SEADS: A modifiable platform for real time monitoring of residential appliance energy consumption

Adabi, Ali; Manovi, Pavlo; Mantey, Patrick E.

doi:10.1109/igcc.2015.7393703

Cited by 4 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Third, NILM models need considerable training data to extract representative statistical characteristics to gain high performance. However, imbalanced data often occurs at user premises due to the operating frequency of the appliances and thus leads to poor model fitting [1], especially in the cold-start phase. Although existing approaches can tackle this issue by collecting data from stakeholders for centralized model training, the potential risks of privacy leakage [42,50] and expensive data transmission preclude them from practical use.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Fed-GBM

Chang

Zomaya

2022

Proceedings of the Thirteenth ACM International Conference on Future Energy Systems

View full text Add to dashboard Cite

Non-intrusive load monitoring (NILM) is a computational technique to allow appliance-level energy disaggregation for sustainable energy management. Most NILM models require considerable training data to capture sufficient appliance signatures for robust model fitting. However, local on-site training cannot satisfy that requirement due to limited data availability. It is thus conceivable to perform data collaboration among different stakeholders. Unfortunately, current collaborative learning approaches rely on deep learning, encryption, and differential privacy techniques associated with either expensive computation or inefficient communication. In this paper, we propose a cost-effective collaborative learning framework, Fed-GBM (Federated Gradient Boosting Machines), consisting of two-stage voting and node-level parallelism, to address the problems in comodelling for NILM. Through extensive experiments on real-world residential datasets, Fed-GBM shows remarkable performance on convergence, accuracy, computation and communication efficiency. The impact of hyper-parameters in Fed-GBM is also extensively studied to guide better practical use. CCS CONCEPTS• Computing methodologies → Machine learning; • Hardware → Power and energy.

show abstract

mentioning

confidence: 99%

“…(4) We implement a prototype of Fed-GBM 1 and evaluate its performance with the residential datasets. Extensive experiments are conducted to determine the impact of hyper-parameters used in two-stage voting and node-level parallelism.…”

mentioning

confidence: 99%

Fed-GBM

Chang

Zomaya

2022

Proceedings of the Thirteenth ACM International Conference on Future Energy Systems

View full text Add to dashboard Cite

show abstract

“…In other instances, continued graduate research has produced several theses, journal articles, and conference proceedings. 6,15,16,17,18,19,20,21 Behind the Scenes: Logistics…”

Section:  "Carbon Costs At the University Of Uc Davis": A Comparisonmentioning

confidence: 99%

Setting the Foundations for International and Cross-disciplinary Innovation: The U.S.-Denmark Summer School "Renewable Energy: In Practice"

Favaloro

Jenkins

Lehmann

et al.

2017 ASEE Annual Conference &Amp; Exposition Proceedings

View full text Add to dashboard Cite

Tela Favaloro received a B.S. degree in Physics and a Ph.D. in Electrical Engineering from the University of California, Santa Cruz. She is currently working to further the development and dissemination of alternative energy technology; as project manager of a green building design initiative and researcher with the Center for Sustainable Engineering and Power Systems. Her background is in the development of characterization techniques and laboratory apparatus for advancement of novel electronic devices, in addition to curriculum development for inquiry-based learning and facilitation of interdisciplinary, student-led project design. She emphasizes engineering sustainable solutions from a holistic perspective, incorporating analysis of the full technological life cycle and socioeconomic impact.

show abstract

On enabling collaborative non-intrusive load monitoring for sustainable smart cities

Shi

Chang

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Improving energy efficiency is a crucial aspect of building a sustainable smart city and, more broadly, relevant for improving environmental, economic, and social well-being. Non-intrusive load monitoring (NILM) is a computing technique that estimates energy consumption in real-time and helps raise energy awareness among users to facilitate energy management. Most NILM solutions are still a single machine approach and do not fit well in smart cities. This work proposes a model-agnostic hybrid federated learning framework to collaboratively train NILM models for city-wide energy-saving applications. The framework supports both centralised and decentralised training modes to provide a cluster-based, customisable and optimal learning solution for users. The proposed framework is evaluated on a real-world energy disaggregation dataset. The results show that all NILM models trained in our proposed framework outperform the locally trained ones in accuracy. The results also suggest that the NILM models trained in our framework are resistant to privacy leakage.

show abstract

SEADS: A modifiable platform for real time monitoring of residential appliance energy consumption

Cited by 4 publications

References 8 publications

Fed-GBM

Fed-GBM

Setting the Foundations for International and Cross-disciplinary Innovation: The U.S.-Denmark Summer School "Renewable Energy: In Practice"

On enabling collaborative non-intrusive load monitoring for sustainable smart cities

Contact Info

Product

Resources

About