Wind power ramp events classification and forecasting: A data mining approach

Zareipour, Hamidreza; Huang, Dongliang; Rosehart, William

doi:10.1109/pes.2011.6039625

Cited by 67 publications

(45 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…[36] gives WPRE prediction in a probabilistic way. In [70], an SVM for classification is used to forecast WPREs, after grouping the ramp events into different classes. The reported results show a good WPRE prediction with the SVM methodology.…”

Section: Statistical Approachesmentioning

confidence: 99%

Wind Power Ramp Events Prediction with Hybrid Machine Learning Regression Techniques and Reanalysis Data

et al. 2017

View full text Add to dashboard Cite

Wind Power Ramp Events (WPREs) are large fluctuations of wind power in a short time interval, which lead to strong, undesirable variations in the electric power produced by a wind farm. Its accurate prediction is important in the effort of efficiently integrating wind energy in the electric system, without affecting considerably its stability, robustness and resilience. In this paper, we tackle the problem of predicting WPREs by applying Machine Learning (ML) regression techniques. Our approach consists of using variables from atmospheric reanalysis data as predictive inputs for the learning machine, which opens the possibility of hybridizing numerical-physical weather models with ML techniques for WPREs prediction in real systems. Specifically, we have explored the feasibility of a number of state-of-the-art ML regression techniques, such as support vector regression, artificial neural networks (multi-layer perceptrons and extreme learning machines) and Gaussian processes to solve the problem. Furthermore, the ERA-Interim reanalysis from the European Center for Medium-Range Weather Forecasts is the one used in this paper because of its accuracy and high resolution (in both spatial and temporal domains). Aiming at validating the feasibility of our predicting approach, we have carried out an extensive experimental work using real data from three wind farms in Spain, discussing the performance of the different ML regression tested in this wind power ramp event prediction problem.

show abstract

Section: Statistical Approachesmentioning

confidence: 99%

Wind Power Ramp Events Prediction with Hybrid Machine Learning Regression Techniques and Reanalysis Data

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Documents [14,15] introduce the basic concepts of climbing events and their relationship with extreme weather conditions. A new method of predicting climbing events based on probability is proposed in [16], but the accuracy is low and it's not acceptable for practice.…”

Section: The Climbing Control Abilitymentioning

confidence: 99%

The Problems and Key Technologies of Large Scale Wind Power Into the Power Grid

Qin¹,

Wen²

2017

dtetr

View full text Add to dashboard Cite

Abstract. This paper summarizes a series of problems brought by the large-scale wind power connecting to the grid: effects on power quality, off-grid accidents, bring great difficulties to the power dispatching and the huge increase to the cost. Based on the problems above and the latest researches, this paper enumerates some key technologies of large-scale wind power into the grid, including the LVRT technology, on-line monitoring, evaluation of operation state, climbing control ability and energy storage technology etc.

show abstract

“…Based on the definition of ramp events, R Sevlian and R Rajagopal proposed an effective method for the detection of ramp events in [8] , which can detect the possible existence of ramp events by wind power data. On the basis of the detection of ramp events, N Cutler，M Kay，K Jacka，et al used the K-means method to classify the ramp events [9], and H Zareipour，D L Huang，W Rosehart used support vector machine model (SVM) to train the classifier in [10].…”

Section: Introductionmentioning

confidence: 99%

Probabilistic model of Wind Power Ramp Events Based On Moving Ratio Analysis

Liu¹,

Wang²

2016

Proceedings of the 2016 5th International Conference on Energy and Environmental Protection (ICEEP 2016)

View full text Add to dashboard Cite

Abstract. Description of probability distribution characteristics of wind power ramp events is always a challenge in grid-connected wind power operation analysis. In this paper, a moving ratio based approach of wind power ramp events is introduced and an probability model is described for the wind ramp events. The proposed model is useful to estimate the relationship between power ramp events and the variability of the wind power. The proposed model is able to satisfactorily approximate the actual distribution of wind power ramp events . It is shown that the linear difference based ramp distribution can be calculated using the proposed moving ratio based approach. The proposed model can be an effective tool in planning for wind power ramp control.

show abstract

Wind power ramp events classification and forecasting: A data mining approach

Cited by 67 publications

References 10 publications

Wind Power Ramp Events Prediction with Hybrid Machine Learning Regression Techniques and Reanalysis Data

Wind Power Ramp Events Prediction with Hybrid Machine Learning Regression Techniques and Reanalysis Data

The Problems and Key Technologies of Large Scale Wind Power Into the Power Grid

Probabilistic model of Wind Power Ramp Events Based On Moving Ratio Analysis

Contact Info

Product

Resources

About