Very-Short-Term Probabilistic Wind Power Forecasts by Sparse Vector Autoregression

Accurate forecasting of wind farm power generation is essential for successful operation and management of wind farms and to minimize risks associated with their integration into energy systems. However, due to the inherent wind intermittency, wind power forecasts are highly prone to error and often far from being perfect. The purpose of this paper is to develop statistical methods for quantifying uncertainties associated with wind power generation forecasts. Prediction intervals (PIs) with a prescribed confidence level are constructed using the delta and bootstrap methods for neural network forecasts. The moving block bootstrap method is applied to preserve the correlation structure in wind power observations. The effectiveness and efficiency of these two methods for uncertainty quantification is examined using two month datasets taken from a wind farm in Australia. It is demonstrated that while all constructed PIs are theoretically valid, bootstrap PIs are more informative than delta PIs, and are therefore more useful for decision-making.

Very short-term forecasting of wind power generation using hybrid deep learning model

Extracting energy from renewable sources such as wind energy is widely investigated in the past decades to mitigate the global energy crisis and environmental pollution. For a wind farm that converts wind energy into electricity power, a real-time prediction system of the output power is significant. In this paper, a prediction system is developed with a method of combining statistical model and physical model. In this system, the inlet condition of the wind farm is forecasted by the auto regressive model. The flow field is computed by the Reynolds average Navier-stokes simulation in the computational fluid dynamics model. The wake flow is calculated by the particle model, which can be used over complex terrain. Taking also the terrain condition, the property of turbines and wake flow model into account, the output power of the wind farm can be further predicted. The proposed prediction system is tested by the data from Wattle Point Wind Farm in Australia. Through the data post-processing, the error of the mean daily output power is less than 5%. The proposed system is effective for power output prediction of wind farm.

Probabilistic wind power forecasting for newly-built wind farms based on multi-task Gaussian process method

The development of wind energy in Australia has been subject to ongoing public debate and has been characterised by concerns over the health impacts of wind turbines. Using discursive psychology, we examine 'wind turbine syndrome' as a contested illness and analyse how people build and undermine divergent arguments about wind-farm health effects. This article explores two facets of the dispute. First, we consider how participants construct 'facts' about the health effects of wind farms. We examine rhetorical resources used to construct wind farms as harmful or benign. Second, we examine the local negotiation of the legitimacy of health complaints. In the research interviews examined, even though interviewees treat those who report experiencing symptoms from wind farms as having primary rights to narrate their own experience, this epistemic primacy does not extend to the ability to 'correctly' identify symptoms' cause. As a result, the legitimacy of health complaints is undermined. Wind turbine syndrome is an example of a contested illness that is politically controversial. We show how stake, interest and legitimacy are particularly relevant for participants' competing descriptions about the 'facts' of wind turbine health effects.

This paper makes use of the idea of prediction intervals (PIs) to capture the uncertainty associated with wind power generation in power systems. Since the forecasting errors cannot be appropriately modeled using distribution probability functions, here we employ a powerful nonparametric approach called lower upper bound estimation (LUBE) method to construct the PIs. The proposed LUBE method uses a new framework based on a combination of PIs to overcome the performance instability of neural networks (NNs) used in the LUBE method. Also, a new fuzzy-based cost function is proposed with the purpose of having more freedom and flexibility in adjusting NN parameters used for construction of PIs. In comparison with the other cost functions in the literature, this new formulation allows the decision-makers to apply their preferences for satisfying the PI coverage probability and PI normalized average width individually. As the optimization tool, bat algorithm with a new modification is introduced to solve the problem. The feasibility and satisfying performance of the proposed method are examined using datasets taken from different wind farms in Australia.

A multi-criteria decision-making framework for site selection of offshore wind farms in Australia

Bayesian bootstrapping in real-time probabilistic photovoltaic power forecasting

Very-short-term wind power prediction is of great significance for the safe and stable operation of power system. As a well-known time series model, vector autoregressive (VAR) model is very suitable for very-short-term forecasting, and it can consider the temporal and spatial correlation among multiple wind farms to improve the forecasting accuracy. However, when there are a large number of wind farms, VAR model is prone to over-fitting. Slow calculation speed is also the problem of VAR model. This paper adds regularization terms in estimating coefficients to obtain a sparse coefficient matrix, which helps to avoid over-fitting. Online VAR model is used to improve the calculation speed, and a specific improved online VAR method is proposed for forecasting wind power output from new-built wind farms. This method is tested in a specific case, and the prediction accuracy and calculation speed are better than the traditional VAR model. In addition, the improved online VAR method can accurately predict wind power output of new-built wind farms with little historical data.

