Forecasting conditional extreme quantiles for wind energy

Gonçalves, Carla; Cavalcante, Laura; Brito, Margarida; Bessa, Ricardo J.; Gama, João

doi:10.1016/j.epsr.2020.106636

“…Forecasting [24][25], [27][28][29][30][31], [35][36][37][38], [40][41][42][43], [45][46], [49][50][51], [54], [57][58] Storage systems [27][28][29], [31], [35], [37], [41], [46], [49][50][51], [54], [57], [62] Risk management [24], [27][28], [45], [50][51], [58], [59] Electric vehicles [24][25], [27], [35], [45], [49],…”

Section: Reviewed Workmentioning

confidence: 99%

A review of short‐term wind power probabilistic forecasting and a taxonomy focused on input data

Bazionis

¹

,

Karafotis

²

,

Georgilakis

³

2021

IET Renewable Power Gen

View full text Add to dashboard Cite

A review of state‐of‐the‐art short‐term wind power probabilistic forecasting models is the focus here. The improvement of the accuracy and efficiency of probabilistic forecasting models has been in the centre of attention of researchers in recent years, since the need to further comprehend and efficiently use the uncertainty of forecasts is increasing. Since the optimal operation and control of energy systems and electricity markets is one of the important aspects of performing wind power forecasts, this review focuses in short‐term probabilistic forecasting models, which could prove to be useful in the daily planning and operation of power systems. The short‐term concept of forecasts is analysed in detail, along with the case studies and examples proposed by the reviewed literature. The key advantages and disadvantages of the reviewed probabilistic forecasting methodologies are identified. Furthermore, different classifications of the reviewed works according to the data that are used to provide an accurate forecasting model are also provided. Future directions in the field of short‐term wind power probabilistic forecasting are also proposed.

show abstract

“…Extreme value theory provides a theoretical framework for this task, particularly the peaks-over-threshold method and the resulting Generalised Pareto Distribution (GPD) [13]. The GPD has recently been applied to the tails of probabilistic wind power forecasts and shown to be effective where quantile regression fails [14]. We propose applying a similar technique for net-load here, but, while in [14] the GPD parameters are fixed, we allow them to depend on covariates along the lines of [15].…”

Section: Introductionmentioning

confidence: 99%

“…The GPD has recently been applied to the tails of probabilistic wind power forecasts and shown to be effective where quantile regression fails [14]. We propose applying a similar technique for net-load here, but, while in [14] the GPD parameters are fixed, we allow them to depend on covariates along the lines of [15]. In the case of net-load, we suspect that, similarly to the central portion of the predictive distribution, the tails will depend on behavioural and weather effects.…”

Section: Introductionmentioning

confidence: 99%

Probabilistic Forecasting of Regional Net-Load With Conditional Extremes and Gridded NWP

Browell

¹

,

Fasiolo

²

2021

IEEE Trans. Smart Grid

View full text Add to dashboard Cite

The increasing penetration of embedded renewables makes forecasting net-load, consumption less embedded generation, a significant and growing challenge. Here a framework for producing probabilistic forecasts of net-load is proposed with particular attention given to the tails of predictive distributions, which are required for managing risk associated with lowprobability events. Only small volumes of data are available in the tails, by definition, so estimation of predictive models and forecast evaluation requires special attention. We propose a solution based on a best-in-class load forecasting methodology adapted for netload, and model the tails of predictive distributions with the Generalised Pareto Distribution, allowing its parameters to vary smoothly as functions of covariates. The resulting forecasts are shown to be calibrated and sharper than those produced with unconditional tail distributions. In a use-case inspired evaluation exercise based on reserve setting, the conditional tails are shown to reduce the overall volume of reserve required to manage a given risk. Furthermore, they identify periods of high risk not captured by other methods. The proposed method therefore enables user to both reduce costs and avoid excess risk.

show abstract

“…Extreme value theory provides a theoretical framework for this task, particularly the peaksover-threshold method and the resulting Generalised Pareto Distribution (GPD) [10]. The GPD has recently been applied to the tails of probabilistic wind power forecasts and shown to be effective where quantile regression fails [11]. We propose applying a similar technique for net-load here, but, while in [11] the GPD parameters are fixed, we allow them to depend on covariates along the lines of [12].…”

Section: Introductionmentioning

confidence: 99%

“…The GPD has recently been applied to the tails of probabilistic wind power forecasts and shown to be effective where quantile regression fails [11]. We propose applying a similar technique for net-load here, but, while in [11] the GPD parameters are fixed, we allow them to depend on covariates along the lines of [12]. In the case of net-load, we suspect that, similarly to the central portion of the predictive distribution, the tails will depend on behavioural and weather effects.…”

Section: Introductionmentioning

confidence: 99%

Probabilistic Forecasting of Regional Net-load with Conditional Extremes and Gridded NWP

Browell,

Fasiolo

2021

Preprint

0

View full text Add to dashboard Cite

The increasing penetration of embedded renewables makes forecasting net-load, consumption less embedded generation, a significant and growing challenge. Here a framework for producing probabilistic forecasts of net-load is proposed with particular attention given to the tails of predictive distributions, which are required for managing risk associated with lowprobability events. Only small volumes of data are available in the tails, by definition, so estimation of predictive models and forecast evaluation requires special attention. We propose a solution based on a best-in-class load forecasting methodology adapted for netload, and model the tails of predictive distributions with the Generalised Pareto Distribution, allowing its parameters to vary smoothly as functions of covariates. The resulting forecasts are shown to be calibrated and sharper than those produced with unconditional tail distributions. In a use-case inspired evaluation exercise based on reserve setting, the conditional tails are shown to reduce the overall volume of reserve required to manage a given risk. Furthermore, they identify periods of high risk not captured by other methods. The proposed method therefore enables user to both reduce costs and avoid excess risk.

show abstract

Forecasting conditional extreme quantiles for wind energy

Cited by 16 publications

References 19 publications

A review of short‐term wind power probabilistic forecasting and a taxonomy focused on input data

A review of short‐term wind power probabilistic forecasting and a taxonomy focused on input data

Probabilistic Forecasting of Regional Net-Load With Conditional Extremes and Gridded NWP

Probabilistic Forecasting of Regional Net-load with Conditional Extremes and Gridded NWP

Contact Info

Product

Resources

About