy efficiency but must be coupled with other cooling technologies. Energy savings can also be achieved through building envelope improvements. Considering the investment and recovery period for IDC, it is essential to seek efficient cooling solutions that are suitable for IDC and take into account factors such as IDC scale, climate conditions, maintenance requirements, etc. This paper serves as a reference for the construction and development of green IDC in China.

Cooling load forecasting is a crucial aspect of optimizing energy efficiency and efficient operation in central air conditioning systems for manufacturing plants. Due to the influence of multiple factors, the cooling load in manufacturing plants exhibits complex characteristics, including multi-peak patterns, periodic fluctuations, and short-term disturbances during meal periods. Existing methods struggle to accurately capture the relationships among variables and temporal dependencies, leading to limited forecasting accuracy. To address these challenges, this paper proposes a hybrid forecasting method based on the iTransformer-BiLSTM. First, the Pearson correlation coefficient is employed to select time-series variables that have a significant impact on cooling load. Then, iTransformer is utilized for feature extraction to capture nonlinear dependencies among multivariate inputs and global temporal patterns. Finally, BiLSTM is applied for temporal modeling, leveraging its bidirectional recurrent structure to capture both forward and backward dependencies in time series, thereby improving forecasting accuracy. Experimental validation on a cooling load dataset from a welding workshop in a manufacturing plant, including ablation studies and comparative analyses with other algorithms, demonstrates that the proposed method achieves superior performance compared to traditional approaches in forecasting accuracy. Meanwhile, by integrating the SHAP sensitivity analysis method, the contributions of input variables to the cooling load prediction results are systematically evaluated, thereby enhancing the interpretability of the model. This research provides a reliable technical foundation for energy-efficient control of central air conditioning systems in manufacturing plants.

Accurate prediction of the heat load in district heating systems is challenging due to various influencing factors, substantial transmission lag in the pipe network, frequent fluctuations, and significant peak-to-valley differences. An autoencoder—grey wolf optimization—gated recurrent unit (AE-GWO-GRU)-based heat load prediction method for district heating systems is proposed, employing techniques such as data augmentation, lag feature extraction, and input feature extraction, which contribute to improvements in the model’s prediction accuracy and heat load control stability. By using the AE approach to augment the data, the issue of the training model’s accuracy being compromised due to a shortage of data is effectively resolved. The study discusses the influencing factors and lag time of heat load, applies the partial autocorrelation function (PACF) principle to downsample the sequence, reduces the interference of lag and instantaneous changes, and improves the stationary characteristics of the heat load time series. To increase prediction accuracy, the GWO algorithm is used to tune the parameters of the GRU prediction model. The prediction error, measured by RMSE and MAPE, dropped from 56.69 and 2.45% to 47.90 and 2.17%, respectively, compared to the single GRU prediction approach. The findings demonstrate greater accuracy and stability in heat load prediction, underscoring the practical value of the proposed method.

Optimizing airflow organization is essential for ensuring the energy-efficient and secure operation of data centers. To address common airflow distribution issues in air-cooled systems, such as uneven air supply and cooling capacity imbalance, this study investigates a bidirectional airflow data center room located in a hot-summer and warm-winter region. A computational fluid dynamics (CFD) model was developed based on field-measured data to analyze the airflow distribution characteristics and evaluate the existing thermal conditions. Three optimization strategies were systematically examined: (1) Installation of rack blanking panels, (2) cold aisle containment with varying degrees of closure, and (3) combined implementations of these measures. Performance evaluation was conducted using three thermal metrics: the Return Temperature Index (RTI), Supply Heat Index (SHI), and Rack Cooling Index (RCIHI). The results demonstrate that among individual optimization strategies, rack blanking panels achieved the most significant improvement, reducing SHI by 42.61% while effectively eliminating local hotspots. For combined optimization strategies, the rack blanking panels and fully contained cold aisle containment showed optimal performance, improving cooling utilization efficiency by 88.26%. The optimal retrofit solution for this data center is the rack blanking panels with fully contained cold aisle containment. When considering budget constraints, the secondary option would be rack blanking panels with cold aisle top-only containment. These findings provide practical guidance for energy efficiency improvements in similar data center environments.

This study proposes a method based on image segmentation for accurately identifying liquid aluminum leakage during deep well casting, which is crucial for providing early warnings and preventing potential explosions in aluminum processing. Traditional DeepLabV3+ models in this domain encounter challenges such as prolonged training duration, the requirement for abundant data, and insufficient understanding of the liquid surface characteristics of casting molds. This work presents an enhanced DeepLabV3+ method to address the restrictions and increase the accuracy of calculating liquid surface areas for casting molds. This algorithm substitutes the initial feature extraction network with ResNet-50 and integrates the CBAM attention mechanism and transfer learning techniques. The results of ablation experiments and comparative trials demonstrate that the proposed algorithm can achieve favorable segmentation performance, delivering an MIoU of 91.88%, an MPA of 96.53%, and an inference speed of 55.05 FPS. Furthermore, this study presents a technique utilizing OpenCV to accurately measure variations in the surface areas of casting molds when there are leakages of liquid aluminum. In addition, this work introduces a measurement to quantify these alterations and establish an abnormal threshold by utilizing the Interquartile Range (IQR) method. Empirical tests confirm that the threshold established in this study can accurately detect instances of liquid aluminum leakage.