Data driven prediction models of energy use of appliances in a low-energy house

Candanedo, Luis M.; Feldheim, Véronique; Deramaix, Dominique

doi:10.1016/j.enbuild.2017.01.083

Cited by 432 publications

(223 citation statements)

References 43 publications

Supporting

Mentioning

196

Contrasting

Unclassified

Order By: Relevance

“…Linear regression is performed with SGD on the energy dataset [43], which contains 19, 735 records of measurements from multiple sensors and the energy consumptions of appliances and lights. The model learns to predict the appliance energy consumption from sensor measurements.…”

Section: Cnn (Sgd) + Cifar-10mentioning

confidence: 99%

Adaptive Federated Learning in Resource Constrained Edge Computing Systems

Wang

Tuor

Salonidis

et al. 2019

IEEE J. Select. Areas Commun.

1,752

896

View full text Add to dashboard Cite

Emerging technologies and applications including Internet of Things (IoT), social networking, and crowd-sourcing generate large amounts of data at the network edge. Machine learning models are often built from the collected data, to enable the detection, classification, and prediction of future events. Due to bandwidth, storage, and privacy concerns, it is often impractical to send all the data to a centralized location. In this paper, we consider the problem of learning model parameters from data distributed across multiple edge nodes, without sending raw data to a centralized place. Our focus is on a generic class of machine learning models that are trained using gradientdescent based approaches. We analyze the convergence bound of distributed gradient descent from a theoretical point of view, based on which we propose a control algorithm that determines the best trade-off between local update and global parameter aggregation to minimize the loss function under a given resource budget. The performance of the proposed algorithm is evaluated via extensive experiments with real datasets, both on a networked prototype system and in a larger-scale simulated environment. The experimentation results show that our proposed approach performs near to the optimum with various machine learning models and different data distributions.

show abstract

Section: Cnn (Sgd) + Cifar-10mentioning

confidence: 99%

Adaptive Federated Learning in Resource Constrained Edge Computing Systems

Wang

Tuor

Salonidis

et al. 2019

IEEE J. Select. Areas Commun.

1,752

896

View full text Add to dashboard Cite

show abstract

“…The goal is to predict the UPDRS (Unified Parkinson's Disease Rating Scale) score [14], that indicates the disease severity. (ii) Appliance Energy Usage Dataset: [15] -This dataset contains measurements pertinent to house temperature and humidity conditions and the goal is to estimate the amount of energy usage by the appliances (in Wh units). There are 29 input attributes, out of which two of them are random variables, corresponding to 19, 735 samples.…”

Section: Methodsmentioning

confidence: 99%

Understanding Deep Neural Networks through Input Uncertainties

Thiagarajan

Kim

Bremer

2019

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Techniques for understanding the functioning of complex machine learning models are becoming increasingly popular, not only to improve the validation process, but also to extract new insights about the data via exploratory analysis. Though a large class of such tools currently exists, most assume that predictions are point estimates and use a sensitivity analysis of these estimates to interpret the model. Using lightweight probabilistic networks we show how including prediction uncertainties in the sensitivity analysis leads to: (i) more robust and generalizable models; and (ii) a new approach for model interpretation through uncertainty decomposition. In particular, we introduce a new regularization that takes both the mean and variance of a prediction into account and demonstrate that the resulting networks provide improved generalization to unseen data. Furthermore, we propose a new technique to explain prediction uncertainties through uncertainties in the input domain, thus providing new ways to validate and interpret deep learning models.

show abstract

“…However, all predictions are based on modelfree empirical statistics. In [17], multiple linear regression, support vector machines with a radial kernel, random forests, and gradient boosting machines are evaluated for appliance load prediction.…”

Section: B Related Workmentioning

confidence: 99%

Data-Driven Load Modeling and Forecasting of Residential Appliances

Buechler

Rajagopal

2020

IEEE Trans. Smart Grid

View full text Add to dashboard Cite

The expansion of residential demand response programs and increased deployment of controllable loads will require accurate appliance-level load modeling and forecasting. This paper proposes a conditional hidden semi-Markov model to describe the probabilistic nature of residential appliance demand, and an algorithm for short-term load forecasting. Model parameters are estimated directly from power consumption data using scalable statistical learning methods. Case studies performed using submetered 1-minute power consumption data from several types of appliances demonstrate the effectiveness of the model for load forecasting and anomaly detection.Index Terms-Hidden semi-Markov model, residential appliances, load model, short-term load forecast.

show abstract

Data driven prediction models of energy use of appliances in a low-energy house

Cited by 432 publications

References 43 publications

Adaptive Federated Learning in Resource Constrained Edge Computing Systems

Adaptive Federated Learning in Resource Constrained Edge Computing Systems

Understanding Deep Neural Networks through Input Uncertainties

Data-Driven Load Modeling and Forecasting of Residential Appliances

Contact Info

Product

Resources

About