Continuous and Distribution-free Probabilistic Wind Power Forecasting

We present a data-driven approach for probabilistic wind power forecasting based on conditional normalizing flow~(CNF). In contrast with the existing, this approach is distribution-free (as for non-parametric and quantile-based approaches) and can directly yield continuous probability densities, hence avoiding quantile crossing. It relies on a base distribution and a set of bijective mappings. Both the shape parameters of the base distribution and the bijective mappings are approximated with neural networks. Spline-based conditional normalizing flow is considered owing to its universal approximation capability. Over the training phase, the model sequentially maps input examples onto samples of base distribution, where parameters are estimated through maximum likelihood. To issue probabilistic forecasts, one eventually map samples of the base distribution into samples of a desired distribution. Case studies based on open datasets validate the effectiveness of the proposed model, and allows us to discuss its advantages and caveats with respect to the state of the art. Code will be released upon publication.

Download Full-text

Probabilistic Short-Term Wind Power Forecasting Using Sparse Bayesian Learning and NWP

Mathematical Problems in Engineering ◽

10.1155/2015/785215 ◽

2015 ◽

Vol 2015 ◽

pp. 1-11 ◽

Cited By ~ 6

Author(s):

Kaikai Pan ◽

Zheng Qian ◽

Niya Chen

Keyword(s):

Wind Power ◽

Bayesian Learning ◽

Weather Prediction ◽

Parameters Optimization ◽

Gaussian Kernel ◽

Sparse Bayesian Learning ◽

Short Term ◽

Wind Power Forecasting ◽

Proposed Model ◽

Power Forecasting

Probabilistic short-term wind power forecasting is greatly significant for the operation of wind power scheduling and the reliability of power system. In this paper, an approach based on Sparse Bayesian Learning (SBL) and Numerical Weather Prediction (NWP) for probabilistic wind power forecasting in the horizon of 1–24 hours was investigated. In the modeling process, first, the wind speed data from NWP results was corrected, and then the SBL was used to build a relationship between the combined data and the power generation to produce probabilistic power forecasts. Furthermore, in each model, the application of SBL was improved by using modified-Gaussian kernel function and parameters optimization through Particle Swarm Optimization (PSO). To validate the proposed approach, two real-world datasets were used for construction and testing. For deterministic evaluation, the simulation results showed that the proposed model achieves a greater improvement in forecasting accuracy compared with other wind power forecast models. For probabilistic evaluation, the results of indicators also demonstrate that the proposed model has an outstanding performance.

Download Full-text

IEA Wind Task 36 Forecasting

10.5194/egusphere-egu2020-14253 ◽

2020 ◽

Author(s):

Gregor Giebel ◽

Will Shaw ◽

Helmut Frank ◽

Pierre Pinson ◽

Caroline Draxl ◽

...

Keyword(s):

Wind Power ◽

Selection Process ◽

Meteorological Data ◽

Weather Prediction ◽

International Energy Agency ◽

General Situation ◽

Energy Agency ◽

Wind Power Forecasting ◽

Probabilistic Forecasts ◽

Power Forecasting

Wind power forecasts have been used operatively for over 20 years. Despite this fact, there are still several possibilities to improve the forecasts, both from the weather prediction side and from the usage of the forecasts. The International Energy Agency (IEA) Wind Task on Wind Power Forecasting organises international collaboration, among national weather centres with an interest and/or large projects on wind forecast improvements (NOAA, DWD, UK MetOffice, ...), forecast vendors and forecast users. Collaboration is open to IEA Wind member states, 12 countries are already therein.The Task is divided in three work packages: Firstly, a collaboration on the improvement of the scientific basis for the wind predictions themselves. This includes numerical weather prediction model physics, but also widely distributed information on accessible datasets. Secondly, we will be aiming at an international pre-standard (an IEA Recommended Practice) on benchmarking and comparing wind power forecasts, including probabilistic forecasts. This WP will also organise benchmarks for NWP models. Thirdly, we will be engaging end users aiming at dissemination of the best practice in the usage of wind power predictions.The main result is the IEA Recommended Practice for Selecting Renewable Power Forecasting Solutions. This document in three parts (Forecast solution selection process, and Designing and executing forecasting benchmarks and trials, and their Evaluation) takes its outset from the recurrent problem at forecast user companies of how to choose a forecast vendor. The first report describes how to tackle the general situation, while the second report specifically describes how to set up a forecasting trial so that the result is what the client intended. Many of the pitfalls which we have seen over the years, are avoided. Other results include a paper on possible uses of uncertainty forecasts, an assessment of the uncertainty chain within the forecasts, and meteorological data on an information portal for wind power forecasting. This meteorological data is used for a benchmark exercise, to be announced at the conference. The poster will present the latest developments from the Task, and announce the next activities.

