Intelligent Neural Learning Models for Multi-step Wind Speed Forecasting in Renewable Energy Applications

Wind energy is one of the fastest growing renewable energy sources. Wind speed forecasting is essential to enhance the utilization of wind energy. Various prediction models have been developed to improve the prediction accuracy of wind speed. However, wind speed time series has nonlinearity, fluctuation, and intermittence, which makes the prediction difficult. Existing prediction models ignore data decomposition and feature reduction and suffer from the deficiency of individual models. This paper proposes a novel ensemble prediction model, which integrates data preprocessing, feature selection, parameter optimization, three intelligent prediction models, and an ensemble strategy. To improve prediction performance, a highly efficient optimization algorithm is applied to determine the individual models’ optimal parameters. Furthermore, partial least square regression is used to calculate combination weight. Additionally, two 10 min datasets from the National Renewable Energy Laboratory (NREL) are employed for one-step-ahead prediction. Among the involved models, the proposed model can obtain the best prediction accuracy. The experimental results indicate that the mean absolute percent errors of the proposed model are 7.97% and 9.99%, which are lower than the comparison methods. Pearson’s test reveals that the proposed approach can have the strongest association between the actual data and the prediction results.

Download Full-text

A new weighted MSE loss for wind speed forecasting based on deep learning models

10.5194/egusphere-egu2020-12899 ◽

2020 ◽

Author(s):

Xi Chen ◽

Ruyi Yu ◽

Sajid Ullah ◽

Dianming Wu ◽

Min Liu ◽

...

Keyword(s):

Time Series ◽

Deep Learning ◽

Wind Speed ◽

Loss Function ◽

Time Series Data ◽

Series Data ◽

Learning Models ◽

Wind Speed Forecasting ◽

Training Samples ◽

Forecasting Performance

Wind speed forecasting is very important for a lot of real-life applications, especially for controlling and monitoring of wind power plants. Owing to the non-linearity of wind speed time series, it is hard to improve the accuracy of runoff forecasting, especially several days ahead. In order to improve the forecasting performance, many forecasting models have been proposed. Recently, deep learning models have been paid great attention, since they excel the conventional machine learning models. The majority of existing deep learning models take the mean squared error (MSE) loss as the loss function for forecasting. MSE loss is linear. Consequently, it hinders further improvement of forecasting performance over nonlinear wind speed time series data. &#160;&#160; &#160; In this work, we propose a new weighted MSE loss function for wind speed forecasting based on deep learning. As is well known, the training procedure is dominated by easy-training samples in applications. The domination will cause the ineffectiveness and inefficiency of computation. In the new weighted MSE loss function, loss weights of samples can be automatically reduced, according to the contribution of easy-training samples. Thus, the total loss mainly focuses on hard-training samples. To verify the new loss function, Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) have been used as base models.&#160; &#160; A number of experiments have been carried out by using open wind speed time series data collected from China and Unites states to demonstrate the effectiveness of the new loss function with three popular models. The performances of the models have been evaluated through the statistical error measures, such as Mean Absolute Error (MAE). MAE of the proposed weighted MSE loss are at most 55% lower than traditional MSE loss. The experimental results indicate that the new weighted loss function can outperform the popular MSE loss function in wind speed forecasting.&#160;

Download Full-text

A Novel Approach for Wind Speed Forecasting Using LSTM-ARIMA Deep Learning Models

International Journal of Agricultural and Environmental Information Systems ◽

10.4018/ijaeis.2020070102 ◽

2020 ◽

Vol 11 (3) ◽

pp. 13-30

Author(s):

Vikram Bali ◽

Ajay Kumar ◽

Satyam Gangwar

Keyword(s):

Artificial Intelligence ◽

Deep Learning ◽

Wind Speed ◽

Arima Model ◽

Learning Models ◽

Wind Speed Forecasting ◽

Research Article ◽

Novel Approach ◽

Future Value ◽

Precision Rate

The term which is used to predict wind speed to produce wind power is wind speed forecasting. Deep learning, is a form of AI, basically indulging in artificial intelligence and thus can greatly increase the precision rate on larger datasets. In this research paper, the two techniques are being used together to obtain the better forecasting results. Both the techniques are forecasting based and combining LSTM and deep learning can increase the forecast rate because of the pattern remembering attribute of LSTM over a longer interval/period of time. If there is the inclusion of the ARIMA model the likelihood of a future value lying between two indicated limits is increased. So, overall if both the techniques are hybridized than it is most probable that the obtained results should be more accurate than both the techniques used separately. So, the main focus of this research article is on the efficiency and evaluation of hybridized LSTM-ARIMA model to predict wind speed forecasting.

Download Full-text

Lossless Dynamic Models of the Quasi-Z-Source Converter Family

Scientific Journal of Riga Technical University Power and Electrical Engineering ◽

10.2478/v10144-011-0013-y ◽

2011 ◽

Vol 29 (1) ◽

pp. 73-78 ◽

Cited By ~ 1

Author(s):

Dmitri Vinnikov ◽

Oleksandr Husev ◽

Indrek Roasto

Keyword(s):

Renewable Energy ◽

Dynamic Models ◽

Energy Applications

Lossless Dynamic Models of the Quasi-Z-Source Converter FamilyThis paper is devoted to the quasi-Z-source (qZS) converter family. Recently, the qZS-converters have attracted attention because of their specific properties of voltage boost and buck functions with a single switching stage, which could be especially beneficial in renewable energy applications. As main representatives of the qZS-converter family, the traditional quasi-Z-source inverter as well as two novel extended boost quasi-Z-source inverters are discussed. Lossless dynamic models of these topologies are presented and analyzed.

Download Full-text