Day‐ahead wind power combination forecasting based on corrected numerical weather prediction and entropy method

Two-stage correction prediction of wind power based on numerical weather prediction wind speed superposition correction and improved clustering

Wind power ultra-short-term prediction method based on NWP wind speed correction and double clustering division of transitional weather process

Importance of thermal effects and sea surface roughness for offshore wind resource assessment

Ramp phenomena caused by abrupt changes in wind speed may confound the stable operation of correlated electrical power supply systems, yet accurate numerical predictions are challenging, as the wind is affected by complex interactions between large‐scale weather patterns and local geographical conditions. Further, optimal numerical weather prediction (NWP) methods and physics schemes vary as a function of weather patterns. The present study proposed a new real‐time wind power ramp forecast framework based on the flexible selection of optimal NWP models, which were derived via principal component analysis (PCA). The novelty of this analysis lies in that statistical methods were employed for NWP optimization, compared with their more conventional use during an NWP postprocessing. Here, a weather pattern was classified by PCA using outcomes from the global‐scale prediction models, and the optimum regional NWP system settings were acquired according to the weather patterns for further wind field dynamical downscaling. The performance of the developed prediction system was verified with wind power at wind turbine hub‐heights for three areas in eastern Japan, and the Critical Success Index (CSI) indicated an improvement of prediction accuracy over benchmark predictions by ≤0.184 for ramp‐up events and ≤0.127 for ramp‐down events (both observed in Tohoku area). Higher CSI values were consistently seen in three wind farm areas, indicative of the improvement in detection probability for actual ramp events compared with benchmark.

Wind power is currently the fastest growing power generation sector in the world-worldwide growth in wind power generation has been at 40% a year for the last 10 years. With this rapid growth of generation, new challenges are being introduced to power markets. Wind power is an intermittent source. For example, at a wind site in Tasmania, Australia, the average change in mean wind speed vectors over a 2.5- minute period is about 44.4% and the average change in maximum wind speeds over the same period is 55.0%. This demonstrates that the wind speed and its direction can change rapidly by a large amount over a very short period of time. Great variability in wind farm generation has both technical and commercial implications for the efficient planning and operation of power systems. Large wind farms tend to use large wind turbines. Large turbines have a significant rotational inertia when considering a short time frame. As a result, wind patterns shorter than 10 seconds usually have a negligible effect on the turbine output, and it is a standard practice in wind generation to neglect short-term gusts. However, trends over several minutes are of vital importance. In order to accommodate the increase in wind power generation, we need to change the way that wind generation is scheduled. Both utilities and electricity market operators will be required to forecast the wind generation to improve system performance. Wind generation will have to be bid into the market like any other generation. In order to handle these requirements, power system operators will need to have better wind forecasting models and tools. Forecasting is a vital part of business planning in today’s competitive environment, regardless of the field in which you work. To be ready for a situation before it occurs gives a distinct advantage over the competition. Wind prediction is complex due to the wind’s high degree of volatility and deviation. This means that standard time length definitions for power engineering do not strictly apply. The phrase shortterm in the case of wind forecasting, normally means periods from minutes out to half an hour while longterm forecasting means periods from several hours out to a few days. This difference between the two forecasting time periods is important when it comes to creating a prediction system. Three main classes of different techniques have been used for wind power forecasting. These are numerical weather prediction (NWP) methods, statistical methods, and methods based on applications of artificial neural networks (ANN) and adaptive neuro-fuzzy inference systems (ANFISs). TheNWP methods are dominant for forecasts over 10 hours ahead. However, statistical and ANN-based methods appear to be more accurate over shorter periods (minutes to a few hours). They are also much simpler than the NWP methods.

Deep learning approaches for bias correction in WRF model outputs for enhanced solar and wind energy estimation: A case study in East and West Malaysia

Analysis and application of forecasting models in wind power integration: A review of multi-step-ahead wind speed forecasting models

Many renewable energy resources, including wind energy, are uncertain and often unavailable when needed, with high variability and dependency on atmospheric and climatic conditions. Variability and uncertainty of wind energy follow those wind speed and occur at multiple timescales; that is, from seconds to minutes and then to hours. They also require movement of other resources to ensure the balance between generation and load. This requires an accurate wind speed prediction. However, most existing wind speed forecasting models are based on data that do not take into account the difference between day and night, which can limit the accuracy of wind speed forecasting. Therefore, to improve the prediction accuracy, this study proposes three scenarios for wind speed prediction: first, the prediction model does not take into account the difference between day and night. The second model uses only data recorded during the day, and the third model deals with data measured during the night only. A comparative analysis and comprehensive evaluation will be given at the end of this work to verify the proposed hypothesis. The recorded climate data and measured wind speed at AUMET station will be used in this study.

