Applied System Innovation

Existing unsupervised anomaly detection methods suffer from insufficient parameter precision, poor robustness to noise, and limited generalization capability. To address these issues, this paper proposes an Adaptive Diffusion Adversarial Evolutionary Network (ADAEN) for unsupervised anomaly detection in tabular data. The proposed network employs an adaptive hierarchical feature evolution generator that captures multi-scale feature representations at different abstraction levels through learnable attribute encoding and a three-layer Transformer encoder, effectively mitigating the gradient vanishing problem and the difficulty of modeling complex feature relationships that are commonly observed in conventional generators. ADAEN incorporates a multi-scale adaptive diffusion-augmented discriminator, which preserves scale-specific features across different diffusion stages via cosine-scheduled adaptive noise injection, thereby endowing the discriminator with diffusion-stage awareness. Furthermore, ADAEN introduces a multi-scale robust adversarial gradient loss function that ensures training stability through a diffusion-step-conditional Wasserstein loss combined with gradient penalty. The method has been evaluated on 14 UCI benchmark datasets and achieves state-of-the-art performance in anomaly detection compared to existing advanced algorithms, with an average improvement of 8.3% in AUC, an 11.2% increase in F1-Score, and a 15.7% reduction in false positive rate.

Sustainable virtualization is essential for enterprises seeking to reduce energy use, increase resource efficiency, and connect IT operations with global sustainability goals. This study describes a hybrid decision-support framework that uses the ISO/IEC 25010 quality characteristics and sustainability factors to evaluate virtualization technologies using FAHP, RST, and TOPSIS. To obtain robust FAHP weights in uncertain situations, expert linguistic assessments are converted into fuzzy pairwise comparisons. RST is then used to determine the most important sustainability criteria, thereby improving interpretability while minimizing model complexity. TOPSIS compares virtualization platforms to the best sustainability solution. Empirical validation involved five domain experts, eight criteria, and four virtualization platforms. Performance efficiency, reliability, and security are the main criteria, with lightweight, resource-efficient hypervisors scoring highest in sustainability factors. To implement the framework, a lightweight web-based decision-support dashboard was developed. The dashboard allows real-time FAHP computation, RST reduct extraction, TOPSIS ranking visualization, and automatic sustainability reporting. The proposed technique provides a clear, replicable, and functional tool for sustainability-focused virtualization decisions. It helps IT administrators link digital infrastructure planning with the SDG-driven green IT objectives.

Since the compressor system in underground gas storage (UGS) facilities operates under highly dynamic and complex injection conditions, traditional rule-based operation and mechanism-based modeling approaches prove inadequate for meeting the stringent requirements of high-accuracy prediction under such variable conditions. To address this, a data-driven two-phase prediction framework for compressor energy consumption is proposed. In the first phase, a convolutional neural network with efficient channel attention (CNN-ECA) is developed to accurately forecast key operating condition parameters. Based on these outputs, the second phase employs a compressor performance prediction model to estimate unit energy consumption with improved precision. In addition, a hybrid prediction strategy integrating a Transformer architecture is introduced to capture long-range temporal dependencies, thereby enhancing both single-step and multi-step forecasting performance. The proposed method is evaluated using operational data from eight compressors at the Xiangguosi underground gas storage. Experimental results show that the framework achieves high prediction accuracy, with a MAPE of 4.0779% (single-step) and 4.2449% (multi-step), outperforming advanced benchmark models.