Fill Missing Data for Wind Farms Using Long Short-Term Memory Based Recurrent Neural Network

Wind power is one of the most efficient renewable resources without emissions. Nonetheless, it is difficult to exactly forecast wind power generation given historical power and wind speed information, the failure of which may cost the risk of large-scale outages. This article takes a close look at the artificial recurrent neural network framework in the application of wind power forecasting. More intelligent mechanisms using attention to capture spatial-temporal patterns within historical data are emphasized in this work and are shown to be state-of-the-art for short-term wind power forecasting. Our experiments at a wind farm in southeast Australia using only the historical wind power generation and wind speed records from ambient weather stations show that, e.g., 7.4750% in mean absolute error (MAE) and 0.3345 in the coefficient of variation in the root mean squared error (CV-RMSE) for half-hour-ahead prediction. To interpret how the three models under consideration—the long- and short-term time-series network (LSTNet), the temporal pattern attention-based long short-term memory (TPA-LSTM) and the dual-stage attention-based recurrent neural network (DA-RNN)—work, we visualize and analyze the details of the models so that further improvement can be made by combining the advantageous components of the models.

With the rising demand for environmental protection, wind energy has made considerable progress as a clean energy source. Due to the uncertainty of wind power generation, accurate forecasting of wind power is conducive to achieving stable grid-connected control of wind turbines. This paper proposes an ultra-short-term wind power forecasting model composed of variational modal decomposition (VMD) and long short-term memory (LSTM) networks. Obtain the recorded historical wind speed and historical power from the wind field data acquisition and monitoring control system (SCADA), and use VMD to decompose and reconstruct the historical wind speed of the wind field to form 5 training data sets. Using historical power, historical wind speed, and predicted wind speed as input, wind power forecasts for the next 4 hours (15 minutes apart) are made. In order to evaluate the prediction ability of the proposed model, two algorithms, LSTM and XGBoost, are used for prediction. Taking root mean square error (RMSE) and mean absolute error (MAE) as evaluation indicators, the results show that the prediction accuracy of wind power is significantly improved after VMD processing, and the performance of LSTM is better than XGBoost in the two evaluation indicators.

The accuracy of wind power forecasting has a very important influence on the safe and stable operation of power system. However, wind power prediction is very difficult, especially under the environment of massive data. This paper presents a novel multi-step ahead wind power prediction model based on recurrent neural network (RNN) with long short-term memory (LSTM) unit or gated recurrent unit (GRU) to improve the accuracy. Firstly, an overall forecasting framework for wind power with diverse forms of optional hybrid models is proposed. Moreover, an innovative LSTM/GRU-based forecasting model is developed with a wind speed correction process using numerical weather prediction (NWP) data. Through the application of GRU network, the correction process can provide corrected wind speed at the predicted moment as an input of the forecasting model. Finally, the experimental results demonstrate the superiority of the proposed RNN approaches as compared to the ARIMA method and SVM method while the main distinctions between the LSTM and GRU network are also illustrated.

Wind power is one of the most large-scale new energy sources. But wind power instability will affect power grid safety, which is in a great need for wind power forecasting algorithms. To accurately predict wind power and reduce power grid fluctuations, it proposes a new wind power forecasting (WPF) algorithm based on long short-term memory (LSTM) neural network using wind farm real operation data. First, the wind farm power data are de-averaged and divided into two different sets in order to meet the requirements of the algorithm. Then, structure of the LSTM neural network is designed and hyper-parameters are adjusted to improve accuracy of forecasting. Finally, the definite LSTM neural network is used for forecasting the power data in time series to derive the power forecasting value, which is reduced and evaluated according to the original size. The results show that compared with other forecasting methods, in short-term WPF at different time scales, this algorithm has smaller errors in power forecasting results, which is also suitable for long-term WPF.

A CNN encoder decoder LSTM model for sustainable wind power predictive analytics

Accurate wind power prediction can reduce the negative impact of wind power on power grid and reduce the operation cost of power system. Wind power forecasting is of great significance in spot trading, but the instability of wind power series brings difficulties to forecasting. With the rapid development of deep learning technology, prediction algorithm based on deep learning has been widely used in wind power prediction. The long short-term memory (LSTM) network performs well in a variety of prediction scenarios, but there is still room for improvement. In order to improve the prediction accuracy of LSTM in wind power prediction, this paper adopts a new gating mechanism in LSTM network, which can improve the context information modeling ability of LSTM network. The experimental results based on real data show that the proposed improved LSTM prediction model can improve the prediction accuracy of LSTM prediction model in ultra-short term wind power prediction scenarios.

