Uncertainty quantification for wind farm power generation

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.

Stochastic models of road geometry and wind condition for vehicle energy management and control

Modeling and simulation is commonly used to improve vehicle performance, to optimize vehicle system design, and to reduce vehicle development time. Vehicle performances can be affected by environmental conditions and driver behavior factors, which are often uncertain and immeasurable. To incorporate the role of environmental conditions in the modeling and simulation of vehicle systems, both real and artificial data are used. Often, real data are unavailable or inadequate for extensive investigations. Hence, it is important to be able to construct artificial environmental data whose characteristics resemble those of the real data for modeling and simulation purposes. However, to produce credible vehicle simulation results, the simulated environment must be realistic and validated using accepted practices. This paper proposes a stochastic model that is capable of creating artificial environmental factors such as road geometry and wind conditions. In addition, road geometric design principles are employed to modify the created road data, making it consistent with the real-road geometry. Two sets of real-road geometry and wind condition data are employed to propose probability models. To justify the distribution goodness of fit, Pearson's chi-square and correlation statistics have been used. Finally, the stochastic models of road geometry and wind conditions (SMRWs) are developed to produce realistic road and wind data. SMRW can be used to predict vehicle performance, energy management, and control strategies over multiple driving cycles and to assist in developing fuel-efficient vehicles.

Wind farm power uncertainty quantification using a mean-variance estimation method

This paper proposes an innovative optimized parametric method for construction of prediction intervals (PIs) for uncertainty quantification. The mean-variance estimation (MVE) method employs two separate neural network (NN) models to estimate the mean and variance of targets. A new training method is developed in this study that adjusts parameters of NN models through minimization of a PI-based cost functions. A simulated annealing method is applied for minimization of the nonlinear non-differentiable cost function. The performance of the proposed method for PI construction is examined using monthly data sets taken from a wind farm in Australia. PIs for the wind farm power generation are constructed with five confidence levels between 50% and 90%. Demonstrated results indicate that valid PIs constructed using the optimized MVE method have a quality much better than the traditional MVE-based PIs.

The novel as social satire: 60 years later, the wind done gone and the limitations of fair use

The absence of the doctrine of fair use from Australian copyright law has been a bone of contention in Australia after the Australia-United States Free Trade Agreement (FTA). As the Australian government reformed the Copyright Act 1968 (Cth) in the aftermath of the FTA it eschewed the option of adopting fair use. Instead, Australia chose to incorporate a version of fair use into its existing fair dealing framework. Accordingly, the Copyright Amendment Act 2006 (Cth) inserted ss 41A and 103AA into the Copyright Act. These provisions provide that a fair dealing with a copyright protected work does not constitute an infringement if it is done for the purposes of parody or satire. These provisions codify part of the ratio of the United States Supreme Court in the seminal case of Campbell v Acuff Rose Music. However, the parameters of these new provisions are unexplored and the sparse nature of fair dealing jurisprudence means that the true meaning of the provisions is unclear. Moreover, two cases from the United States, SunTrust Bank v Houghton Mifflin and Salinger v Colting, underline just how important it is to have legal rules that protect literary ‘re-writes’. Both cases involved authors using an original novel to ‘write back’ to the original author and the broader culture. ‘Writing back’ or the ‘re-write’ has a firm basis in literature. It adds something invaluable to our culture. The key question is whether our legal landscape can allow it to flourish. This paper examines the interaction between fair use and literary re-writes.

Combined nonparametric prediction intervals for wind power generation

Prediction intervals (PIs) are a promising tool for quantification of uncertainties associated with point forecasts of wind power. However, construction of PIs using parametric methods is questionable, as forecast errors do not follow a standard distribution. This paper proposes a nonparametric method for construction of reliable PIs for neural network (NN) forecasts. A lower upper bound estimation (LUBE) method is adapted for construction of PIs for wind power generation. A new framework is proposed for synthesizing PIs generated using an ensemble of NN models in the LUBE method. This is done to guard against NN performance instability in generating reliable and informative PIs. A validation set is applied for short listing NNs based on the quality of PIs. Then, PIs constructed using filtered NNs are aggregated to obtain combined PIs. Performance of the proposed method is examined using data sets taken from two wind farms in Australia. Simulation results indicate that the quality of combined PIs is significantly superior to the quality of PIs constructed using NN models ranked and filtered by the validation set.

Prediction intervals for short-term wind farm power generation forecasts

Quantification of uncertainties associated with wind power generation forecasts is essential for optimal management of wind farms and their successful integration into power systems. This paper investigates two neural network-based methods for direct and rapid construction of prediction intervals (PIs) for short-term forecasting of power generation in wind farms. The lower upper bound estimation and bootstrap methods are used to quantify uncertainties associated with forecasts. The effectiveness and efficiency of these two general methods for uncertainty quantification is examined using twenty four month data from a wind farm in Australia. PIs with a confidence level of 90% are constructed for four forecasting horizons: five, ten, fifteen, and thirty minutes. Quantitative measures are applied for objective evaluation and unbiased comparison of PI quality. Demonstrated results indicate that reliable PIs can be constructed in a short time without resorting to complicate computational methods or models. Also quantitative comparison reveals that bootstrap PIs are more suitable for short prediction horizon, and lower upper bound estimation PIs are more appropriate for longer forecasting horizons.

An approach for wind power integration using demand side resources

Renewable energy resources, especially wind power, are expected to provide a considerable portion of the world energy requirements in the near future. Large-scale wind power penetration impacts the electricity industry in many aspects and raises a number of technical challenges for the electricity network. A day-ahead network-constrained market clearing formulation is proposed which considers demand side resources. The proposed approach can provide flexible load profile and reduce the need for ramp up/down services by the conventional generators. This method can potentially facilitate a large penetration of wind power by shifting the wind power generation from the off-peak periods to the high-peak hours. The validity of the proposed approach has been verified using the IEEE 30 bus and 57 bus test systems.