Latent Representation Learning for Artificial Bandwidth Extension Using a Conditional Variational Auto-encoder

Bachhav, Pramod; Todisco, Massimiliano; Evans, Nicholas

doi:10.1109/icassp.2019.8683611

Cited by 9 publications

(5 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…VAE combined with neural layers and its versions were explained for the uses of anomaly detection. Also, the process of forecasting became more efficient [53][54][55][56].…”

Section: V) Variational Auto-encoders (Vae)mentioning

confidence: 99%

Load Forecasting Techniques for Power System: Research Challenges and Survey

et al. 2022

View full text Add to dashboard Cite

The main and pivot part of electric companies is the load forecasting. Decision-makers and think tank of power sectors should forecast the future need of electricity with large accuracy and small error to give uninterrupted and free of load shedding power to consumers. The demand of electricity can be forecasted amicably by many Machine Learning (ML), Deep Learning (DL) and Artificial Intelligence (AI) techniques among which hybrid methods are most popular. The present technologies of load forecasting and present work regarding combination of various ML, DL and AI algorithms are reviewed in this paper. The comprehensive review of single and hybrid forecasting models with functions; advantages and disadvantages are discussed in this paper. The comparison between the performance of the models in terms of Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE) values are compared and discussed with literature of different models to support the researchers to select the best model for load prediction. This comparison validates the fact that the hybrid forecasting models will provide a more optimal solution.INDEX TERMS load forecasting, machine learning, load shedding, root mean squared error, mean absolute percentage error.

show abstract

“…VAE combined with neural layers and its versions were explained for the uses of anomaly detection. Also, the process of forecasting became more efficient [53][54][55][56].…”

Section: V) Variational Auto-encoders (Vae)mentioning

confidence: 99%

Load Forecasting Techniques for Power System: Research Challenges and Survey

et al. 2022

View full text Add to dashboard Cite

show abstract

“…VAEs are relatively a new class of AEs in energy systems which employ the concept of variational inference and Bayesian optimization to carry out the encoding and decoding operations [126, 127]. VAE integrated with recurrent neural layers and its variants have been recently explored for the application of anomaly detection and to make the forecasting process more efficient [128–131]. To reduce the dimensionality arising from time lags considered in renewable generation forecasting, VAEs have been implemented in [132] before performing forecasts with BLSTM.…”

Section: Data Pre‐processing Techniques For Energy Forecastingmentioning

confidence: 99%

“…tion of anomaly detection and to make the forecasting process more efficient [128][129][130][131]. To reduce the dimensionality arising from time lags considered in renewable generation forecasting, VAEs have been implemented in [132] before performing forecasts with BLSTM.…”

Section: Variational Auto-encoders (Vae)mentioning

confidence: 99%

Energy forecasting in smart grid systems: recent advancements in probabilistic deep learning

Kaur

Islam

Mahmud

et al. 2022

IET Generation Trans & Dist

View full text Add to dashboard Cite

Energy forecasting plays a vital role in mitigating challenges in data rich smart grid (SG) systems involving various applications such as demand-side management, load shedding, and optimum dispatch. Managing efficient forecasting while ensuring the least possible prediction error is one of the main challenges posed in the grid today, considering the uncertainty in SG data. This paper presents a comprehensive and application-oriented review of state-of-the-art forecasting methods for SG systems along with recent developments in probabilistic deep learning (PDL). Traditional point forecasting methods including statistical, machine learning (ML), and deep learning (DL) are extensively investigated in terms of their applicability to energy forecasting. In addition, the significance of hybrid and data preprocessing techniques to support forecasting performance is also studied. A comparative case study using the Victorian electricity consumption in Australia and American electric power (AEP) datasets is conducted to analyze the performance of deterministic and probabilistic forecasting methods. The analysis demonstrates higher efficacy of DL methods with appropriate hyper-parameter tuning when sample sizes are larger and involve nonlinear patterns. Furthermore, PDL methods are found to achieve at least 60% lower prediction errors in comparison to other benchmark DL methods. However, the execution time increases significantly for PDL methods due to large sample space and a tradeoff between computational performance and forecasting accuracy needs to be maintained.

show abstract

“…In this context, variational autoencoders (VAE), widely used in the existing deep learning literature for dimensionality reduction [28], can be implemented to improve the computational efficiency of Bayesian deep learning techniques. VAE represents the encoder with probability distributions which transforms the input data to adopt a lower dimensional structure [29].…”

Section: Introductionmentioning

confidence: 99%

A VAE-Bayesian Deep Learning Scheme for Solar Generation Forecasting based on Dimensionality Reduction

Kaur¹,

Islam²,

Mahmud³

et al. 2021

Preprint

View full text Add to dashboard Cite

The advancement in distributed generation technologies in modern power systems has led to a widespread integration of renewable power generation at customer side. However, the intermittent nature of renewable energy pose new challenges to the network operational planning with underlying uncertainties. This paper proposes a novel Bayesian probabilistic technique for forecasting renewable power generation by addressing data and model uncertainties by integrating bidirectional long short-term memory (BiLSTM) neural networks while compressing the weight parameters using variational autoencoder (VAE). Existing Bayesian deep learning methods suffer from high computational complexities as they require to draw a large number of samples from weight parameters expressed in the form of probability distributions. The proposed method can deal with uncertainty present in model and data in a more computationally efficient manner by reducing the dimensionality of model parameters. The proposed method is evaluated using pinball loss, reconstruction error, and other forecasting evaluation metrics. It is inferred from the numerical results that VAE-Bayesian BiLSTM outperforms other probabilistic deep learning methods in terms of forecasting accuracy and computational efficiency for different sizes of the dataset.

show abstract

Latent Representation Learning for Artificial Bandwidth Extension Using a Conditional Variational Auto-encoder

Cited by 9 publications

References 19 publications

Load Forecasting Techniques for Power System: Research Challenges and Survey

Load Forecasting Techniques for Power System: Research Challenges and Survey

Energy forecasting in smart grid systems: recent advancements in probabilistic deep learning

A VAE-Bayesian Deep Learning Scheme for Solar Generation Forecasting based on Dimensionality Reduction

Contact Info

Product

Resources

About