Evaluating the impact of Numerical Weather Prediction variables on wind power forecasting: A case study of the Alpha Ventus offshore wind farm

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

FDNet: Frequency filter enhanced dual LSTM network for wind power forecasting

Wind energy is one of the fastest progressing renewable energy sources. Wind speed forecasting has gained more attention as wind energy never causes air pollution and other hazards to the environment. Eco-friendliness and cost-effectiveness are the main reasons for the high demand for wind energy. Accurate and reliable prediction model for wind speed forecasting is very challenging because of its intermittent nature. Deep learning based architectures like Recurrent Neural Networks (RNN) and Long Short Term Memory (LSTM) are considered as better models for time series prediction. LSTM neural network models are more appropriate for learning long term dependencies. In this paper, an LSTM network for a multi-step-ahead short term wind speed forecasting is proposed. As lag values have importance in time series prediction problems, tests are conducted to find optimal lag value. The value which contributes minimum mean square error is selected as optimal lag value. The study of the results reveals that the proposed LSTM model is more effective and efficient with high predictive accuracy compared to Auto-Regressive Integrated Moving Average (ARIMA) model.

Renewable sources such as solar PV and wind are stochastic in nature, hence their integration with emerging isolated microgrid (MG) is challenging especially with regards to stability issues. An accurate prediction model of wind and solar sources is necessary to analyze the uncertainty in MG system and to encourage the reliable participation of wind and solar power in the energy market. The advancement in deep learning methods has made it possible to develop a multi-step forecasting model unlike shallow neural networks (SNNs). The time series forecasting using SNN and Recurrent Neural Network (RNN) suffers from the problem of vanishing/exploding gradient while training. To eliminate this problem the long short-term memory (LSTM) RNN has been used in this study for wind speed and solar irradiance prediction. The forecasted solar and wind power is applied to analyze the load frequency behavior and the response of nonrenewable sources for sudden rise and fall in load power demand and PI controller is used to mitigate frequency deviation to ensure the stability of the MG power system.

The sustainability of the electricity market relies on enhanced forecasting of renewable energy sources combined with energy storage arbitrage. This paper introduces a bi-level approach with a novel contribution to wind farms and energy storage to generate maximum revenue in the day-ahead (DA) electricity market. In the first stage, the maximum revenue of the wind farm is estimated by forecasting wind power and market prices. The second stage models the optimal energy arbitrage strategy for storage devices. To solve the first problem, a well-organized Long-Short-Term-Memory (LSTM) combined with recurrent neural network (RNN)—Adam optimizer model is used, and for the second level by using Monte-Carlo optimization, the superior frontier of the revenue is estimated with locational based marginal prices (LBMPs). The solution to the second-level problem delivers a solitary value of the foremost boundary of the revenue and the equivalent charging/discharging schedule. An effective and feasible solution for improving the financial performance of renewable energy and storage systems in the DA market is offered by the suggested framework, which presents a novel approach to incorporating analytical prediction and optimization methodologies.

The rapid rate of transformation in the power sector of India has placed a significant emphasis on robust grids and distributed generation units. The observable shift in the energy sector, especially in wind and solar energy, also requires smooth integration of Distributed Generation units with the existing power grid. Precise wind power generation forecast, therefore, becomes an important and complex task for the strategic planning and management of the systems. We, thus, aim towards a system that can actually provide precise wind power forecasts by applying machine learning techniques. This work proposes a comparative and comprehensive analysis of Artificial Neural Network (ANN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Autoregressive Integrated Moving Average (ARIMA) model. The experimentations and modelling are performed considering meteorological and historical power generation data. The study is concentrated in Kutch, Gujarat and is validated on the data collected from the Central Electricity Authority (CEA), India for power generation data and weather data collected from regional weather centres. The findings show that ARIMA outperforms the other models for non-linear data in multivariate analysis, with a MAPE score of less than 5.5 on the prediction dataset.

Short-term multi-hour ahead country-wide wind power prediction for Germany using gated recurrent unit deep learning

Accurate forecasting is the key factor in promoting wind power consumption and improving the stable operation of power systems. A short-term wind power forecasting (WPF) and uncertainty analysis method based on whale optimization algorithm (WOA), least squares support vector machine (LSSVM), and nonparametric kernel density estimation (NPKDE) was proposed in this paper. The advantages of WOA (fast convergence speed and high convergence accuracy) were used to optimize the penalty factor and kernel function width of the LSSVM model, and the calculation speed and forecasting accuracy of the LSSVM model were improved. The training sample set is classified according to the wind speed interval, and the WOA-LSSVM forecasting model is trained by subclass after classification to further improve the accuracy of short-term WPF. The NPKDE method is used to accurately calculate the probability density distribution characteristics of the forecasting error of wind power, and the confidence interval of the WPF is accurately calculated based on the probability density distribution characteristics. The calculation results show that the forecasting accuracy of the WOA-LSSVM model is higher than those of the LSSVM, long short-term memory (LSTM), and particle swarm optimization and least squares support vector machine (PSO-LSSVM) models, and the forecasting accuracy of the WOA-LSSVM model can be further improved after classifying the training sample set. The coverage of the confidence intervals in different time scales is higher than the corresponding confidence level, indicating that the NPKDE method can accurately describe the probability density distribution characteristics of the WPF errors.