Download Full-text

Using quantile regression to extend an existing wind power forecasting system with probabilistic forecasts

Wind Energy ◽

10.1002/we.180 ◽

2006 ◽

Vol 9 (1-2) ◽

pp. 95-108 ◽

Cited By ~ 155

Author(s):

Henrik Aalborg Nielsen ◽

Henrik Madsen ◽

Torben Skov Nielsen

Keyword(s):

Quantile Regression ◽

Wind Power ◽

Wind Power Forecasting ◽

Probabilistic Forecasts ◽

Forecasting System ◽

Power Forecasting

Download Full-text

Integrated Machine Learning and Enhanced Statistical Approach-Based Wind Power Forecasting in Australian Tasmania Wind Farm

Complexity ◽

10.1155/2020/9250937 ◽

2020 ◽

Vol 2020 ◽

pp. 1-12

Author(s):

Fang Yao ◽

Wei Liu ◽

Xingyong Zhao ◽

Li Song

Keyword(s):

Machine Learning ◽

Wind Speed ◽

Wind Power ◽

Wind Farm ◽

Statistical Approach ◽

Short Term Memory ◽

Prediction Interval ◽

Wind Power Forecasting ◽

Proposed Model ◽

Power Forecasting

This paper develops an integrated machine learning and enhanced statistical approach for wind power interval forecasting. A time-series wind power forecasting model is formulated as the theoretical basis of our method. The proposed model takes into account two important characteristics of wind speed: the nonlinearity and the time-changing distribution. Based on the proposed model, six machine learning regression algorithms are employed to forecast the prediction interval of the wind power output. The six methods are tested using real wind speed data collected at a wind station in Australia. For wind speed forecasting, the long short-term memory (LSTM) network algorithm outperforms other five algorithms. In terms of the prediction interval, the five nonlinear algorithms show superior performances. The case studies demonstrate that combined with an appropriate nonlinear machine learning regression algorithm, the proposed methodology is effective in wind power interval forecasting.

Download Full-text

Probabilistic Wind Power Forecasting Approach via Instance-Based Transfer Learning Embedded Gradient Boosting Decision Trees

Energies ◽

10.3390/en12010159 ◽

2019 ◽

Vol 12 (1) ◽

pp. 159 ◽

Cited By ~ 12

Author(s):

Long Cai ◽

Jie Gu ◽

Jinghuan Ma ◽

Zhijian Jin

Keyword(s):

Power System ◽

Decision Trees ◽

Wind Power ◽

Transfer Learning ◽

Training Data ◽

Gradient Boosting ◽

Training Process ◽

Wind Power Forecasting ◽

Proposed Model ◽

Power Forecasting

With the high wind penetration in the power system, accurate and reliable probabilistic wind power forecasting has become even more significant for the reliability of the power system. In this paper, an instance-based transfer learning method combined with gradient boosting decision trees (GBDT) is proposed to develop a wind power quantile regression model. Based on the spatial cross-correlation characteristic of wind power generations in different zones, the proposed model utilizes wind power generations in correlated zones as the source problems of instance-based transfer learning. By incorporating the training data of source problems into the training process, the proposed model successfully reduces the prediction error of wind power generation in the target zone. To prevent negative transfer, this paper proposes a method that properly assigns weights to data from different source problems in the training process, whereby the weights of related source problems are increased, while those of unrelated ones are reduced. Case studies are developed based on the dataset from the Global Energy Forecasting Competition 2014 (GEFCom2014). The results confirm that the proposed model successfully improves the prediction accuracy compared to GBDT-based benchmark models, especially when the target problem has a small training set while resourceful source problems are available.

Download Full-text

A XGBoost Model with Weather Similarity Analysis and Feature Engineering for Short-Term Wind Power Forecasting

Applied Sciences ◽

10.3390/app9153019 ◽

2019 ◽

Vol 9 (15) ◽

pp. 3019 ◽

Cited By ~ 5

Author(s):

Huan Zheng ◽

Yanghui Wu

Keyword(s):

Wind Power ◽

Gradient Boosting ◽

Support Vector ◽

Similarity Analysis ◽

Feature Engineering ◽

Short Term ◽

Wind Power Forecasting ◽

Proposed Model ◽

Extreme Gradient Boosting ◽

Power Forecasting

Large-scale wind power access may cause a series of safety and stability problems. Wind power forecasting (WPF) is beneficial to dispatch in advance. In this paper, a new extreme gradient boosting (XGBoost) model with weather similarity analysis and feature engineering is proposed for short-term wind power forecasting. Based on the similarity among historical days’ weather, k-means clustering algorithm is used to divide the samples into several categories. Additionally, we also create some time features and drop unimportant features through feature engineering. For each category, we make predictions using XGBoost. The results of the proposed model are compared with the back propagation neural network (BPNN) and classification and regression tree (CART), random forests (RF), support vector regression (SVR), and a single XGBoost model. It is shown that the proposed model produces the highest forecasting accuracy among all these models.

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