Probabilistic spatiotemporal wind speed forecasting based on a variational Bayesian deep learning model

Liu, Yongqi; Hui, Qing; Zhang, Zhendong; Pei, Shaoqian; Jiang, Zhiqiang; Feng, Zhong-kai; Zhou, Jing

doi:10.1016/j.apenergy.2019.114259

Cited by 135 publications

(40 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some recent studies explored the BDL concept for weather forecasting applications. A model built on GRU and 3D CNN, along with variational Bayesian inference for estimating posterior parameter distributions, has been presented by Liu et al [141] for probabilistic wind speed forecasting of up to 3 h. A study from Vandal et al [92] demonstrates the use of BDL to capture the uncertainty from observation data and unknown model parameters in the context of statistical downscaling of precipitation forecasts. These are relevant contributions, but a lot remains to be done before the uncertainty of DL weather forecasts can be assessed at a level similar to current NWP ensemble systems.…”

Section: Uncertainty Estimationmentioning

confidence: 99%

Can deep learning beat numerical weather prediction?

Schultz

Betancourt

Gong

et al. 2021

Phil. Trans. R. Soc. A.

187

110

View full text Add to dashboard Cite

The recent hype about artificial intelligence has sparked renewed interest in applying the successful deep learning (DL) methods for image recognition, speech recognition, robotics, strategic games and other application areas to the field of meteorology. There is some evidence that better weather forecasts can be produced by introducing big data mining and neural networks into the weather prediction workflow. Here, we discuss the question of whether it is possible to completely replace the current numerical weather models and data assimilation systems with DL approaches. This discussion entails a review of state-of-the-art machine learning concepts and their applicability to weather data with its pertinent statistical properties. We think that it is not inconceivable that numerical weather models may one day become obsolete, but a number of fundamental breakthroughs are needed before this goal comes into reach. This article is part of the theme issue ‘Machine learning for weather and climate modelling’.

show abstract

Section: Uncertainty Estimationmentioning

confidence: 99%

Can deep learning beat numerical weather prediction?

Schultz

Betancourt

Gong

et al. 2021

Phil. Trans. R. Soc. A.

187

110

View full text Add to dashboard Cite

show abstract

“…Firstly, one can implement a two-step procedure whereby a point forecasting is firstly obtained and a distribution should then be estimated to calibrate the point results and get a final density forecast. In particular, an efficient framework to approximate the posterior distribution that quantifies the prediction uncertainty consists in using variational inference [35]- [37]. Secondly, there are methods directly providing the probabilistic predictions.…”

Section: Inputs Selection and Model Trainingmentioning

confidence: 99%

Capturing Spatio-Temporal Dependencies in the Probabilistic Forecasting of Distribution Locational Marginal Prices

Toubeau

Morstyn

Bottieau

et al. 2021

IEEE Trans. Smart Grid

View full text Add to dashboard Cite

This paper presents a new spatio-temporal framework for the day-ahead probabilistic forecasting of Distribution Locational Marginal Prices (DLMPs). The approach relies on a recurrent neural network, whose architecture is enriched by introducing a deep bidirectional variant designed to capture the complex time dynamics in multi-step forecasts. In order to account for nodal price differentiation (arising from grid constraints) within a procedure that is scalable to large distribution systems, nodal DLMPs are predicted individually by a single model guided by a generic representation of the grid. This strategy offers the additional benefit to enable cold-start forecasting for new nodes with no history. Indeed, in case of topological changes, e.g. building of a new home or installation of photovoltaic panels, the forecaster intrinsically leverages the statistical information learned from neighbouring nodes to predict the new DLMP, without needing any modification of the tool. The approach is evaluated, along with several other methods, on a radial low voltage network. Outcomes highlight that relying on a compact model is a key component to boost its generalization capabilities in high-dimensionality, while indicating that the proposed tool is effective for both temporal and spatial learning.

show abstract

“…While IPIFs are based on the use of a predicted value calculated through a PPF as a baseline for the interval's value prediction, DPIFs predict the interval directly without the use of a PPF value. A review of the literature suggests that even though researchers are developing both DPIFs [35,36] and IPIFs [33,34,[37][38][39], more effort is going into IPIF, and thus there more published studies involving IPIFs. The second dimension splits PIFs into parametric and non-parametric forecasters.…”

Section: Introductionmentioning

confidence: 99%

A Very Short-Term Probabilistic Prediction Interval Forecaster for Reducing Load Uncertainty Level in Smart Grids

et al. 2021

View full text Add to dashboard Cite

Very short-term load demand forecasters are essential for power systems’ decision makers in real-time dispatching. These tools allow traditional network operators to maintain power systems’ safety and stability and provide customers energy with high reliability. Although research has traditionally focused on developing point forecasters, these tools do not provide complete information because they do not estimate the deviation between actual and predicted values. Therefore, the aim of this paper is to develop a very short-term probabilistic prediction interval forecaster to reduce decision makers’ uncertainty by computing the predicted value’s upper and lower bounds. The proposed forecaster combines an artificial intelligence-based point forecaster with a probabilistic prediction interval algorithm. First, the point forecaster predicts energy demand in the next 15 min and then the prediction interval algorithm calculates the upper and lower bounds with the user’s chosen confidence level. To examine the reliability of proposed forecaster model and resulting interval sharpness, different error metrics, such as prediction interval coverage percentage and a skill score, are computed for 95, 90, and 85% confidence intervals. Results show that the prediction interval coverage percentage is higher than the confidence level in each analysis, which means that the proposed model is valid for practical applications.

show abstract

Probabilistic spatiotemporal wind speed forecasting based on a variational Bayesian deep learning model

Cited by 135 publications

References 40 publications

Can deep learning beat numerical weather prediction?

Can deep learning beat numerical weather prediction?

Capturing Spatio-Temporal Dependencies in the Probabilistic Forecasting of Distribution Locational Marginal Prices

A Very Short-Term Probabilistic Prediction Interval Forecaster for Reducing Load Uncertainty Level in Smart Grids

Contact Info

Product

Resources

About