Download Free Probabilistic Wind Power Ramp Forecasting Based On A Scenario Generation Method Preprint Book in PDF and EPUB Free Download. You can read online Probabilistic Wind Power Ramp Forecasting Based On A Scenario Generation Method Preprint and write the review.

Wind power ramps (WPRs) are particularly important in the management and dispatch of wind power, and they are currently drawing the attention of balancing authorities. With the aim to reduce the impact of WPRs for power system operations, this paper develops a probabilistic ramp forecasting method based on a large number of simulated scenarios. An ensemble machine learning technique is first adopted to forecast the basic wind power forecasting scenario and calculate the historical forecasting errors. A continuous Gaussian mixture model (GMM) is used to fit the probability distribution function (PDF) of forecasting errors. The cumulative distribution function (CDF) is analytically deduced. The inverse transform method based on Monte Carlo sampling and the CDF is used to generate a massive number of forecasting error scenarios. An optimized swinging door algorithm is adopted to extract all the WPRs from the complete set of wind power forecasting scenarios. The probabilistic forecasting results of ramp duration and start time are generated based on all scenarios. Numerical simulations on publicly available wind power data show that within a predefined tolerance level, the developed probabilistic wind power ramp forecasting method is able to predict WPRs with a high level of sharpness and accuracy.
This SpringerBrief presents spatio-temporal data analytics for wind energy integration using stochastic modeling and optimization methods. It explores techniques for efficiently integrating renewable energy generation into bulk power grids. The operational challenges of wind, and its variability are carefully examined. A spatio-temporal analysis approach enables the authors to develop Markov-chain-based short-term forecasts of wind farm power generation. To deal with the wind ramp dynamics, a support vector machine enhanced Markov model is introduced. The stochastic optimization of economic dispatch (ED) and interruptible load management are investigated as well. Spatio-Temporal Data Analytics for Wind Energy Integration is valuable for researchers and professionals working towards renewable energy integration. Advanced-level students studying electrical, computer and energy engineering should also find the content useful.
The goal of research in this dissertation is to bring more wind resources into the power grid by mitigating the uncertainty of the current wind power, by developing a new algorithm to respond to the fluctuation of the future wind power, and by building additional transmission lines to bring more wind resources from a remote area to the load center. First, in order to overcome the wind power uncertainty, the probabilistic and ensemble wind power forecasting is proposed to increase the forecasting accuracy and to deliver the probability density function of the uncertainty. Accurate wind power forecasting reduces the amounts and cost of ancillary services (AS). As the mismatch between the bid and actual amount of delivered energy decreases, the imbalance between supply and demand also decreases. If the forecasting ahead is increased up to 24 hours, accurate wind power forecasting can also help wind farm owners bid the exact amount of wind power in the day ahead (DA) market. Furthermore, wind power owners can use the parametric probabilistic density of error distributions for hedging the price risk and building a better offer curve. Second, a novel algorithm to generate many wind power scenarios as a function of installed capacity of wind power is proposed based on an analysis of the power spectral density of wind power. Scenarios can be used to simulate the power system to estimate the required amount of AS to respond to the fluctuation of future wind power as the installed capacity of wind power increases. Scenarios have statistical characteristics of the future wind power that are regressed as a function of the installed capacity of wind power from the statistical characteristics of the current wind power. This algorithm can generate many possible scenarios to simulate the power system in many different situations. Third, optimal transmission expansion by simulating the power system with the multiple load and wind power scenarios in different locations is planned to prepare the preliminary result to bring more wind resources in remote areas to the load center in Texas. In this process, the geographical smoothing effects of wind power and the stochastic correlation structure between the load and wind power are considered. Furthermore, the generalized dynamic factor model (GDFM) is used to synthesize load and wind power scenarios to keep their correlation structure. The premise of the GDFM is that a few factors can drive the correlated movements of load and wind power simultaneously, so the scenario generation process is parsimonious.
This thesis describes performance measures and ensemble architectures for deterministic and probabilistic forecasts using the application example of wind power forecasting and proposes a novel scheme for the situation-dependent aggregation of forecasting models. For performance measures, error scores for deterministic as well as probabilistic forecasts are compared, and their characteristics are shown in detail. For the evaluation of deterministic forecasts, a categorization by basic error measure and normalization technique is introduced that simplifies the process of choosing an appropriate error measure for certain forecasting tasks. Furthermore, a scheme for the common evaluation of different forms of probabilistic forecasts is proposed. Based on the analysis of the error scores, a novel hierarchical aggregation technique for both deterministic and probabilistic forecasting models is proposed that dynamically weights individual forecasts using multiple weighting factors such as weather situation and lead time dependent weighting. In the experimental evaluation it is shown that the forecasting quality of the proposed technique is able to outperform other state of the art forecasting models and ensembles.
