A novel deep learning intelligent clustered hybrid models for wind speed and power forecasting

To address foreseeable challenges during the penetration of wind energy into the power grid, including accurate wind power forecasting and smart power generation scheduling, this study proposes a novel short-term wind speed forecasting model, named EMD-KM-SXL, which is based on empirical mode decomposition (EMD), K-means clustering and machine learning, and a new two-stage short-term wind power forecasting model based on wind speed forecasting and wind power curve modeling. The former wind speed forecasting model regards historical wind speed observations as model inputs, and the latter power forecasting model utilizes knowledge augmentation, introducing wind power conversion relationship, environmental factors as well as wind power system status parameters. In the proposed wind speed forecasting model, three machine learning models, including support vector regressor, XGBoost regressor, and Lasso regressor, are employed to forecast three types of frequency components that are generated via EMD and K-means clustering. Then, the wind power curve model is utilized to compute potential outpower based on the predicted wind speed, which is regarded as the first stage of the proposed wind power forecasting model. In the second stage, environmental factors and wind power system status parameters are introduced and an artificial neural network model, considering preliminary predicted power, environmental factors, and wind power system status parameters as model inputs, is built to make final power prediction. Computational results show that proposed models achieve the best performance in terms of wind speed and power forecasting over different forecasting horizons ranging from 10 to 40 minutes, compared with benchmarking methods.

The intermittent nature of wind energy raised multiple challenges to the power systems and is the biggest challenge to declare wind energy a reliable source. One solution to overcome this problem is wind energy forecasting. A precise forecast can help to develop appropriate incentives and well-functioning electric markets. The paper presents a comprehensive review of existing research and current developments in deterministic wind speed and power forecasting. Firstly, we categorize wind forecasting methods into four broader classifications: input data, time-scales, power output, and forecasting method. Secondly, the performance of wind speed and power forecasting models is evaluated based on 634 accuracy tests reported in twenty-eight published articles covering fifty locations of ten countries. From the analysis, the most significant errors were witnessed for the physical models, whereas the hybrid models showed the best performance. Although, the physical models have a large normalized root mean square error values but have small volatility. The hybrid models perform best for every time horizon. However, the errors almost doubled at the medium-term forecast from its initial value. The statistical models showed better performance than artificial intelligence models only in the very short term forecast. Overall, we observed the increase in the performance of forecasting models during the last ten years such that the normalized mean absolute error and normalized root mean square error values reduced to about half the initial values.

Wind power is one of the most widespread renewable resources, offering the benefits of no pollution and competitive cost when compared to conventional and other renewable sources. Since wind speed is highly stochastic, integrating wind power in the grid requires an accurate modeling and forecasting of wind speed and power. Including the seasonal trend of wind speed in the forecasting process is a key aspect of the modeling and forecasting process. One of the best methods for modeling and forecasting wind speed is the Auto-Regression and Moving Average (ARMA). In this paper, the impact of seasonal ARMA wind speed and power modeling on the reliability of power distribution systems is investigated. Daily and hourly wind speed modeling will be used to assess the reliability of residential, commercial and industrial loads when the wind power is installed at the local load.

Wind is a renewable and green energy source that is vital for sustainable human development. Wind variability implies that wind power is random, intermittent, and volatile. For the reliable, stable, and secure operation of an electrical grid incorporating wind power systems, a multi-hour ahead wind power forecasting system comprising a physics-based model, a multi-criteria decision making scheme, and two artificial intelligence models was proposed. Specifically, a Weather Research and Forecasting (WRF) model was used to produce wind speed forecasts. A technique for order of preference by similarity to ideal solution (TOPSIS) scheme was employed to construct a 5-in-1 (ensemble) WRF model relying on 1334 initial ensemble members. Two adaptive neuro-fuzzy inference system (ANFIS) models were utilised to correct the wind speed forecasts and determine a power curve model converting the improved wind speed forecasts to wind power forecasts. Moreover, three common statistics-based forecasting models were chosen as references for comparing their predictive performance with that of the proposed WRF-TOPSIS-ANFIS model. Using a set of historical wind data obtained from a wind farm in China, the WRF-TOPSIS-ANFIS model was shown to provide good wind speed and power forecasts for 30-min to 24-h time horizons. This paper demonstrates that the novel forecasting system has excellent predictive performance and is of practical relevance.

Wind Power Forecasting

Short-term wind speed and wind power forecasts (for a 72 h period) are obtained using a nonlinear autoregressive exogenous artificial neural network (ANN) methodology which incorporates either numerical weather prediction or high-resolution computational fluid dynamics wind field information as an exogenous input. An ensemble approach is used to combine the predictions from many candidate ANNs in order to provide improved forecasts for wind speed and power, along with the associated uncertainties in these forecasts. More specifically, the ensemble ANN is used to quantify the uncertainties arising from the network weight initialization and from the unknown structure of the ANN. All members forming the ensemble of neural networks were trained using an efficient particle swarm optimization algorithm. The results of the proposed methodology are validated using wind speed and wind power data obtained from an operational wind farm located in Northern China. The assessment demonstrates that this methodology for wind speed and power forecasting generally provides an improvement in predictive skills when compared to the practice of using an “optimal” weight vector from a single ANN while providing additional information in the form of prediction uncertainty bounds.

