A Novel Approach for Seamless Probabilistic Photovoltaic Power Forecasting Covering Multiple Time Frames

Carrière, Thomas; Vernay, Christophe; Pitaval, Sébastien; Kariniotakis, Georges

doi:10.1109/tsg.2019.2951288

Cited by 42 publications

(32 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, spatio-temporal data improve the CAR performances by up to 3.5% for short-term horizons. The proposed deterministic approach could be extended to probabilistic forecasting using, for instance, kernel density estimation [17].…”

Section: Discussionmentioning

confidence: 99%

“…The literature has shown the relevance of exogenous inputs for PV production forecasting. Indeed, recent years have seen an increasing use of satellite images [6], [17] and distributed PV sites [7], [8] to reduce forecasting errors for short lead times. By considering nearby weather conditions, spatiotemporal models tend to outperform temporal-only models.…”

Section: Multi-input Approachmentioning

confidence: 99%

“…To decrease the related computational burden, only the most informative pixels are retained. To select the relevant pixels, the mutual information (MI) criterion is used [17]. Here, only the 10 most informative pixels are kept.…”

Section: Dimensionality Reductionmentioning

confidence: 99%

See 2 more Smart Citations

Short-term Forecasting of Photovoltaic Generation based on Conditioned Learning of Geopotential Fields

Bellinguer

Girard

Bontron³

et al. 2020

2020 55th International Universities Power Engineering Conference (UPEC)

View full text Add to dashboard Cite

Due to environmental concerns, renewable energy sources (RES) play an increasingly important role in the energy mix. In France, from 2018 to 2019, an increase of 21.2% and 7.8% of energy production was observed for wind and solar respectively [1]. RES are characterized by high variability and limited predictability, mostly due to their dependence on meteorological factors. This variability presents challenges for RES integration into grids and electricity markets: as the penetration of RES increases, power system balancing becomes more complex, and congestions may occur in the grid. This lack of predictability can also have financial consequences. In some European countries, energy producers have to pay penalties proportional to the forecasting error of the injected power. To address these challenges, it is important to accurately predict the future amount of energy production. In this paper we propose a spot statistical forecasting model for very short-term time horizons (from a few minutes up to 6 hours ahead). This model is based on a combination of heterogeneous inputs with a conditioned learning approach. Spatio-temporal inputs (measurements from geographically distributed PV sites and satellite images) are used to enhance short-term predictability, while a weather analog approach enables adaptability to changes in meteorological conditions by considering the most relevant past observations. The performance evaluations are carried out on a case study featuring nine PV plants located in France, over a one-year period. Index Terms-Short-term solar power forecasting, analog approach, conditional forecast, spatio-temporal, auto-regressive processes, smart grid.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Multi-input Approachmentioning

confidence: 99%

See 1 more Smart Citation

Short-term Forecasting of Photovoltaic Generation based on Conditioned Learning of Geopotential Fields

Bellinguer

Girard

Bontron³

et al. 2020

2020 55th International Universities Power Engineering Conference (UPEC)

View full text Add to dashboard Cite

show abstract

“…This is appealing in regional forecasting where synthetic regional indicators are needed. This idea of generating analogs from a similarity ranking has proved to be efficient in wind forecasting [21] and solar forecasting [22], [23]. In this paper, we adapt an analog-based approach considering spatially distributed data [24] to estimate the future regional wind production.…”

Section: Feature Engineeringmentioning

confidence: 99%

Probabilistic Forecasting of Regional Wind Power Generation for the EEM20 Competition: a Physics-oriented Machine Learning Approach

Bellinguer

Mahler

Camal

et al. 2020

2020 17th International Conference on the European Energy Market (EEM)

View full text Add to dashboard Cite

Variable renewable energy has a growing impact on electricity markets and power systems in many regions of the world. In this context, the 17th International Conference on the European Energy Market EEM20 set up a competition to develop probabilistic forecasting tools of wind production at a regional level. This paper proposes an adaptive approach for regional wind power forecasting. A physics-oriented preprocessing of the data delivers analog weather patterns and windpower-related variables, then a k-means clustering of wind farms further reduces the dimension of the problem. The generated representative features feed a Quantile Regression Forests model that produces sharp and reliable predictions. As a result, our model won the competition with a relative improvement of the average pinball loss of 6.7% and 14.7%, compared to the teams ranked second and third respectively.

show abstract

“…The model we use to produce PV production forecasts for the first case study is an improvement of the AnEn model [14], which is presented in [28]. One advantage of this model is that it is very close to a kNN estimator, which makes it simple to understand.…”

Section: B Pv Power Forecasting Model: the Analog Ensemblementioning

confidence: 99%

An Integrated Approach for Value-Oriented Energy Forecasting and Data-Driven Decision-Making Application to Renewable Energy Trading

Carrière

Kariniotakis

2019

IEEE Trans. Smart Grid

Self Cite

View full text Add to dashboard Cite

A Novel Approach for Seamless Probabilistic Photovoltaic Power Forecasting Covering Multiple Time Frames

Cited by 42 publications

References 40 publications

Short-term Forecasting of Photovoltaic Generation based on Conditioned Learning of Geopotential Fields

Short-term Forecasting of Photovoltaic Generation based on Conditioned Learning of Geopotential Fields

Probabilistic Forecasting of Regional Wind Power Generation for the EEM20 Competition: a Physics-oriented Machine Learning Approach

An Integrated Approach for Value-Oriented Energy Forecasting and Data-Driven Decision-Making Application to Renewable Energy Trading

Contact Info

Product

Resources

About