The deployment of smart grids and renewable energy dispatch centers motivates the development of forecasting techniques that take advantage of near real‐time measurements collected from geographically distributed sensors. This paper describes a forecasting methodology that explores a set of different sparse structures for the vector autoregression (VAR) model using the least absolute shrinkage and selection operator (LASSO) framework. The alternating direction method of multipliers is applied to fit the different LASSO‐VAR variants and create a scalable forecasting method supported by parallel computing and fast convergence, which can be used by system operators and renewable power plant operators. A test case with 66 wind power plants is used to show the improvement in forecasting skill from exploring distributed sparse structures. The proposed solution outperformed the conventional autoregressive and vector autoregressive models, as well as a sparse VAR model from the state of the art. Copyright © 2016 John Wiley & Sons, Ltd.

Providing accurate forecasts for the future power generation of renewable energy power plants is critical for the power grid operation and related tasks. Probabilistic forecasts provide additional information in comparison to conventional point forecasts and can be used to retain optimal decision-making performance under uncertain future conditions. In this article, we present a hierarchical ensemble technique that combines multiple probabilistic forecasting techniques and multiple weather models (WM). In a first step, multiple probabilistic forecasting techniques create predictions on each weather model individually. Thereafter, this set of probabilistic forecasts from each WM is aggregated to an overall refined prediction using a novel dynamic weighting technique which we call gradual coopetitive soft gating. The proposed combination technique introduces a weather situation-adaptive and lead-time dependent weighting that better exploits the advantages of single predictive models in the overall ensemble. We compare the proposed method to other state of the art probabilistic forecasting methods and weather ensemble methods on 37 data sets of wind farms with multi-model weather forecasts. The proposed technique is able to achieve statistically significant performance improvements compared to other techniques.

K-nearest neighbors and a kernel density estimator for GEFCom2014 probabilistic wind power forecasting

This paper proposes a privacy-preserving framework that couples probabilistic wind power forecasting with decentralized anomaly detection in complex power networks. We first design an adaptive federated learning (FL) scheme to produce probabilistic forecasts for multiple geographically distributed wind farms while keeping their raw data local. In this scheme, an artificial neural network with quantile regression is trained collaboratively across sites to provide calibrated prediction intervals for wind power outputs. These forecasts are then embedded into an alternating direction method of multipliers (ADMM)-based load-side dispatch and anomaly detection model for decentralized power systems with plug-and-play industrial users. Each monitoring node uses local measurements and neighbor communication to solve a distributed economic dispatch problem, detect abnormal load behaviors, and maintain network consistency without a central coordinator. Experiments on the GEFCom 2014 wind power dataset show that the proposed FL-based probabilistic forecasting method outperforms persistence, local training, and standard FL in RMSE and MAE across multiple horizons. Simulations on IEEE 14-bus and 30-bus systems further verify fast convergence, accurate anomaly localization, and robust operation, indicating the effectiveness of the integrated forecasting–dispatch framework for smart industrial grids with high wind penetration.

The fluctuation and uncertainty of wind power generation bring severe challenges to secure and economic operation of power systems. Because wind power forecasting error is unavoidable, probabilistic forecasting becomes critical to accurately quantifying the uncertainty involved in traditional point forecasts of wind power and to providing meaningful information to conduct risk management in power system operation. This paper proposes a novel direct quantile regression approach to efficiently generate nonparametric probabilistic forecasting of wind power generation combining extreme learning machine and quantile regression. Quantiles with different proportions can be directly produced via an innovatively formulated linear programming optimization model, without dependency on point forecasts. Multistep probabilistic forecasting of 10-min wind power is newly carried out based on real wind farm data from Bornholm Island in Denmark. The superiority of the proposed approach is verified through comparisons with other well-established benchmarks. The proposed approach forms a new artificial neural network-based nonparametric forecasting framework for wind power with high efficiency, reliability, and flexibility, which can be beneficial to various decision-making activities in power systems.

Herding in Probabilistic Forecasts