Attention mechanism for developing wind speed and solar irradiance forecasting models

2020 ◽  
pp. 0309524X2098188
Author(s):  
Banalaxmi Brahma ◽  
Rajesh Wadhvani ◽  
Sanyam Shukla
Keyword(s):  
Neural Network ◽  
Renewable Energy ◽  
Wind Speed ◽  
Recurrent Neural Network ◽  
Solar Irradiance ◽  
Power Plants ◽  
Energy Resource ◽  
Attention Mechanism ◽  
Wind Speed Prediction ◽  
Forecasting Models

This article presents the Recurrent Neural Network (RNN) and its Attention mechanism to develop forecasting models for renewable energy applications. In this study, wind speed and solar irradiance forecasting models have been developed as these two factors play a significant role in renewable energy production. The irregular nature of wind poses the challenge of accurate wind speed prediction, while solar irradiance forecasting can aid in the planning and deployment of solar power plants. In this paper, six RNN techniques, namely RNN, GRU, LSTM, Content-based Attention, Luong Attention, and Self-Attention based RNN are considered for forecasting the future values of wind speed and solar irradiance in particular geographical locations. The aim is the identification of the advantages, comparison, and importance of different recurrent neural network methods for forecasting models. All models are developed on the datasets of the National Renewable Energy Laboratory (NREL) and NASA’s Prediction of Worldwide Energy Resource (POWER).

scholarly journals Day-Ahead Solar Irradiance Forecasting Using Hybrid Recurrent Neural Network with Weather Classification for Power System Scheduling

2021 ◽  
Vol 11 (15) ◽  
pp. 6738
Author(s):  
Rehman Zafar ◽  
Ba Hau Vu ◽  
Munir Husein ◽  
Il-Yop Chung
Keyword(s):  
Neural Network ◽  
Renewable Energy ◽  
Power System ◽  
Recurrent Neural Network ◽  
Solar Irradiance ◽  
Short Term Memory ◽  
Dew Point ◽  
Support Vector ◽  
Renewable Energy Resources ◽  
Feed Forward Neural Network

At the present time, power-system planning and management is facing the major challenge of integrating renewable energy resources (RESs) due to their intermittent nature. To address this problem, a highly accurate renewable energy generation forecasting system is needed for day-ahead power generation scheduling. Day-ahead solar irradiance (SI) forecasting has various applications for system operators and market agents such as unit commitment, reserve management, and biding in the day-ahead market. To this end, a hybrid recurrent neural network is presented herein that uses the long short-term memory recurrent neural network (LSTM-RNN) approach to forecast day-ahead SI. In this approach, k-means clustering is first used to classify each day as either sunny or cloudy. Then, LSTM-RNN is used to learn the uncertainty and variability for each type of cluster separately to predict the SI with better accuracy. The exogenous features such as the dry-bulb temperature, dew point temperature, and relative humidity are used to train the models. Results show that the proposed hybrid model has performed better than a feed-forward neural network (FFNN), a support vector machine (SVM), a conventional LSTM-RNN, and a persistence model.

Very Short-Term Wind Speed Prediction of a Wind Farm Based on Artificial Neural Network

2012 ◽  
Vol 608-609 ◽  
pp. 677-682 ◽  
Author(s):  
Rui Ma ◽  
Shu Ju Hu ◽  
Hong Hua Xu
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Wind Speed ◽  
Power Plants ◽  
Wind Farm ◽  
Model Parameters ◽  
Ann Model ◽  
Wind Speed Prediction ◽  
Speed Prediction ◽  
Artificial Neural

Wind speed prediction is critical for wind energy conversion system since it not only can relieve or avoid the disadvantageous impact on power system, but also can enhance the competitive ability of wind power plants against others in electricity markets. The model presented in this paper was based on artificial neural network (ANN) and the selection of the model parameters was presented in detail. The autocorrelation function (ACF) of wind speed time series was used to determine the input variables of the neural network. The simulation was carried out with the proposed ANN model.The conclusion that the optimal network structure may be different corresponding to different error evaluation was drawn through a large number of simulation experiments. And the simulaiton results showed that the ANN model is less than 10.77% in terms of root mean square error and 5.86% in terms of mean absolute error compared with the persistence model.

scholarly journals An Intelligent Ensemble Neural Network Model for Wind Speed Prediction in Renewable Energy Systems

2016 ◽  
Vol 2016 ◽  
pp. 1-14 ◽  
Author(s):  
V. Ranganayaki ◽  
S. N. Deepa
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Renewable Energy ◽  
Wind Speed ◽  
Neural Model ◽  
Wind Speed Prediction ◽  
Speed Prediction ◽  
Ensemble Neural Network ◽  
Hidden Neurons ◽  
Selection Of

Various criteria are proposed to select the number of hidden neurons in artificial neural network (ANN) models and based on the criterion evolved an intelligent ensemble neural network model is proposed to predict wind speed in renewable energy applications. The intelligent ensemble neural model based wind speed forecasting is designed by averaging the forecasted values from multiple neural network models which includes multilayer perceptron (MLP), multilayer adaptive linear neuron (Madaline), back propagation neural network (BPN), and probabilistic neural network (PNN) so as to obtain better accuracy in wind speed prediction with minimum error. The random selection of hidden neurons numbers in artificial neural network results in overfitting or underfitting problem. This paper aims to avoid the occurrence of overfitting and underfitting problems. The selection of number of hidden neurons is done in this paper employing 102 criteria; these evolved criteria are verified by the computed various error values. The proposed criteria for fixing hidden neurons are validated employing the convergence theorem. The proposed intelligent ensemble neural model is applied for wind speed prediction application considering the real time wind data collected from the nearby locations. The obtained simulation results substantiate that the proposed ensemble model reduces the error value to minimum and enhances the accuracy. The computed results prove the effectiveness of the proposed ensemble neural network (ENN) model with respect to the considered error factors in comparison with that of the earlier models available in the literature.

Evaluation of energy generation in Iraqi territory by solar photovoltaic power plants with a capacity of 20 MW

2022 ◽  
Vol 0 (0) ◽  
Author(s):  
Qusay Hassan ◽  
Saadoon Abdul Hafedh ◽  
Ali Hasan ◽  
Marek Jaszczur
Keyword(s):  
Experimental Data ◽  
Wind Speed ◽  
Power Plant ◽  
Ambient Temperature ◽  
Solar Irradiance ◽  
Electricity Generation ◽  
Power Plants ◽  
Solar Photovoltaic ◽  
Photovoltaic Power ◽  
Plant Capacity

Abstract The study evaluates the visibility of solar photovoltaic power plant construction for electricity generation based on a 20 MW capacity. The assessment was performed for four main cities in Iraq by using hourly experimental weather data (solar irradiance, wind speed, and ambient temperature). The experimental data was measured for the period from 1st January to 31st December of the year 2019, where the simulation process was performed at a 1 h time step resolution at the same resolution as the experimental data. There are two positionings considered for solar photovoltaic modules: (i) annual optimum tilt angle and (ii) two-axis tracking system. The effect of the ambient temperature and wind on the overall system energy generated was taken into consideration. The study is targeted at evaluating the potential solar energy in Iraq and the viability of electricity generation using a 20 MW solar photovoltaic power plant. The results showed that the overall performance of the suggested power plant capacity is highly dependent on the solar irradiance intensity and the ambient temperature with wind speed. The current 20 MW solar photovoltaic power plant capacity shows the highest energy that can be generated in the mid-western region and the lowest in the northeast regions. The greatest influence of the ambient temperature on the energy genrated by power plants is observed in the southern regions.

Sign in / Sign up

Export Citation Format

Share Document