Review of Evaluation Criteria and Main Methods of Wind Power Forecasting

Zhao, Xin; Wang, Shuangxin; Li, Tao

doi:10.1016/j.egypro.2011.10.102

Cited by 148 publications

(67 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Some common error criteria include absolute error (AE), mean absolute error (MAE), mean absolute percentage error (MAPE), root mean-square error (RMSE), standard deviation of error (SDE) [8,15,[27][28][29], etc. Compared to MAE, RMSE is more sensitive to large data samples and is robust when dealing with large errors [30]. Here we use MAE and RMSE, given by:…”

Section: Error Criteriamentioning

confidence: 99%

Lorenz Wind Disturbance Model Based on Grey Generated Components

et al. 2014

View full text Add to dashboard Cite

Abstract:In order to meet the needs of wind speed prediction in wind farms, we consider the influence of random atmospheric disturbances on wind variations. Considering a simplified fluid convection mode, a Lorenz system can be employed as an atmospheric disturbance model. Here Lorenz disturbance is defined as the European norm of the solutions of the Lorenz equation. Grey generating and accumulated generating models are employed to explore the relationship between wind speed and its related disturbance series. We conclude that a linear or quadric polynomial generating model are optimal through the verification of short-term wind speed prediction in the Sotavento wind farm. The new proposed model not only greatly improves the precision of short-term wind speed prediction, but also has great significance for the maintenance and stability of wind power system operation.

show abstract

Section: Error Criteriamentioning

confidence: 99%

Lorenz Wind Disturbance Model Based on Grey Generated Components

et al. 2014

View full text Add to dashboard Cite

show abstract

“…Globally and locally the further the prediction, the larger the inaccuracies because of the sensitivities of the weather systems to initial conditions. Based on the following references [34,46], the short term time horizon estimations seem to oscillate between 48 and 72 hours and medium term covers 1 week ahead forecasting. Table 3.1 depicts these time brackets and their use.…”

Section: Similaritiesmentioning

confidence: 99%

“…Probabilistic forecasts of wind energy generation are of high financial importance for wind power industry players to assess the financial risk. Such forecasts can be based on forecast ensembles from numerical weather prediction models which is discussed shortly in the next subsection [47] [42] Up to 30 min ahead [34] Up to 9 hrs ahead [46] • Electricity market clearing [34] • Wind turbine control [34] • Ancillary services [46] Short term (hours)…”

Section: Similaritiesmentioning

confidence: 99%

“…Up to 48 or 72 hours ahead [34,46] • Economic load dispatch planning [34] • Load increment/decrement decisions [34] • Trading [46] Medium term (days) 48 or 72 hours to 1 week ahead [34,46] • Generator online/offline decisions (arragements for maintenance) [34,46] • Unit commitment decisions [34,46] [43] [44] [41] Probabilistic forecast methods can use ensembles to define the probability of the weather or atmosphere. Ensembles are different possible states in the atmosphere at a certain time.…”

Section: Similaritiesmentioning

confidence: 99%

See 1 more Smart Citation

Parametric Sensitivity Study for Wind Power Trading through Stochastic Reserve and Energy Market Optimization

Menin

Uzunoğlu

2015

2015 Seventh Annual IEEE Green Technologies Conference

View full text Add to dashboard Cite

Trading optimal wind power in energy and regulation market offers possibilities for increasing revenues as well as impacting security of the system in a positive way [33]. The bidding in both energy and regulation markets can be done through stochastic optimization process of both markets.Stochastic optimization can be possible once the probabilistic forecst is available through ensemble forecast methodology. For stochastic optimization, the post-processing of the ensembles to generate quantiles that will be used in optimization can be accomplished by employing different methodology. In this study, we will concentrate on the impact of post-processing of ensembles on the stochastic optimization.Generation of quantiles needed for stochastic optimization used herein for market optimization will be the main focus of the investigation. The impact of price ratios between energy and reserve market will be also investigated to analyse the impact of said ratios on the revenues. Furthermore this analysis will be performed for both US and Swedish markets.

show abstract

“…However, it is still one of the most difficult quantities to forecast [1], namely due its stochastic nature. The actual state of the art includes five main families of methods: persistence Method [2], physical Methods [3], spatial Correlation Models [5], artificial Intelligence Methods [6] and hybrid Methods [7].However, there will always be an inherent and irreducible uncertainty in every prediction.…”

Section: Introductionmentioning

confidence: 99%

Online Bayesian Learning with Natural Sequential Prior Distribution Used for Wind Speed Prediction

Cheggaga

2017

E3S Web Conf.

View full text Add to dashboard Cite

Predicting wind speed is one of the most important and critic tasks in a wind farm. All approaches, which directly describe the stochastic dynamics of the meteorological data are facing problems related to the nature of its non-Gaussian statistics and the presence of seasonal effects .In this paper, Online Bayesian learning has been successfully applied to online learning for three-layer perceptron's used for wind speed prediction. First a conventional transition model based on the squared norm of the difference between the current parameter vector and the previous parameter vector has been used. We noticed that the transition model does not adequately consider the difference between the current and the previous wind speed measurement. To adequately consider this difference, we use a natural sequential prior. The proposed transition model uses a Fisher information matrix to consider the difference between the observation models more naturally. The obtained results showed a good agreement between both series, measured and predicted. The mean relative error over the whole data set is not exceeding 5 %.

show abstract

Review of Evaluation Criteria and Main Methods of Wind Power Forecasting

Cited by 148 publications

References 21 publications

Lorenz Wind Disturbance Model Based on Grey Generated Components

Lorenz Wind Disturbance Model Based on Grey Generated Components

Parametric Sensitivity Study for Wind Power Trading through Stochastic Reserve and Energy Market Optimization

Online Bayesian Learning with Natural Sequential Prior Distribution Used for Wind Speed Prediction

Contact Info

Product

Resources

About