用真实电力系统仿真测试机器学习模型，发现离线高准确率不等于现场可用。
The Wisdom of the Crowd: High-Fidelity Classification of Cyber-Attacks and Faults in Power Systems Using Ensemble and Machine Learning
- 在4.8 kHz高频仿真下训练12种模型，结合滤波与置信度阈值提升实时稳定性。
- 仅多层感知机（MLP）在流式推理中保持98%-99%覆盖，集成模型精度虽高但弃权率达10%-49%。
- 强调必须用真实场景测试才能评估模型在含大量逆变器的电网中的实际可靠性。
本文提出一种基于机器学习的高保真分类框架，用于识别电力系统中的网络攻击与物理故障。采用4.8 kHz采样频率的电磁暂态仿真与数字变电站模拟，训练了包括集成算法和多层感知机（MLP）在内的12种模型。所有模型均基于时域测量数据进行标注，并在设计为支持子周期响应的实时流式环境中评估。该架构引入周期长度平滑滤波器和置信度阈值以稳定决策结果。结果显示，尽管多个模型在离线测试中达到接近完美的准确率（最高99.9%），但仅有MLP在流式推理中维持98%-99%的持续覆盖能力；而集成模型虽保持100%异常检出精度，却频繁拒绝判断（弃权率10%-49%）。这些发现表明，仅依赖离线准确率无法反映模型在真实环境中的部署可行性，凸显了构建现实测试与推理流程的必要性，以确保在含大量逆变器资源（IBR）的电网中实现可靠分类。
原文摘要 · Abstract (English)
This paper presents a high-fidelity evaluation framework for machine learning (ML)-based classification of cyber-attacks and physical faults using electromagnetic transient simulations with digital substation emulation at 4.8 kHz. Twelve ML models, including ensemble algorithms and a multi-layer perceptron (MLP), were trained on labeled time-domain measurements and evaluated in a real-time streaming environment designed for sub-cycle responsiveness. The architecture incorporates a cycle-length smoothing filter and confidence threshold to stabilize decisions. Results show that while several models achieved near-perfect offline accuracies (up to 99.9%), only the MLP sustained robust coverage (98-99%) under streaming, whereas ensembles preserved perfect anomaly precision but abstained frequently (10-49% coverage). These findings demonstrate that offline accuracy alone is an unreliable indicator of field readiness and underscore the need for realistic testing and inference pipelines to ensure dependable classification in inverter-based resources (IBR)-rich networks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。