Load forecasting using deep neural networks

Hosein, Stefan; Hosein, Patrick

doi:10.1109/isgt.2017.8085971

Cited by 86 publications

(54 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the demand side, charging the EV battery is considered as a controllable load. All the other loads in a typical household are lumped and considered as uncontrollable and predictable (see [26]). It is technically beneficial to allow charging at the maximum rate and instead use scheduling to spread the load over time.…”

Section: A Power Production and Consumption Modelsmentioning

confidence: 99%

Electric Vehicle Implementation Guidelines

Meetoo¹,

Bahadoorsingh²,

Sharma³

2019

Proceedings of the 17th LACCEI International Multi-Conference for Engineering, Education, and Technology: “Industry, Innovation

View full text Add to dashboard Cite

SIDS (Small Island Developing States) are unique in their drive to reducing GHGs. Since these countries need to be self-sufficient in energy, there is a dilemma on the best way to reduce GHG while maintaining energy security. One way would be to drive the implementation of EVs for the transportation sector. However this can wreak havoc on the SIDS electrical network if not done properly. This paper reviews the possible effects of introducing EV charging on the grid. The authors have given Policy recommendations as to how EV penetration can be managed whilst maintaining the reliability and quality of the electricity grid. The authors also suggest a unique controller that can be used by the utility to limit charging time and window.

show abstract

Section: A Power Production and Consumption Modelsmentioning

confidence: 99%

Electric Vehicle Implementation Guidelines

Meetoo¹,

Bahadoorsingh²,

Sharma³

2019

Proceedings of the 17th LACCEI International Multi-Conference for Engineering, Education, and Technology: “Industry, Innovation

View full text Add to dashboard Cite

show abstract

“…In [23], the authors evaluated the effects of deep stacked autoencoders and RNN-LSTM forecasting models, and the test results suggested the superiority of the DL based method compared to traditional models. In [18], the authors built models using FF-DNN and deep RNN and extracted up to 13 features from the raw load and meteorological data to drive the model.…”

Section: Introductionmentioning

confidence: 99%

Spatiotemporal Feature Learning Based Hour-Ahead Load Forecasting for Energy Internet

Zhang

Wang

2020

Electronics

View full text Add to dashboard Cite

In this paper, we analyze the characteristics of the load forecasting task in the Energy Internet context and the deficiencies of existing methods and then propose a data driven approach for one-hour-ahead load forecasting based on the deep learning paradigm. The proposed scheme involves three aspects. First, we formulate a historical load matrix (HLM) with spatiotemporal correlation combined with the EI scenario and then create a three-dimensional historical load tensor (HLT) that contains the HLMs for multiple consecutive time points before the forecasted hour. Second, we preprocess the HLT leveraging a novel low rank decomposition algorithm and different load gradients, aiming to provide a forecasting model with richer input data. Third, we develop a deep forecasting framework (called the 3D CNN-GRU) featuring a feature learning module followed by a regression module, in which the 3D convolutional neural network (3D CNN) is used to extract the desired feature sequences with time attributes, while the gated recurrent unit (GRU) is responsible for mapping the sequences to the forecast values. By feeding the corresponding load label into the 3D CNN-GRU, our proposed scheme can carry out forecasting tasks for any zone covered by the HLM. The results of self-evaluation and a comparison with several state-of-the-art methods demonstrate the superiority of the proposed scheme.

show abstract

“…It consists of a multilayer constrained Boltzmann machine stack, which can cope with the complex and nonlinear problems. For the load forecasting problem based on DNN, the literature proposed a method based on DNN with Pretraining Using Stacked Autoencoders (DNN‐SA), which achieves good results in the day‐to‐day load forecasting. Literature uses the deep residual network to realize monthly electricity consumption forecasting, and applies DNN to medium and LTLF.…”

Section: Introductionmentioning

confidence: 99%

Very‐short‐term load forecasting based on empirical mode decomposition and deep neural network

Cheng

Bao

Tang

et al. 2019

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

Very-short-term load forecasting (VSTLF) predicts the load from minutes to 1-hour timescale. Effective forecasting is important for in-day scheduling of the power systems. In this paper, a VSTLF method based on empirical mode decomposition and deep neural network is proposed. The extreme point span is used to determine a proper empirical modal number, so as to successfully decompose the load data into different timescales, based on which the deep-neural-network-based forecasting model is established. The accuracy of the proposed method is verified by the testing results in this paper.

show abstract

Load forecasting using deep neural networks

Cited by 86 publications

References 6 publications

Electric Vehicle Implementation Guidelines

Electric Vehicle Implementation Guidelines

Spatiotemporal Feature Learning Based Hour-Ahead Load Forecasting for Energy Internet

Very‐short‐term load forecasting based on empirical mode decomposition and deep neural network

Contact Info

Product

Resources

About