Probabilistic photovoltaic power forecasting model based on deterministic forecasts

This paper presents an original probabilistic photovoltaic (PV) power forecasting model for the day-ahead hourly generation in a PV plant. The probabilistic forecasting model is based on 12 deterministic models developed with different techniques. An optimization process, ruled by a genetic algorithm, chooses the forecasts of the deterministic models in order to achieve the probability distribution function (PDF) for the PV generation in each one of the daylight hours of the following day in a parametric approach. The PDFs, which constitute the probabilistic forecasts, are a mixture of normal distributions, each one centred in the forecasts of the selected deterministic models. The genetic algorithm chooses the deterministic forecasts, the variance of the normal distributions and their weights in the mixture. In a case study the proposed model achieves better forecasting results than the obtained with the conditional quantile regression method applied to the same data used to develop the deterministic forecasting models.

Download Full-text

Probabilistic forecasting of coastal wave height during typhoon warning period using machine learning methods

Journal of Hydroinformatics ◽

10.2166/hydro.2019.115 ◽

2019 ◽

Vol 21 (2) ◽

pp. 343-358 ◽

Cited By ~ 2

Author(s):

Shien-Tsung Chen

Keyword(s):

Machine Learning ◽

Wave Height ◽

Fuzzy Inference ◽

Forecasting Model ◽

Probabilistic Forecasting ◽

Inference Model ◽

Machine Learning Methods ◽

Probabilistic Forecasts ◽

Forecasting Method ◽

Height Data

Abstract This study applied machine learning methods to perform the probabilistic forecasting of coastal wave height during the typhoon warning period. The probabilistic forecasts comprise a deterministic forecast and the probability distribution of a forecast error. A support vector machine was used to develop a real-time forecasting model for generating deterministic wave height forecasts. The forecast errors of deterministic forecasting were then used as a database to generate probabilistic forecasts by using the modified fuzzy inference model. The innovation of the modified fuzzy inference model includes calculating the similarity of the data by performing fuzzy implication and resampling the potential data from the fuzzy database for probability distribution. The probabilistic forecasting method was applied to the east coast of Taiwan, where typhoons frequently cause large waves. Hourly wave height data from an offshore buoy and various typhoon characteristics were used as inputs of the probabilistic forecasting model. Validation results from real typhoon events verified that the proposed probabilistic forecasting model can generate the predicted confidence interval, which can properly enclose the observed wave height data, excluding some cases with extreme wave heights. Moreover, an objective measure was used to validate the proposed probabilistic forecasting method.

Download Full-text

Adaptive correction of deterministic models to produce probabilistic forecasts

Hydrology and Earth System Sciences ◽

10.5194/hess-16-2783-2012 ◽

2012 ◽

Vol 16 (8) ◽

pp. 2783-2799 ◽

Cited By ~ 25

Author(s):

P. J. Smith ◽

K. J. Beven ◽

A. H. Weerts ◽

D. Leedal

Keyword(s):

Efficient Method ◽

Flood Forecasting ◽

Forecasting Model ◽

Computationally Efficient ◽

Deterministic Models ◽

Probabilistic Forecasts ◽

Adaptive Correction ◽

System Output ◽

Forecasting System

Abstract. This paper considers the correction of deterministic forecasts given by a flood forecasting model. A stochastic correction based on the evolution of an adaptive, multiplicative, gain is presented. A number of models for the evolution of the gain are considered and the quality of the resulting probabilistic forecasts assessed. The techniques presented offer a computationally efficient method for providing probabilistic forecasts based on existing flood forecasting system output.

Download Full-text

Adaptive correction of deterministic models to produce accurate probabilistic forecasts

Hydrology and Earth System Sciences Discussions ◽

10.5194/hessd-9-595-2012 ◽

2012 ◽

Vol 9 (1) ◽

pp. 595-627 ◽

Cited By ~ 2

Author(s):

P. J. Smith ◽

K. Beven ◽

A. Weerts ◽

D. Leedal

Keyword(s):

Efficient Method ◽

Flood Forecasting ◽

Forecasting Model ◽

Computationally Efficient ◽

Deterministic Models ◽

Probabilistic Forecasts ◽

Adaptive Correction ◽

System Output ◽

Forecasting System

Abstract. This paper considers the correction of deterministic forecasts given by a flood forecasting model. A stochastic correction based on the evolution of an adaptive, multiplicative, gain is presented. A number of models for the evolution of the gain are considered and the quality of the resulting probabilistic forecasts assessed. The techniques presented offer, in certain situations, an effective and computationally efficient method for providing probabilistic forecasts based on existing flood forecasting system output.

Download Full-text

Probabilistic reference model for hourly PV power generation forecasting

E3S Web of Conferences ◽

10.1051/e3sconf/202015201002 ◽

2020 ◽

Vol 152 ◽

pp. 01002

Author(s):

L. Alfredo Fernandez-Jimenez ◽

Sonia Terreros-Olarte ◽

Alberto Falces ◽

Pedro M. Lara-Santillan ◽

Enrique Zorzano-Alba ◽

...

