Machine Learning Models for Electricity Consumption Forecasting: A Review

González‐Briones, Alfonso; Hernández, Guillermo; Corchado, Juan M.; Omatu, Sigeru; Mohamad, Mohd Saberi

doi:10.1109/cais.2019.8769508

Cited by 49 publications

(22 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As expected, the advantages of ARIMA emerge in the long period of 1W and 1D, and nonlinear mapping methods such as support vector regressor (SVR) and neural networks alleviate errors in a short period of 1H and 1M. The proposed method achieves the best performance in all temporal resolutions against the latest machine learning methods [7,8] and deep learning method [10]. We confirm the effect of changes in time lag parameter .…”

Section: Power Consumption Prediction Performancesupporting

confidence: 75%

“…In order to build time-invariant features and perform the non-linear mapping for predicting the power consumption, Tso and Yau presented a neural network and compared the performance with existing prediction methods based on the rules and symbols [18]. Among the power demand forecasting methods based on machine learning such as the autoregressive integrated moving average (ARIMA) [7] and decision tree [8], the neural network achieved the best performance, and its non-linear mapping capability attracted much attention [19]. In particular, combining the approach of machine learning algorithms like the ensemble of recurrent neural network and support vector regressor [20] improved the accuracy and the stability of power demand prediction.…”

Section: Related Workmentioning

confidence: 99%

“…The main findings of this research can be summarized as follows: In the domain of energy, machine learning aims at exploiting a database generated with the historical data of all the clients and predicting the future energy demand. Various regression techniques, including autoregressive integrated moving average [7] and support vector regressor [8], which are representative methods for the energy prediction, successfully model the long-term behavior of end-users and improve the prediction accuracy. Yet, in the prediction task under high-temporal resolution conditions [9] aimed at modeling the short-term behaviors that expose the behavioral patterns, a more complex and practical time series modeling method is required.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Time Series Forecasting with Multi-Headed Attention-Based Deep Learning for Residential Energy Consumption

Cho

2020

Energies

View full text Add to dashboard Cite

Predicting residential energy consumption is tantamount to forecasting a multivariate time series. A specific window for several sensor signals can induce various features extracted to forecast the energy consumption by using a prediction model. However, it is still a challenging task because of irregular patterns inside including hidden correlations between power attributes. In order to extract the complicated irregular energy patterns and selectively learn the spatiotemporal features to reduce the translational variance between energy attributes, we propose a deep learning model based on the multi-headed attention with the convolutional recurrent neural network. It exploits the attention scores calculated with softmax and dot product operation in the network to model the transient and impulsive nature of energy demand. Experiments with the dataset of University of California, Irvine (UCI) household electric power consumption consisting of a total 2,075,259 time-series show that the proposed model reduces the prediction error by 31.01% compared to the state-of-the-art deep learning model. Especially, the multi-headed attention improves the prediction performance even more by up to 27.91% than the single-attention.

show abstract

Section: Power Consumption Prediction Performancesupporting

confidence: 75%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Time Series Forecasting with Multi-Headed Attention-Based Deep Learning for Residential Energy Consumption

Cho

2020

Energies

View full text Add to dashboard Cite

show abstract

“…The use of artificial intelligence (AI) methods, including machine learning, is worth considering [207]. The use of machine learning models can be considered for estimating O-D matrices (especially using data from satellite navigation, mobile phones, or the Internet of Things).…”

Section: Methods Of Model Developmentmentioning

confidence: 99%

Bicycle Traffic Model for Sustainable Urban Mobility Planning

2021

View full text Add to dashboard Cite

Modelling tools and transport models are required to assess the impact of measures for the effective planning of cycling routes in cities. This paper presents the methodology for developing a four-stage macroscopic model of bicycle traffic for the city of Gdynia, and its use in planning new bicycle routes, considering a modal shift. The model presented in this paper allows for the evaluation of the influence of the characteristics of the cycling infrastructure, along with the development of the cycling network based on the choice of cycling as an alternative to other modes of transport, by taking into account the modal shift. The model takes into account the influence of the longitudinal gradient, link, and surface type of cycling routes on the distribution and demand for bicycle traffic. The results of our research allow us to assess the impact of planned cycling routes on the reduction in the volume of car traffic, which is crucial for reducing energy consumption and negative environmental impacts. Experiences from the application of the model in Gdynia suggest that the model provides a strong basis to support mobility planning and monitoring processes in cities worldwide. Cities should take into account the methods proposed in this paper when planning the development of their transport systems.

show abstract

“…In this kind of case, where we expect to get a category on the way out, we are talking about classification problems. If, on the other hand, we expect to get a continuous numerical value at the output, for example, if we want to predict the value of an action over time, we are talking about a regression problem [13].…”

Section: Supervised Learningmentioning

confidence: 99%

A Review of k-NN Algorithm Based on Classical and Quantum Machine Learning

Mezquita

Alonso

Casado‐Vara

et al. 2020

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Artificial intelligence algorithms, developed for traditional computing, based on Von Neumann's architecture, are slow and expensive in terms of computational resources. Quantum mechanics has opened up a new world of possibilities within this field, since, thanks to the basic properties of a quantum computer, a great degree of parallelism can be achieved in the execution of the quantum version of machine learning algorithms. In this paper, a study has been carried out on these properties and on the design of their quantum computing versions. More specifically, the study has been focused on the quantum version of the k-NN algorithm that allows to understand the fundamentals when transcribing classical machine learning algorithms into its quantum versions.

show abstract

Machine Learning Models for Electricity Consumption Forecasting: A Review

Cited by 49 publications

References 32 publications

Time Series Forecasting with Multi-Headed Attention-Based Deep Learning for Residential Energy Consumption

Time Series Forecasting with Multi-Headed Attention-Based Deep Learning for Residential Energy Consumption

Bicycle Traffic Model for Sustainable Urban Mobility Planning

A Review of k-NN Algorithm Based on Classical and Quantum Machine Learning

Contact Info

Product

Resources

About