Wind power forecasting (WPF) provides important inputs to power system operators and electricity market participants. It is therefore not surprising that WPF has attracted increasing interest within the electric power industry. In this report, we document our research on improving statistical WPF algorithms for point, uncertainty, and ramp forecasting. Below, we provide a brief introduction to the research presented in the following chapters. For a detailed overview of the state-of-the-art in wind power forecasting, we refer to [1]. Our related work on the application of WPF in operational decisions is documented in [2]. Point forecasts of wind power are highly dependent on the training criteria used in the statistical algorithms that are used to convert weather forecasts and observational data to a power forecast. In Chapter 2, we explore the application of information theoretic learning (ITL) as opposed to the classical minimum square error (MSE) criterion for point forecasting. In contrast to the MSE criterion, ITL criteria do not assume a Gaussian distribution of the forecasting errors. We investigate to what extent ITL criteria yield better results. In addition, we analyze time-adaptive training algorithms and how they enable WPF algorithms to cope with non-stationary data and, thus, to adapt to new situations without requiring additional offline training of the model. We test the new point forecasting algorithms on two wind farms located in the U.S. Midwest. Although there have been advancements in deterministic WPF, a single-valued forecast cannot provide information on the dispersion of observations around the predicted value. We argue that it is essential to generate, together with (or as an alternative to) point forecasts, a representation of the wind power uncertainty. Wind power uncertainty representation can take the form of probabilistic forecasts (e.g., probability density function, quantiles), risk indices (e.g., prediction risk index) or scenarios (with spatial and/or temporal dependence). Statistical approaches to uncertainty forecasting basically consist of estimating the uncertainty based on observed forecasting errors. Quantile regression (QR) is currently a commonly used approach in uncertainty forecasting. In Chapter 3, we propose new statistical approaches to the uncertainty estimation problem by employing kernel density forecast (KDF) methods. We use two estimators in both offline and time-adaptive modes, namely, the Nadaraya-Watson (NW) and Quantilecopula (QC) estimators. We conduct detailed tests of the new approaches using QR as a benchmark. One of the major issues in wind power generation are sudden and large changes of wind power output over a short period of time, namely ramping events. In Chapter 4, we perform a comparative study of existing definitions and methodologies for ramp forecasting. We also introduce a new probabilistic method for ramp event detection. The method starts with a stochastic algorithm that generates wind power scenarios, which are passed through a high-pass filter for ramp detection and estimation of the likelihood of ramp events to happen. The report is organized as follows: Chapter 2 presents the results of the application of ITL training criteria to deterministic WPF; Chapter 3 reports the study on probabilistic WPF, including new contributions to wind power uncertainty forecasting; Chapter 4 presents a new method to predict and visualize ramp events, comparing it with state-of-the-art methodologies; Chapter 5 briefly summarizes the main findings and contributions of this report.
The increase of wind penetration into electric power system creates challenges to power grid management due to the variable nature of wind. Unlike conventional power plants, such as thermal, gas or hydro-based plants, wind power generation is not controllable. For example, days of calm weather may suddenly be followed by gusty winds associated with a storm or a front. The current wind power forecasting methodologies, which combine Numerical Weather Prediction (NWP) models and mathematical methods, have been well established during the last decade. However, this forecasting methodology has demonstrated a limited ability to forecast wind ramp events, which are defined as sudden, large changes in wind production. In this study different strategies are developed to improve wind ramp prediction and to provide additional probabilistic information of wind ramp occurrences to end users. First, a methodology of separate wind power predictions based on different weather regimes is presented. Second, an independent wind ramp prediction system is proposed to complement conventional ramp predictions. This system integrates information about the pressure gradient that is extracted by applying Gabor filters to two-dimensional pressure grids. Third, the temporal uncertainty of wind ramp occurrences is addressed using power scenarios generated from quantile forecasts of wind power. The probability of a wind ramp occurrence conditional to the number of scenarios predicting the ramp within certain time intervals is estimated using a logistic regression technique. The proposed strategies were tested on four wind farms located in southern Alberta, Canada, and their performance is discussed.
Probabilistic wind power forecasts that quantify the uncertainty in wind output have the potential to aid in the economic grid integration of wind power at large penetration levels. In this paper, a novel probabilistic wind forecasting approach based on pinball loss optimization is proposed, in conjunction with a multi-model machine learning based ensemble deterministic forecasting framework. By assuming the pointforecasted value as the mean at each point, one unknown parameter (i.e., standard deviation) of a predictive distribution at each forecasting point is determined by minimizing the pinball loss. A surrogate model is developed to represent the unknown distribution parameter as a function of deterministic forecasts. This surrogate model can be used together with deterministic forecasts to predict the unknown distribution parameter and thereby generate probabilistic forecasts. Numerical results of case studies show that the proposed method has improved the pinball loss by up to 35% compared to a baseline quantile regression forecasting model.