Beijing Computing Center

With the development of social economy, the population of cities is increasing, and there are also more and more problems in urban planning, construction, management, and other aspects. At the same time, the new generation of big data information and communication technology is continuously developing and improving, and gradually integrating with various levels of society. Big data visualization technology is also widely used in the practical work of urban planning industry.

The quality of the scheduling method for virtualization clusters directly affects the performance of the entire cluster. Improper scheduling can even eliminate the advantages of virtualization clusters and reduce the performance of the entire system. Aiming at the problems of low resource utilization and poor performance caused by improper resource scheduling in cluster mode, a comprehensive heuristic resource scheduling method based on virtualization cluster - Resource Type Priority List Scheduling (RTPLS) algorithm is proposed. The entire algorithm includes two stages: resource monitoring and virtual machine scheduling. On the basis of considering multiple threshold triggering conditions such as CPU, memory, and network in the host load judgment during virtual machine scheduling, the host’s resource oscillation granularity and resource weight are introduced to comprehensively evaluate the resource load situation of the entire host, avoiding frequent migration of virtual machines caused by the oscillation of host resource load. In the selection of target virtual machine migration, in order to minimize the number of virtual machine migrations as much as possible, the compatibility coefficient λ of virtual machines is introduced, and the migration is sorted according to the priority list of λ to reduce the server load and energy consumption caused by virtual machine migration with the minimum number of virtual machine migrations. When selecting the target server, in order to minimize the load on the target virtual machine, target server relevance is introduced. Finally, by testing the algorithm in practical environments, it was found that the RTPLS algorithm can significantly improve the efficiency of host load balancing adjustments and enhance resource utilization.

Controlling the combustion process in aero-engines is critical for optimizing performance, yet it presents significant challenges due to complex, nonlinear dynamics. Traditional Proportional-Integral-Derivative (PID) controllers are often inadequate for simultaneously managing the multiple interdependent parameters required for efficient combustion. This paper introduces a novel control method based on the Soft Actor-Critic (SAC) deep reinforcement learning algorithm to regulate pressure distribution within an engine combustion chamber. The proposed model synergistically controls key parameters—fuel equivalence ratio, fuel injection port flow proportion, and slider displacement—to achieve adaptive and stable combustion management. Experiments in a dedicated simulation environment demonstrate that the method successfully achieves high-precision pressure tracking, maintaining a root mean squared error (RMSE) of less than 1%. This approach offers a robust and efficient pathway toward intelligent aero-engine control.

“Law is code” is pivotal for advancing the intelligent judiciary. This article proposes a business process modeling notation-large language model (BPMN-LLM), which transforms BPMN models of legal contracts (LCs) into smart contracts (SCs) using LLMs in a user-friendly and cost-effective manner.

Silent speech decoding using EEG signals is a key area in Brain-Computer Interfaces (BCIs), enabling communication without vocalized speech. This study is part of the Silent Speech Decoding Challenge (SSDC) and focuses on classifying six imagined speech commands: Up, Down, Left, Right, Select, and Cancel.EEG signals from eight subjects underwent preprocessing, including bandpass (0.5-50 Hz) and notch filtering, Independent Component Analysis (ICA) for artifact removal and segmentation using a 250 ms sliding window with $50 \%$ overlap. Time-domain features were extracted and normalized before classification.Models-Naïve Bayes, KNN, SVM, XGBoost, and Light-GBM-were evaluated using 10-fold cross-validation. While baseline models showed moderate performance (SVM: 24.3% accuracy, KNN: 35.2%), XGBoost and LightGBM achieved perfect validation accuracy (100%). An independent test set from two subjects was also analyzed, though ground truth labels were unavailable for objective assessment.These results highlight the effectiveness of hand-crafted features with gradient-boosting classifiers for silent speech recognition, demonstrating the potential of EEG-based BCIs for real-world applications.

Abstract In long-range air defense multi-missile cooperative interception missions, due to the low accuracy of indication information and the lack of ground radar support, significant errors exist in estimating the true position of the target. This makes it difficult for the interception regions of multiple missiles to cooperatively cover the target error region. To address this issue, a multi-missile cooperative coverage guidance strategy based on an improved snake optimization (ISO) algorithm is proposed. First, a missile cooperative coverage model is established, with the interception regions treated as nodes in the coverage optimization problem, and the highest regional interception probability used as the optimization criterion. Next, the snake optimization (SO) algorithm is improved by enhancing its initialization, exploration, and exploitation phases, resulting in the ISO algorithm. Based on this, a multi-missile cooperative coverage guidance strategy is proposed, where the interception regions of each missile are optimally allocated within the target error region, expanding the overall interception region and improving the cooperative interception probability across the coverage area. Finally, the effectiveness of the proposed strategy is validated through numerical simulations.