Keyword(s):

Time Series ◽

Reference Model ◽

Power Production ◽

Forecasting Model ◽

Probabilistic Forecasting ◽

Mean Power ◽

Forecasting Models ◽

Proposed Model ◽

Probabilistic Forecasts

This paper presents a new probabilistic forecasting model of the hourly mean power production in a Photovoltaic (PV) plant. It uses the minimal information and it can provide probabilistic forecasts in the form of quantiles for the desired horizon, which ranges from the next hours to any day in the future. The proposed model only needs a time series of hourly mean power production in the PV plant, and it is intended to fill a gap in international literature where hardly any model has been proposed as a reference for comparison or benchmarking purposes with other probabilistic forecasting models. The performance of the proposed forecasting model is tested, in a case study, with the time series of hourly mean power production in a PV plant with 1.9 MW capacity. The results show an improvement with respect to the reference probabilistic PV power forecasting models reported in the literature.

Download Full-text

A Hybrid Wind Power Forecasting Model with XGBoost, Data Preprocessing Considering Different NWPs

Applied Sciences ◽

10.3390/app11031100 ◽

2021 ◽

Vol 11 (3) ◽

pp. 1100

Author(s):

Quoc Thang Phan ◽

Yuan Kang Wu ◽

Quoc Dung Phan

Keyword(s):

Deep Learning ◽

Wind Power ◽

Weather Prediction ◽

Data Preprocessing ◽

Forecasting Model ◽

Efficient Operation ◽

Wind Power Forecasting ◽

Wind Speeds ◽

Probabilistic Forecasts ◽

Power Forecasting

In recent years, wind energy has become a competitively priced source of energy around the world, which has created increasing challenges for system operators. Accurate wind power generation forecasting plays an important role in power systems to improve the reliable and efficient operation. Therefore, numerous artificial intelligent methods such as machine learning and deep learning have been considered as solutions for accurate wind power forecasts. In addition to deterministic forecasting, the probabilistic forecasting becomes more important, because it indicates the level of uncertainty. In this paper, a hybrid forecasting model considering different Numerical Weather Prediction (NWP) models and the XGBoost training model is proposed for short-term wind power forecasting. The proposed forecasting algorithm includes data preprocessing, in which an autoencoder model is used to reduce the dimension of 20 NWP ensembles. The performance of the proposed method is investigated using historical wind power measurements and NWP results by the Taiwan Central Weather Bureau (CWB); the NWP includes spot wind speeds from WRFD, RWRF, and ensemble wind speeds from WEPS. Based on the forecasting results, the proposed model produces better performance and forecasting accuracy among other forecasting models, which reveals the importance of data preprocessing using autoencoders and the use of deep learning models in deterministic or probabilistic forecasts.

Download Full-text

ESTIMATION OF THE FROCINI CRITERIA AND OMEGA SQUARE CRITERIA STATISTICS BY THE STATISTICAL TESTS METHOD FOR A MIXTURE OF NORMAL DISTRIBUTIONS

Siberian Journal of Science and Technology ◽

10.31772/2587-6066-2019-20-1-28-34 ◽

2019 ◽

Vol 20 (1) ◽

pp. 28-34

Author(s):

S. V. Ushanov ◽

◽

D. A. Ogurtsov ◽

Keyword(s):

Statistical Tests ◽

Normal Distributions ◽

Mixture Of Normal Distributions

Download Full-text

Normal approximation for mixtures of normal distributions and the evolution of phenotypic traits

Advances in Applied Probability ◽

10.1017/apr.2020.53 ◽

2021 ◽

Vol 53 (1) ◽

pp. 162-188

Author(s):

Krzysztof Bartoszek ◽

Torkel Erhardsson

Keyword(s):

Normal Distribution ◽

Phenotypic Trait ◽

Phenotypic Traits ◽

Normal Distributions ◽

Average Value ◽

Conditional Moments ◽

Mixture Of Normal Distributions ◽

Explicit Bounds ◽

Mixtures Of Normal Distributions ◽

Parameter Values

AbstractExplicit bounds are given for the Kolmogorov and Wasserstein distances between a mixture of normal distributions, by which we mean that the conditional distribution given some $\sigma$ -algebra is normal, and a normal distribution with properly chosen parameter values. The bounds depend only on the first two moments of the first two conditional moments given the $\sigma$ -algebra. The proof is based on Stein’s method. As an application, we consider the Yule–Ornstein–Uhlenbeck model, used in the field of phylogenetic comparative methods. We obtain bounds for both distances between the distribution of the average value of a phenotypic trait over n related species, and a normal distribution. The bounds imply and extend earlier limit theorems by Bartoszek and Sagitov.

Download Full-text