关键电力基础设施处理数据异质性的联合学习,用于变电站设备的预测性维护
1Department of Electrical Engineering, Black and Veatch, Overland Park, KS, United States.
Frontiers in artificial intelligence
|February 12, 2026
概括
联合学习通过实现协作模型培训而无需共享敏感数据来增强关键电力基础设施的预测性维护. 联合批量规范化 (FedBN) 有效地解决了公用事业提供商之间的数据异质性.
科学领域:
- 电气工程 电气工程
- 计算机科学 计算机科学
- 人工智能的人工智能
背景情况:
- 高压变电站是关键基础设施,需要对电网可靠性进行强有力的预测性维护.
- 联合学习 (FL) 提供了一种保护隐私的方法,用于多个公用事业提供商之间的协作模式改进.
- 不同公用事业站点之间的数据异质性对有效的FL模型开发构成重大挑战.
研究的目的:
- 开发和评估保护隐私的联合学习框架,以加强变电站设备的预测性维护.
- 解决和减轻数据异质性对电力系统联合学习的影响.
- 评估不同FL策略的表现,以应对分布变化.
主要方法:
- 为关键电力系统应用量身定制的保护隐私的联合学习框架的开发.
- 评估了四种FL策略:联合平均 (FedAvg,FedAvgM),联合近似 (FedProx) 和联合批量规范化 (FedBN).
- 使用F-score和一个新的联邦信息标准 (FIC) 来衡量模型准确性和异质性缓解的性能评估.
主要成果:
- 联合批量规范化 (FedBN) 在缓解跨实用数据异质性方面表现出卓越的表现,达到0.88.8的最高F-score.
- 根据FL算法,客户数和数据分区策略,F-score在0.60和0.88之间变化.
- 联邦储备银行 (FedBN) 的FIC得分为4.35,相当低,这表明它能够有效地处理异质性.
结论:
- 定制的联合学习方法,特别是FedBN,显著提高了变电站设备维护的预测准确性.
- 在关键电力系统中,FL可实现可扩展和保护隐私的先进维护策略的部署.
- 拟议的联邦信息标准 (FIC) 为评估在异质环境中的FL性能提供了一个新的指标.
更多相关视频
07:41Modeling Fast-scan Cyclic Voltammetry Data from Electrically Stimulated Dopamine Neurotransmission Data Using QNsim1.0
Published on: June 5, 2017
10.4K
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
8.9K
相关概念视频
Leveling Equipment
443
As leveling involves measuring vertical distances relative to a horizontal line of sight, it requires a graduated rod, called a level rod, for vertical measurements and an instrument called a level for a horizontal sight line. A level includes a high-powered telescope with a mechanism for leveling to ensure the line of sight is horizontal when the bubble in the spirit level is centered. Leveling rods, made of wood, metal, or fiberglass, are graduated in feet or meters and commonly used in two-...
443
Sample Handling
2.7K
Transportation of samples from the collection point to the laboratory, as well as storage and preservation techniques, are crucial for maintaining sample integrity and ensuring accurate and reliable test results.
Samples should be transported carefully from collection points to the laboratory. They should be properly sealed and clearly labeled to prevent cross-contamination. To preserve the sample integrity, optimal temperature conditions during transport are essential. This could involve using...
Samples should be transported carefully from collection points to the laboratory. They should be properly sealed and clearly labeled to prevent cross-contamination. To preserve the sample integrity, optimal temperature conditions during transport are essential. This could involve using...
2.7K
Predicting Molecular Geometry
46.1K
VSEPR Theory for Determination of Electron Pair Geometries
46.1K
Critical Region, Critical Values and Significance Level
13.4K
The critical region, critical value, and significance level are interdependent concepts crucial in hypothesis testing.
In hypothesis testing, a sample statistic is converted to a test statistic using z, t, or chi-square distribution. A critical region is an area under the curve in probability distributions demarcated by the critical value. When the test statistic falls in this region, it suggests that the null hypothesis must be rejected. As this region contains all those values of the...
In hypothesis testing, a sample statistic is converted to a test statistic using z, t, or chi-square distribution. A critical region is an area under the curve in probability distributions demarcated by the critical value. When the test statistic falls in this region, it suggests that the null hypothesis must be rejected. As this region contains all those values of the...
13.4K
Personal Protective Equipment
2.4K
Personal protective equipment (PPE) is unique clothing or equipment worn by an employee to minimize or prevent exposure to infectious agents. PPE creates a barrier between the employee and the infectious materials. PPE must be readily available in the patient care area. PPE includes gloves, gowns and aprons, masks and respirators, goggles, face shields, shoes, and headcovers:
2.4K
Critical Values
10.4K
A critical value is a definite value obtained from a particular probability distribution at a predecided confidence level (or a predecided significance level) for a given population parameter. The critical value provides demarcation that separates the sample statistics that are likely to occur from the ones that are unlikely to occur based on the given probability distribution and the population parameter to be estimated. The critical value for normal distribution is obtained from the z...
10.4K
