SAED: self-attentive energy disaggregation
نویسندگان
چکیده
The field of energy disaggregation deals with the approximation appliance electric consumption using only aggregate measurement a mains meter. Recent research developments have used deep neural networks and outperformed previous methods based on Hidden Markov Models. On other hand, learning models are computationally heavy require huge amounts data. main objective current paper is to incorporate attention mechanism into in order reduce their computational complexity. For two different versions utilized, named Additive Dot Attention. experiments show that they perform par, while slightly faster. self-attentive compared against state-of-the-art models. experimental results proposed architecture achieves faster or equal training inference time minor performance drop depending device dataset.
منابع مشابه
Activation Energy of Aggregation-Disaggregation Self-Oscillation of Polymer Chain
In this paper, we investigated the activation energies of the aggregation−disaggregation self-oscillation induced by the Belousov-Zhabotinsky (BZ) reaction by utilizing the nonthermoresponsive polymer chain in a wide temperature range. This is because the conventional type self-oscillating polymer chain, with thermoresponsive poly(Nisopropylacrylamide) (poly(NIPAAm) main-chain covalently bonded...
متن کاملOccupancy-aided energy disaggregation
Energy disaggregation helps to identify major energy guzzlers in the house without introducing extra metering cost. It motivates users to take proper actions for energy saving and facilitates demand response programs. To reduce the computational complexity of pure energy disaggregation, we propose an occupancyaided energy disaggregation (OAED) approach in this paper. Specifically, we make use o...
متن کاملContext-Based Energy Disaggregation in Smart Homes
In this paper, we address the problem of energy conservation and optimization in residential environments by providing users with useful information to solicit a change in consumption behavior. Taking care to highly limit the costs of installation and management, our work proposes a Non-Intrusive Load Monitoring (NILM) approach, which consists of disaggregating the whole-house power consumption...
متن کاملDisambiguating Energy Disaggregation: A Collective Probabilistic Approach
Reducing household energy usage is a priority for improving the resiliency and stability of the power grid and decreasing the negative impact of energy consumption on the environment and public health. Relevant and timely feedback about the power consumption of specific appliances can help household residents reduce their energy demand. Given only a total energy reading, such as that collected ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Machine Learning
سال: 2021
ISSN: ['0885-6125', '1573-0565']
DOI: https://doi.org/10.1007/s10994-021-06106-3