Wind energy is one of the best options for renewable energy such that, many researchers work on wind resource assessment, specifically using numerical weather prediction (NWP) model to forecast atmospheric behavior on a given domain. In addition, every combination of parameterization configuration influences wind assessment. At the same time, choosing the optimum vertical and horizontal resolution may affect its output and processing time. Regardless of available researches, most of them focuses on mid-latitude area but not in tropical areas like the Philippines. In the study, sensitivity analysis of Weather Research and Forecasting (WRF) model version 3.6.1 with 4 configurations was performed. The duration of the simulation was from January 1, 2014 00:00 to December 31, 2014 23:00. The parameters involved were horizontal resolution and vertical levels. Also, meteorological input data from NCEP Final Analysis with 1 degree resolution every 6 hours was used. For validation, wind speed measurements at 10 m height from NOAA Integrated Surface Database (ISD) were utilized, of which, the 3 weather stations are located in Manila, Science Garden and Ninoy Aquino International Airport (NAIA). The results show that increasing horizontal resolution from 4 km to 1 km have no significant increase to wind speed accuracy. In majority, higher vertical levels tend to increase its accuracy. Moreover, the model has higher accuracy during the rainy season and months of April and May. Overall, the model overestimated the observed wind speed but the diurnal cycle of wind speed follows all the simulation.

Transfer learning for short-term wind speed prediction with deep neural networks

Accurate prediction of surface wind speed and temperature is crucial for many sectors. Physical schemes in numerical weather prediction (NWP) and data-driven correction approaches have limitations due to uncertainties in parameterization and lack of robustness, respectively. This study introduces a physics-informed data model, PhyCorNet, which combines a deep learning–based physics emulator (PhyNet) and a subsequent correction network (CorNet). PhyNet imitates the revised surface-layer parameterization scheme [default option of the Weather Research and Forecasting (WRF) Model]. CorNet refines predictions by mitigating the difference between PhyNet and observations. PhyCorNet enables gridded forecasts despite the training data being point based. Therefore, PhyCorNet can be regarded as a rediagnostic scheme for surface wind speed at 10 m (WS10) and temperature at 2 m (T2). Compared to WRF, it reduced diagnostic root-mean-square errors in the 24-h forecasts for WS10 and T2 by 40% and 36%, respectively, across China, with unbiased forecasts at almost all sites. PhyCorNet addresses the oversmoothing prediction issue of other deep learning models by providing the ability to represent fine-scale features and perform well in statistically extreme samples. In grid cells without observations for training, PhyCorNet performed much better than WRF, demonstrating the zero-shot learning capability. This study implies that the emulator plus bias correction provided by PhyCorNet could be used as a simple but effective approach to improve the performance of other diagnostic quantities in NWP. Significance Statement We developed a new model called PhyCorNet to improve the surface wind speed and temperature forecasts. Existing weather forecast models have limitations in accurately predicting these variables. PhyCorNet first uses a neural network (PhyNet) to mimic an existing physics-based wind and temperature calculation method. Another neural network [correction network (CorNet)] improves the PhyNet forecasts by comparing them with observations. Across China, PhyCorNet reduced 24-h forecast errors for wind speed by 40% and temperature by 36% compared to a conventional model. It performed well under diverse conditions and overcame the oversmoothing issues faced by other machine learning models. Importantly, PhyCorNet outperformed traditional models in areas without historical observations. We suggest that this new framework can also be used to enhance the forecasts of other atmospheric variables.

Wind power generated by wind has non-schedule nature due to stochastic nature of meteorological variable. Hence energy business and control of wind power generation requires prediction of wind speed (WS) from few seconds to different time steps in advance. To deal with prediction shortcomings, various WS prediction methods have been used. Predictive data mining offers variety of methods for WS predictions where artificial neural network (ANN) is one of the reliable and accurate methods. It is observed from the result of this study that ANN gives better accuracy in comparison conventional model. The accuracy of WS prediction models is found to be dependent on input parameters and architecture type algorithms utilized. So the selection of most relevant input parameters is important research area in WS predicton field. The objective of the paper is twofold: first extensive review of ANN for wind power and WS prediction is carried out. Discussion and analysis of feature selection using Relief Algorithm (RA) in WS prediction are considered for different Indian sites. RA identify atmospheric pressure, solar radiation and relative humidity are relevant input variables. Based on relevant input variables Cascade ANN model is developed and prediction accuracy is evaluated. It is found that root mean square error (RMSE) for comparison between predicted and measured WS for training and testing wind speed are found to be 1.44 m/s and 1.49 m/s respectively. The developed cascade ANN model can be used to predict wind speed for sites where there are not WS measuring instruments are installed in India.

