A Proposed Forecasting System for Wind Power in Smart Grids

Accurate short-term wind power forecasting has important significance to safety, stability and economy of power system dispatching and also it is a difficult problem in practical engineering application. In this paper, by use of the data of numerical weather forecast, such as wind speed, wind direction, temperature, relative humidity and pressure of atmosphere, a short-term wind power forecasting system based on BP neural network has been developed. For verifying the feasibility of the system, some experiments have been were carried out. The results show that the system is capable of predicting accurately the wind power of future 24 hours and the forecasting accuracy of 85.6% is obtained. The work of this paper has important engineering directive significance to the similar wind power forecasting system.

Download Full-text

Distributed Demand Side Management with Stochastic Wind Power Forecasting

10.36227/techrxiv.13360196 ◽

2020 ◽

Author(s):

Paolo Scarabaggio ◽

Sergio Grammatico ◽

Raffaele Carli ◽

Mariagrazia Dotoli

Keyword(s):

Wind Speed ◽

Wind Power ◽

Smart Grids ◽

Demand Side Management ◽

Expected Value ◽

Noncooperative Game ◽

Theory Approach ◽

Demand Side ◽

Wind Power Forecasting ◽

Power Forecasting

In this paper, we propose a distributed demand side management (DSM) approach for smart grids taking into account uncertainty in wind power forecasting. The smart grid model comprehends traditional users as well as active users (prosumers). Through a rolling-horizon approach, prosumers participate in a DSM program, aiming at minimizing their cost in the presence of uncertain wind power generation by a game theory approach.<br>We assume that each user selfishly formulates its grid optimization problem as a noncooperative game.<br>The core challenge in this paper is defining an approach to cope with the uncertainty in wind power availability. <br>We tackle this issue from two different sides: by employing the expected value to define a deterministic counterpart for the problem and by adopting a stochastic approximated framework.<br>In the latter case, we employ the sample average approximation technique, whose results are based on a probability density function (PDF) for the wind speed forecasts. We improve the PDF by using historical wind speed data, and by employing a control index that takes into account the weather condition stability.<br><div>Numerical simulations on a real dataset show that the proposed stochastic strategy generates lower individual costs compared to the standard expected value approach.</div><div><br></div><div>Preprint of paper submitted to IEEE Transactions on Control Systems Technology<br></div>

Download Full-text

Probabilistic forecasting of wind power production losses in cold climates: a case study

Wind Energy Science ◽

10.5194/wes-3-667-2018 ◽

2018 ◽

Vol 3 (2) ◽

pp. 667-680 ◽

Cited By ~ 7

Author(s):

Jennie Molinder ◽

Heiner Körnich ◽

Esbjörn Olsson ◽

Hans Bergström ◽

Anna Sjöblom

Keyword(s):

Wind Power ◽

Energy Production ◽

Spatial Representation ◽

Forecast Skill ◽

Cold Climates ◽

Probabilistic Forecasting ◽

Probabilistic Forecasts ◽

Forecasting System ◽

Production Losses

Abstract. The problem of icing on wind turbines in cold climates is addressed using probabilistic forecasting to improve next-day forecasts of icing and related production losses. A case study of probabilistic forecasts was generated for a 2-week period. Uncertainties in initial and boundary conditions are represented with an ensemble forecasting system, while uncertainties in the spatial representation are included with a neighbourhood method. Using probabilistic forecasting instead of one single forecast was shown to improve the forecast skill of the ice-related production loss forecasts and hence the icing forecasts. The spread of the multiple forecasts can be used as an estimate of the forecast uncertainty and of the likelihood for icing and severe production losses. Best results, both in terms of forecast skill and forecasted uncertainty, were achieved using both the ensemble forecast and the neighbourhood method combined. This demonstrates that the application of probabilistic forecasting for wind power in cold climates can be valuable when planning next-day energy production, in the usage of de-icing systems and for site safety.

Download Full-text

Probabilistic forecasting of wind power production losses in cold climates: A case study

10.5194/wes-2017-28 ◽

2017 ◽

Cited By ~ 1

Author(s):

Jennie P. Söderman ◽

Heiner Körnich ◽

Esbjörn Olsson ◽

Hans Bergström ◽

Anna Sjöblom

Keyword(s):

Wind Power ◽

Energy Production ◽

Cold Climate ◽

Forecast Skill ◽

Cold Climates ◽

Probabilistic Forecasting ◽

Probabilistic Forecasts ◽

Forecasting System ◽

Production Losses

Abstract. The problem of icing on wind turbines in cold climates is addressed using probabilistic forecasting to improve next- day forecasts of icing and related production losses. A case study of probabilistic forecasts was generated for a two- week period. Uncertainties in initial and boundary conditions are represented with an ensemble forecasting system, while uncertainties in the spatial representation are included with a neighbourhood method. Using probabilistic forecasting instead of one single forecast was shown to improve the forecast skill of the ice-related production loss forecasts and hence the icing forecasts. The spread of the multiple forecasts can be used as an estimate of the forecast uncertainty and of the likelihood for icing and severe production losses. Best results, both in terms of forecast skill and forecasted uncertainty, were achieved using both the ensemble forecast and the neighbourhood method combined. This demonstrates that the application of probabilistic forecasting for wind power in cold climate can be valuable when planning next-day energy production, in the usage of de-icing systems, and for site safety.

Download Full-text

A Short-Term Ensemble Wind Speed Forecasting System for Wind Power Applications

Journal of Applied Meteorology and Climatology ◽

10.1175/jamc-d-11-0122.1 ◽

2012 ◽

Vol 51 (10) ◽

pp. 1763-1774 ◽

Cited By ~ 16

Author(s):

Justin J. Traiteur ◽

David J. Callicutt ◽

Maxwell Smith ◽

Somnath Baidya Roy

Keyword(s):

Wind Speed ◽

Wind Power ◽

Statistical Models ◽

Bayesian Model Averaging ◽

Numerical Models ◽

Weather Prediction ◽

Environmental Stability ◽

Short Term ◽

Wind Speed Forecasting ◽

Forecasting System

AbstractThis study develops an adaptive, blended forecasting system to provide accurate wind speed forecasts 1 h ahead of time for wind power applications. The system consists of an ensemble of 21 forecasts with different configurations of the Weather Research and Forecasting Single Column Model and persistence, autoregressive, and autoregressive moving-average models. The ensemble is calibrated against observations for a 6-month period (January–June 2006) at a potential wind-farm site in Illinois using the Bayesian model averaging technique. The forecasting system is evaluated against observations for the July 2006–December 2007 period at the same site. The calibrated ensemble forecasts significantly outperform the forecasts from the uncalibrated ensemble as well the time series models under all environmental stability conditions. This forecasting system is computationally more efficient than traditional numerical weather prediction models and can generate a calibrated forecast, including model runs and calibration, in approximately 1 min. Currently, hour-ahead wind speed forecasts are almost exclusively produced using statistical models. However, numerical models have several distinct advantages over statistical models including the potential to provide turbulence forecasts. Hence, there is an urgent need to explore the role of numerical models in short-term wind speed forecasting. This work is a step in that direction and is likely to trigger a debate within the wind speed forecasting community.

Download Full-text