Wind speed and wind power are two important indexes for wind farms. Accurate wind speed and power forecasting can help to improve wind farm management and increase the contribution of wind power to the grid. However, nonlinear and non-stationary wind speed and wind power can influence the forecasting performance of different models. To improve forecasting accuracy and overcome the influence of the original time series on the model, a forecasting system that can effectively forecast wind speed and wind power based on a data pre-processing strategy, a modified multi-objective optimization algorithm, a multiple single forecasting model, and a combined model is developed in this study. A data pre-processing strategy was implemented to determine the wind speed and wind power time series trends and to reduce interference from noise. Multiple artificial neural network forecasting models were used to forecast wind speed and wind power and construct a combined model. To obtain accurate and stable forecasting results, the multi-objective optimization algorithm was employed to optimize the weight of the combined model. As a case study, the developed forecasting system was used to forecast the wind speed and wind power over 10 min from four different sites. The point forecasting and interval forecasting results revealed that the developed forecasting system exceeds all other models with respect to forecasting precision and stability. Thus, the developed system is extremely useful for enhancing forecasting precision and is a reasonable and valid tool for use in intelligent grid programming.

Wind energy resources, unlike dispatchable central station generation, produce power dependable on an external irregular source, the incident wind speed, which does not always blow when electricity is needed. This results in the variability, unpredictability, and uncertainty of wind resources. Therefore, the integration of wind facilities to utility electrical grid presents a major challenge to power system operators. Such integration has significant impact on the optimum power flow, transmission congestion, power quality issues, system stability, load dispatch, and economic analysis. Due to the irregular nature of wind power production, accurate prediction represents the major challenge to power system operators. This chapter investigates the usage of Grey predictor rolling models for hourly wind speed forecasting and wind power prediction.

The wind speed forecast (WSF), which is the main source of forecasting error, is a major component of the short‐term wind power forecast (WPF). This study introduces wave‐related data and deep learning algorithms to develop a deep ocean WPF model aimed at improving wind speed and power forecast accuracy, thereby enhancing the operational stability of wind power systems. First, for offshore wind farms, wave height data is introduced as an auxiliary feature to enhance WPF accuracy. Second, a Deep Hidden Markov Model (DHMM) is proposed to correct WSF errors. The DHMM models the state transition process of forecast errors using a Hidden Markov Model (HMM) and incorporates deep learning methods to capture the complex nonlinear relationships between wind speed and prediction errors. Based on this, the relationship between wave height and wind speed is utilised to classify and correct the errors, further improving prediction accuracy. The WPF model's performance is then improved by multi‐feature processing and feature selection algorithms that identify the best feature combinations. Finally, the proposed W‐DHMM‐MR model is validated through examples, and the results show that the model outperforms the selected benchmark models in terms of forecasting accuracy.

In modern development, renewable energy is playing a crucial role for smart grid integration and in electricity demand growth as it is green and clean. Including all sources of renewable energy, wind power is particularly prevalent as it is pollution-free, cheap, and highly efficient. The main challenge that restrains the expansion of wind power utilization within the power grid is wind speed variation and uncertainties. Thus, precise wind speed forecasting is a difficult modeling approach, that greatly influences the wind power and optimal operation of the power grid. Prediction of wind speed is vital for wind power calculation and forecasting. Renewable energy forecasting is important for minimizing the power cost, scheduling energy resources, and planning maintenance. The advanced wind power forecast models help advances efficient operation and maintenance for wind turbines. This paper analytically studies the state-of-the-art approaches of wind speed forecasting regarding statistical methods (ARIMA, Weka time-series, and Deep Learning Networks), including data preprocessing, features engineering, and factors that touch prediction accuracy and modeling time. Likewise, this study provides a comparison to find the most accurate time series forecasting method based on performance evaluation.

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

An intelligent framework for short-term multi-step wind speed forecasting based on Functional Networks

As a renewable and clean energy source, wind power is being widely utilized all over the world. The uncertainty of wind speed, however, makes certain trouble for the development of wind power generation. In order to relieve the disadvantageous impact of wind speed intermittence on the connected power system, the wind power forecasting needs to be carried out. In this paper, a wind speed and power forecasting method based on RBF neural network is proposed. In which, the influence of the dataset construct method on the forecasting accuracy is researched. The simulation results show that the forecasting accuracy is improved by performing the dataset reconstruction. And it is proved that the higher forecasting accuracy of wind power can be gotten through introducing the wind speed as RBF inputs.

With the scale of grid-connected wind farms increasing, accurate forecast of ultra-short-term wind speed and wind power is very important to the stable operation of power systems. This paper presents a dynamic selective neural network ensemble (DSNNE) forecast method, which makes use of K nearest neighbor algorithm to collect the generalization errors of certain different BP neural networks and RBF neural networks into a performance matrix and then the neural networks with low local generalization errors are dynamically selected and locally dynamic averaging is applied to the neural networks in order to conduct the final results of the ensemble. Then this method is applied to realize the wind speed and power ultra-short-term advance forecast, taking the wind speed and wind turbine power output from a wind farm in China as the original data. The research results show that DSNNE improves the generalization ability of the neural network system and the prediction accuracy of wind power and wind speed significantly. It proves the validity and effectiveness of the DSNNE with controlling the biggest mean relative error of 2 minutes ahead wind power and wind speed forecast as low as 25% and 16% respectively.

Non-parametric hybrid models for wind speed forecasting