Federated Clustering for Electricity Consumption Pattern Extraction

Wang, Yi; Jia, Mengshuo; Gao, Ning; Krannichfeldt, Leandro Von; Sun, Mingyang; Hug, Gabriela

doi:10.1109/tsg.2022.3146489

Cited by 35 publications

(11 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, smart meter data analytics has become increasingly popular in the energy sector due to widespread smart meter installations and scalable data collection [4]. Smart meter data can be used for a variety of purposes, among others including load prediction [16][17][18], load profile clustering [4,19] and household characteristics inferences [20,21]. Accurate forecasts not only help utilities plan resources and take control measures to balance energy supply and demand, but also help customers understand their energy consumption and future needs to better manage their usage costs [22].…”

Section: Related Workmentioning

confidence: 99%

Understanding multi-scale spatiotemporal energy consumption data: A visual analysis approach

Junqi

Niu

et al. 2023

Energy

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Understanding multi-scale spatiotemporal energy consumption data: A visual analysis approach

Junqi

Niu

et al. 2023

Energy

View full text Add to dashboard Cite

“…The key component of clustering-based methods is the algorithm to privacy-respectively distinguish the data distribution of clients and then conduct clustering on these clients. CFL works [191,57,155,211,226] clusters clients using K-means clustering based on client parameters. CFL [178,179] separates clients into two partitions, which Figure 6: The illustration of threats in RFL.…”

Section: Assumption 41 (Clustered Federated Learning [178]mentioning

confidence: 99%

A survey on security and privacy threats to federated learning

Zhang

Zeng

et al. 2021

2021 International Conference on Networking and Network Applications (NaNA)

View full text Add to dashboard Cite

Trustworthy artificial intelligence (AI) technology has revolutionized daily life and greatly benefited human society. Among various AI technologies, Federated Learning (FL) stands out as a promising solution for diverse real-world scenarios, ranging from risk evaluation systems in finance to cutting-edge technologies like drug discovery in life sciences. However, challenges around data isolation and privacy threaten the trustworthiness of FL systems. Adversarial attacks against data privacy, learning algorithm stability, and system confidentiality are particularly concerning in the context of distributed training in federated learning. Therefore, it is crucial to develop FL in a trustworthy manner, with a focus on security, robustness, and privacy. In this survey, we propose a comprehensive roadmap for developing trustworthy FL systems and summarize existing efforts from three key aspects: security, robustness, and privacy. We outline the threats that pose vulnerabilities to trustworthy federated learning across different stages of development, including data processing, model training, and deployment. To guide the selection of the most appropriate defense methods, we discuss specific technical solutions for realizing each aspect of Trustworthy FL (TFL). Our approach differs from previous work that primarily discusses TFL from a legal perspective or presents FL from a high-level, non-technical viewpoint.

show abstract

“…Power quality assessment includes reliability assessment, measurement anomaly assessment, full event assessment, overload rate assessment and clock battery low voltage assessment. Finally, through the analysis of each score, the comprehensive score of the watt-hour meter is obtained, and the size of the score can reflect the working condition of the watt-hour meter [3]. According to several important reasons for the failure of electric meters, these five types are selected.…”

Section: Introductionmentioning

confidence: 99%

Application of Clustering Algorithm in Fault State Classification of Low Voltage Watt-Hour Meter

Hao Wang, Chong Li, Yi Wang, Xiaoteng Sun

2024

jes

View full text Add to dashboard Cite

In this paper, a low-voltage digital watt-hour meter monitoring system for smart grid is designed. The system includes information acquisition system, low-voltage digital meter and power service system. The low-voltage digital meter uses RFID chip inside, which can accurately locate the target through high-speed transmission and remote identification. It can effectively overcome the security risks caused by information collision and the problem of slow recognition speed. According to different fault categories, community clustering method is used to classify them. In the actual determination of the fault causes of 32 electric energy meters with this method correctly analyzed the fault causes of 26 electric energy meters. The accuracy rate reached 81.25%.

show abstract

Federated Clustering for Electricity Consumption Pattern Extraction

Cited by 35 publications

References 45 publications

Understanding multi-scale spatiotemporal energy consumption data: A visual analysis approach

Understanding multi-scale spatiotemporal energy consumption data: A visual analysis approach

A survey on security and privacy threats to federated learning

Application of Clustering Algorithm in Fault State Classification of Low Voltage Watt-Hour Meter

Contact Info

Product

Resources

About