Precise wind power forecasting has several benefits, such as optimized peak regulation in power systems, enhanced safety analysis, and improved energy efficiency. Considering the substantial influence of meteorological data, such as wind speed and temperature, on wind power generation, and to minimize the impact of fluctuations and complexity of wind power data on the forecast results, this paper proposes a combined wind power forecasting method. This approach is based on the long short-term memory network (LSTM) model, using the maximal information coefficient (MIC) method to select numerical weather prediction (NWP) and combining the efficiency of complete EEMD with the adaptive noise (CEEMDAN) method for nonlinear signal decomposition. Results indicate that the accuracy of the forecast results is supported by NWP. Moreover, wind power data are decomposed by the CEEMDAN algorithm and converted into relatively regular sub-sequences with small fluctuations. The MIC algorithm effectively reduces the redundant information in NWP data, and the LSTM algorithm addresses the uncertainty of wind power data. Finally, the wind power of multiple wind farms is forecasted. Comparison of the forecast results of different methods revealed that the NWP-CEEMDAN-LSTM method proposed in this paper, which considers feature extraction using MIC, effectively tracks power fluctuations and improves forecast performance, thereby reducing the forecast error of wind power.

Floating offshore wind turbines hold great potential for future solutions to the growing demand for renewable energy production. Thereafter, the prediction of the offshore wind power generation became critical in locating and designing wind farms and turbines. The purpose of this research is to improve the prediction of the offshore wind power generation by the prediction of local wind speed using a Deep Learning technique. In this paper, the future local wind speed is predicted based on the historical weather data collected from National Oceanic and Atmospheric Administration. Then, the prediction of the wind power generation is performed using the traditional methods using the future wind speed data predicted using Deep Learning. The network layers are designed using both Long Short-Term Memory (LSTM) and Bi-directional LSTM (BLSTM), known to be effective on capturing long-term time-dependency. The selected networks are fine-tuned, trained using a part of the weather data, and tested using the other part of the data. To evaluate the performance of the networks, a parameter study has been performed to find the relationships among: length of the training data, prediction accuracy, and length of the future prediction that is reliable given desired prediction accuracy and the training size.

• The hourly wind speed prediction is an important problem. • A feed-forward (FF) multi-layer perceptron (MLP) artificial neural network (ANN) is used for prediction. • The FF MLP ANN is optimized by 9 state-of-art metaheuristic algorithms. • In the experiments, 38 years of hourly wind data belonging to 5 cities were used. • Grey Wolf Optimizer produced best results in terms of mean square error (MSE). The growing population has tremendously increased the daily energy demand all around the world. India is the second-most crowded nation in the world with approximately 1.4 billion people. New and renewable energy is on the agenda of India and in 2021 India possesses the fourth-largest installed capacity of wind power. Accurate prediction of wind speed is vital in wind farm design and operation. In this work, an hourly wind speed prediction with an artificial neural network optimized by a metaheuristics approach is conducted. A feed-forward (FF) multi-layer perceptron (MLP) artificial neural network (ANN) is used for the prediction of the hourly wind speed. In this study, 38 years of hourly wind data belonging to 5 cities (Ambur, Hosur, Kumbakonam, Nagapattinam, and Pudukottai) were used. These cities have different specific properties such as latitude, longitude, and altitude. The FF MLP ANN is optimized by 9 state-of-art metaheuristic algorithms. In this work, Artificial Bee Colony (ABC), Ant Colony Optimization (ACO), Biogeography Based Optimization (BBO), Evolutionary Strategy (ES), Genetic Algorithm (GA), Grey-Wolf-Optimizer (GWO), Population-Based Incremental Learning (PBIL), Particle Swarm Optimization (PSO), Tree-Seed Algorithm (TSA) have been used to optimize the weights of the ANN. GWO outperforms other metaheuristic algorithms in the prediction of wind speed with a FF MLP ANN model, with a success percentage rate of approximately 3% to 10,000%.