Deep Learning with Stacked Denoising Auto-Encoder for Short-Term Electric Load Forecasting

Liu, Peng; Zheng, Peijun; Chen, Ziyu

doi:10.3390/en12122445

Cited by 52 publications

(32 citation statements)

References 34 publications

(38 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This denoising stage will be based on data-driven methods such as ML techniques or ANNs. The ones considered here are the Principal Component Analysis (PCA) [ 23 ] and the Denoising Autoencoders (DAE) [ 24 ]. Moreover, the proposed denoising stage can be understood as as a complement of the ANN-based IMC structure controlling the BSM1

component.…”

Section: Methodsmentioning

confidence: 99%

“…The latter corresponds to a new denoising preprocessing stage which will be proposed to make the controller work with ideal and noise measurements, that is, to be able to work under ideal and real conditions. Two different Machine Learning (ML) approaches, the Principal Component Analysis (PCA) [ 23 ] and a Denoising Autoencoder (DAE) [ 24 ], will be consider as the denoising stage to clean the incoming measurements. In both cases, they correspond to data-driven systems which simplify the denoising stage implementation with respect to (w.r.t.)…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Denoising Autoencoders and LSTM-Based Artificial Neural Networks Data Processing for Its Application to Internal Model Control in Industrial Environments—The Wastewater Treatment Plant Control Case

Pisa

Morell

Vicario

et al. 2020

Sensors

View full text Add to dashboard Cite

The evolution of industry towards the Industry 4.0 paradigm has become a reality where different data-driven methods are adopted to support industrial processes. One of them corresponds to Artificial Neural Networks (ANNs), which are able to model highly complex and non-linear processes. This motivates their adoption as part of new data-driven based control strategies. The ANN-based Internal Model Controller (ANN-based IMC) is an example which takes advantage of the ANNs characteristics by modelling the direct and inverse relationships of the process under control with them. This approach has been implemented in Wastewater Treatment Plants (WWTP), where results show a significant improvement on control performance metrics with respect to (w.r.t.) the WWTP default control strategy. However, this structure is very sensible to non-desired effects in the measurements—when a real scenario showing noise-corrupted data is considered, the control performance drops. To solve this, a new ANN-based IMC approach is designed with a two-fold objective, improve the control performance and denoise the noise-corrupted measurements to reduce the performance degradation. Results show that the proposed structure improves the control metrics, (the Integrated Absolute Error (IAE) and the Integrated Squared Error (ISE)), around a 21.25% and a 54.64%, respectively.

show abstract

component.…”

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Denoising Autoencoders and LSTM-Based Artificial Neural Networks Data Processing for Its Application to Internal Model Control in Industrial Environments—The Wastewater Treatment Plant Control Case

Pisa

Morell

Vicario

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Each node receives values from the nodes in the previous layer to determine the output and provide values for the nodes in the next layer. As this process repeats, the nodes in the output layer provide the required values [56]. The number of hidden layers determines whether the network is deep or shallow.…”

Section: The Second Stage: Combining Stlf Models Using Dnnmentioning

confidence: 99%

A Two-Stage Industrial Load Forecasting Scheme for Day-Ahead Combined Cooling, Heating and Power Scheduling

et al. 2020

View full text Add to dashboard Cite

Smart grid systems, which have gained much attention due to its ability to reduce operation and management costs of power systems, consist of diverse components including energy storage, renewable energy, and combined cooling, heating and power (CCHP) systems. The CCHP has been investigated to reduce energy costs by using the thermal energy generated during the power generation process. For efficient utilization of CCHP and numerous power generation systems, accurate short-term load forecasting (STLF) is necessary. So far, even though many single algorithm-based STLF models have been proposed, they showed limited success in terms of applicability and coverage. This problem can be alleviated by combining such single algorithm-based models in ways that take advantage of their strengths. In this paper, we propose a novel two-stage STLF scheme; extreme gradient boosting and random forest models are executed in the first stage, and deep neural networks are executed in the second stage to combine them. To show the effectiveness of our proposed scheme, we compare our model with other popular single algorithm-based forecasting models and then show how much electric charges can be saved by operating CCHP based on the schedules made by the economic analysis on the predicted electric loads.

show abstract

“…However, there is no solution for the vanishing gradient problem for a long time, which makes it difficult for RNN to capture the dependence of the large time step distance in the time series in practice. Therefore, the deep learning technique known as LSTM network is proposed to resolve the vanishing gradient problem [45].…”

Section: Figure 5 Ordinary Rnn Sequential Logic Architecturementioning

confidence: 99%

Monitoring Water Quality Parameters of Taihu Lake Based on Remote Sensing Images and LSTM-RNN

Huang

Wang

2020

IEEE Access

View full text Add to dashboard Cite

Long-term dynamic monitoring of the water quality of freshwater resources is of great significance to the stable and orderly operation of human society. Most studies only use one of the measured data from the monitoring station and the remote sensing satellite data as the data source. However, a single data source will cause inaccuracy and incompatibility of the water quality monitoring results. Few studies start from practical applications to generate digital images of water quality changes. Furthermore, the performance of shallow neural networks in water quality monitoring is not often ideal. Considering the above problems, we proposed a long short-term memory network model (LSTM) to invert four key water parameters including pondus hydrogenii (PH), dissolved oxygen (DO), chemical oxygen demand (CODMn) and ammonia-nitrogen (NH3-H). Moreover, the model was applied to the satellite images of various periods to generate the inverted image of each water quality parameter. The proposed model has exhibited excellen t performance in the water quality ass essment of the project, with the coefficient of determination (R 2), the relative root-mean-square error (rRMSE), and the mean relative error (MRE) values of 0.83, 0.16, and 0.18, respectively. And the inverted images are also consistent with the official information. INDEX TERMS Remote sensing, water quality parameters, water quality monitoring, LSTM network.

show abstract

Deep Learning with Stacked Denoising Auto-Encoder for Short-Term Electric Load Forecasting

Cited by 52 publications

References 34 publications

Denoising Autoencoders and LSTM-Based Artificial Neural Networks Data Processing for Its Application to Internal Model Control in Industrial Environments—The Wastewater Treatment Plant Control Case

Denoising Autoencoders and LSTM-Based Artificial Neural Networks Data Processing for Its Application to Internal Model Control in Industrial Environments—The Wastewater Treatment Plant Control Case

A Two-Stage Industrial Load Forecasting Scheme for Day-Ahead Combined Cooling, Heating and Power Scheduling

Monitoring Water Quality Parameters of Taihu Lake Based on Remote Sensing Images and LSTM-RNN

Contact Info

Product

Resources

About