Wind Power Ramp Event Forecasting Using a Stochastic Scenario Generation Method

Cui, Mingjian; Ke, Deping; Sun, Yang; Gan, Deqiang; Zhang, Jie; Hodge, Bri-Mathias

doi:10.1109/tste.2014.2386870

Cited by 151 publications

(68 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [22], a Radial Basis Function Neural Networks (RBFNN) is coupled with particle swarm optimization (PSO) algorithm to generate scenarios with input from numerical weather predictions (NWP). In [23], [24], neural network models are trained to output either timeseries power generation or occurrence probability. Compared to copula or time series methods, these machine learning based algorithms may potentially better capture the nonlinear dynamics of renewable generation processes, but all of these depend on careful selection of input features and is nontrivial to tune and use in practice.…”

Section: A Literature Reviewmentioning

confidence: 99%

Model-Free Renewable Scenario Generation Using Generative Adversarial Networks

Chen

Wang

Kirschen

et al. 2019

2019 IEEE Power &Amp; Energy Society General Meeting (PESGM)

View full text Add to dashboard Cite

Scenario generation is an important step in the operation and planning of power systems with high renewable penetrations. In this work, we proposed a data-driven approach for scenario generation using generative adversarial networks, which is based on two interconnected deep neural networks. Compared with existing methods based on probabilistic models that are often hard to scale or sample from, our method is datadriven, and captures renewable energy production patterns in both temporal and spatial dimensions for a large number of correlated resources. For validation, we use wind and solar timesseries data from NREL integration data sets. We demonstrate that the proposed method is able to generate realistic wind and photovoltaic power profiles with full diversity of behaviors. We also illustrate how to generate scenarios based on different conditions of interest by using labeled data during training. For example, scenarios can be conditioned on weather events (e.g. high wind day, intense ramp events or large forecasts errors) or time of the year (e,g. solar generation for a day in July). Because of the feedforward nature of the neural networks, scenarios can be generated extremely efficiently without sophisticated sampling techniques.

show abstract

Section: A Literature Reviewmentioning

confidence: 99%

Model-Free Renewable Scenario Generation Using Generative Adversarial Networks

Chen

Wang

Kirschen

et al. 2019

2019 IEEE Power &Amp; Energy Society General Meeting (PESGM)

View full text Add to dashboard Cite

show abstract

“…Ferreira et al [15] generated statistical scenarios by using a Monte Carlo sampling process given a probability density function (PDF) for the wind power forecasts and then output a histogram of the probability of having a ramp event above a certain magnitude for each prediction horizon. Cui et al [16] derived the probabilistic distribution of ramps using stochastical scenarios of wind power generation, which were generated by an NN model trained using cumulative density function (CDF)-and auto-correlation function (ACF)-based objective functions. A thorough review of ramp forecasting can be found in [6,17].…”

Section: Related Workmentioning

confidence: 99%

Improving the prediction of wind power ramps using texture extraction techniques applied to atmospheric pressure fields

Musilek

Lozowski

2017

Int J Data Sci Anal

View full text Add to dashboard Cite

Much recent research in wind power forecasting has been focused on predicting large, sudden changes in wind power output, called wind ramps. State-of-the-art wind ramp prediction methods estimate future wind ramps from forecast power time series. We suggest that, by analyzing the weather associated with wind ramps, their forecasting can be improved. In particular, we propose a new method for wind ramp forecasting based on the analysis of forecast atmospheric pressure fields. Feature vectors relating to the pressure gradient are extracted from the pressure fields using an image texture extraction technique, called Gabor filtering. Numerical experiments show that these Gabor feature vectors are well correlated with power generation. They are used as inputs to a new wind power forecasting model. Compared with a basic state-of-the-art wind power forecasting model that does not use Gabor features as input, the proposed model exhibits better performance for power prediction, for two of the three wind farms chosen for this study. However, the ability of the model to forecast actual wind ramps is worse than that of the basic model, as measured by ramp capture rate and forecast accuracy. We also describe a second method to pre- Earth and Atmospheric Sciences, University of Alberta, Edmonton, Canada dict the magnitude of a sudden power change (wind ramp), using several input variables, in addition to Gabor features. Numerical experiments show that this second approach has better performance than the basic model, with respect to ramp capture rate and forecast accuracy. We suggest that it could be used operationally to supplement a current state-of-the-art ramp prediction model. We present an example of using this approach to provide a warning of a potential ramp.

show abstract

“…To encounter the uncertainties brought by the DRGs, various methods and optimization models have been proposed with different stochastic variables and constraints embedded, e.g. probabilistic load flow [11]- [13], scenario-based optimization [14]- [18], chance-constrained optimization [19]- [21], and robust optimization [22]- [33], to name a few. The two-stage stochastic programming is proposed in [15] and [16], and the uncertainties are described using a set of scenarios.…”

Section: Introductionmentioning

confidence: 99%

Data-Adaptive Robust Optimization Method for the Economic Dispatch of Active Distribution Networks

Zhang

Wen

et al. 2019

IEEE Trans. Smart Grid

View full text Add to dashboard Cite

Due to the restricted mathematical description of the uncertainty set, the current two-stage robust optimization is usually over-conservative which has drawn concerns from the power system operators. This paper proposes a novel dataadaptive robust optimization method for the economic dispatch of active distribution network with renewables. The scenariogeneration method and the two-stage robust optimization are combined in the proposed method. To reduce the conservativeness, a few extreme scenarios selected from the historical data are used to replace the conventional uncertainty set. The proposed extremescenario selection algorithm takes advantage of considering the correlations and can be adaptive to different historical data sets. A theoretical proof is given that the constraints will be satisfied under all the possible scenarios if they hold in the selected extreme scenarios, which guarantees the robustness of the decision. Numerical results demonstrate that the proposed data-adaptive robust optimization algorithm with the selected uncertainty set is less conservative but equally as robust as the existing two-stage robust optimization approaches. This leads to the improved economy of the decision with uncompromised security.

show abstract

Wind Power Ramp Event Forecasting Using a Stochastic Scenario Generation Method

Cited by 151 publications

References 25 publications

Model-Free Renewable Scenario Generation Using Generative Adversarial Networks

Model-Free Renewable Scenario Generation Using Generative Adversarial Networks

Improving the prediction of wind power ramps using texture extraction techniques applied to atmospheric pressure fields

Data-Adaptive Robust Optimization Method for the Economic Dispatch of Active Distribution Networks

Contact Info

Product

Resources

About