一个混合联合学习框架,用于提高非侵入性负载监控中的隐私和稳定性
Jing Rong1, Qiuzhan Zhou1, Huinan Wu1
1College of Communication Engineering, Jilin University, Changchun 130012, China.
Sensors (Basel, Switzerland)
|January 28, 2026
概括
本研究介绍了一种混合联合学习 (FL) 框架,用于智能电网中的非侵入性负载监控 (NILM). 它通过在集中和分散的FL模式之间动态切换来增强隐私和对攻击的稳定性.
科学领域:
- 智能电网技术 智能电网技术
- 能源系统中的网络安全
- 机器学习用于能源管理
背景情况:
- 非侵入性负载监控 (NILM) 对智能电网至关重要,但传统方法会危及用户隐私.
- 联合学习 (FL) 提供保护隐私的NILM,但面临着诸如模型倒置和参数中毒等安全威胁.
- 现有的FL系统由于依赖于中央服务器而缺乏稳定性,从而危及测量完整性.
研究的目的:
- 为NILM提出混合FL框架,以提高测量隐私和系统稳定性.
- 在集中和分散的FL模式下开发防御机制来抵御复杂的攻击.
- 提高智能电网测量对抗敌对威胁的弹性.
主要方法:
- 一个混合FL框架,可以动态切换集中FL (CFL) 和分散FL (DFL) 模式.
- 在CFL模式下:对层敏感的修剪和强大的参数聚合用于防御模型反向和参数中毒.
- 在DFL模式下:基于图形注意网络 (GAT) 的动态拓调整,以应对拓中毒攻击.
主要成果:
- 建议在CFL模式下进行防御的有限错误度量增加到15.4%以下,即使有30%的恶意客户端.
- 在DFL模式下,攻击后的平均绝对误差 (MAE) 降低了17.2%,并实现了快速的性能恢复.
- 对公共数据集的评估证实了智能电网测量稳定性和隐私方面的显著改进.
结论:
- 混合FL框架有效地平衡了NILM应用程序中的隐私保护和系统稳定性.
- 开发的防御策略显著减轻了各种网络攻击对智能电网测量的影响.
- 这种方法为智能电网中的先进计量基础设施提供了更安全,更可靠的解决方案.
相关概念视频
Hybrid Zones
21.8K
Hybrid zones are narrow regions where two closely related species interact, mate, and produce hybrids. Relative to either parent species, hybrids may possess distinct phenotypic or genetic differences that impact their survival and reproductive success. The genetic variances introduced by hybridization influence species diversity and speciation processes within the hybrid zone.
21.8K
Hybridization of Atomic Orbitals I
66.7K
The mathematical expression known as the wave function, ψ, contains information about each orbital and the wavelike properties of electrons in an isolated atom. When atoms are bound together in a molecule, the wave functions combine to produce new mathematical descriptions that have different shapes. This process of combining the wave functions for atomic orbitals is called hybridization and is mathematically accomplished by the linear combination of atomic orbitals. The new orbitals that...
66.7K
Hybridization of Atomic Orbitals II
48.7K
sp3d and sp3d 2 Hybridization
48.7K
Avoidance Learning and Learned Helplessness
2.6K
Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
2.6K
Self-Evaluation: Self-Enhancement and Self-Verification
5.8K
Social psychologists have documented that feeling good about ourselves and maintaining positive self-esteem is a powerful motivator of human behavior (Tavris & Aronson, 2008). In the United States, members of the predominant culture typically think very highly of themselves and view themselves as good people who are above average on many desirable traits (Ehrlinger, Gilovich, & Ross, 2005). Often, our behavior, attitudes, and beliefs are affected when we experience a threat to our...
5.8K
Impact Loading
691
Impact loading occurs when a moving object collides with a stationary structure, such as a rod with a uniform cross-sectional area fixed at one end. Under these conditions, the rod absorbs the kinetic energy from the striking object, leading to deformation and subsequent stress development. As the rod returns to its original position and reaches maximum stress, the absorbed energy, initially manifested as kinetic energy, transforms entirely into strain energy.
In cases of elastic deformation,...
In cases of elastic deformation,...
691


