Anomaly Detection and Business Process Orchestration for Low-Code Platform in Power System Based on Deep-Cross Model With Data Balancing

This paper presents an innovative approach to anomaly detection in electric vehicle (EV) charging platforms, centered around four key innovations that significantly advance the field of charging infrastructure security. First, we introduce a statistically reliable data balancing methodology that addresses the critical challenge of anomaly sample scarcity, achieving a 47% improvement in detection accuracy compared to conventional sampling techniques. Second, we propose xDeepCIN, a novel deep learning architecture that uniquely combines Compressed Interaction Networks with low-order crossing structures, demonstrating a 28% reduction in feature sparsity compared to existing deep cross models. Third, we implement a hierarchical feature interaction mechanism that enables both explicit and implicit learning of high-order patterns, resulting in a 35% improvement in anomaly pattern recognition over traditional deep learning approaches. Fourth, we develop an adaptive processing framework for asynchronous heterogeneous data streams, reducing detection latency by 62% compared to current synchronous methods. Unlike prior studies that primarily focus on single-aspect improvements in either data processing or model architecture, our comprehensive approach simultaneously addresses data imbalance, feature sparsity, and processing efficiency. Experimental results across multiple real-world datasets demonstrate the framework’s superior performance, achieving an AUC of 0.93 and F1-score of 0.97, representing substantial improvements over existing methods. This advancement has significant implications for the growing EV market, particularly in China, where our framework could prevent an estimated 85% of serious charging infrastructure failures.