Hour-Ahead Solar Irradiance Forecasting Using Multivariate Gated Recurrent Units

Wojtkiewicz, Jessica; Hosseini, Matin; Gottumukkala, Raju; Chambers, Terrence L.

doi:10.3390/en12214055

Cited by 84 publications

(34 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other future research aiming to improve the forecast model's ability to learn nonlinear complexities with regards to cloud coverage and seasonal variations may consider the use of patch-based samples from the satellite images to analyze a broader geographic area for more context on nearby atmospheric and meteorological conditions. The drawback however is that patch-based approaches can be time-consuming and more complex, which may require more sophisticated forecast models such as CNN models [1,35], long short-term memory networks [9], and gated recurrent unit-based models [16]. While this study focuses on integrating COMS and H8 satellite image data, future works can include different ancillary data such as solar resources and various meteorological factors related to the atmosphere and local climate to produce a more comprehensive input dataset which would be more representative of local conditions.…”

Section: Discussionmentioning

confidence: 99%

“…For market participants, PV forecasts are required to avoid potential penalties and generate precise bids. In Korea, the PV market has experienced remarkable growth over the past decade due to considerable improvements in domestic PV technology, steady funding for PV research, implementation of government policies promoting the use of renewable energy, and the establishment of basic plans and detailed action programs [14][15][16]. As shown in Figure 1, the PV power market is continuously expanding in PV power transactions and PV power consumption.…”

Section: Introduction To Meteorological Satellites For Photovoltaic Pmentioning

confidence: 99%

See 1 more Smart Citation

Direct Short-Term Forecast of Photovoltaic Power through a Comparative Study between COMS and Himawari-8 Meteorological Satellite Images in a Deep Neural Network

2020

View full text Add to dashboard Cite

Meteorological satellite images provide crucial information on solar irradiation and weather conditions at spatial and temporal resolutions which are ideal for short-term photovoltaic (PV) power forecasts. Following the introduction of next-generation meteorological satellites, investigating their application on PV forecasts has become imminent. In this study, Communications, Oceans, and Meteorological Satellite (COMS) and Himawari-8 (H8) satellite images were inputted in a deep neural network (DNN) model for 2 hour (h)- and 1 h-ahead PV forecasts. A one-year PV power dataset acquired from two solar power test sites in Korea was used to directly forecast PV power. H8 was used as a proxy for GEO-KOMPSAT-2A (GK2A), the next-generation satellite after COMS, considering their similar resolutions, overlapping geographic coverage, and data availability. In addition, two different data sampling setups were designed to implement the input dataset. The first setup sampled chronologically ordered data using a relatively more inclusive time frame (6 a.m. to 8 p.m. in local time) to create a two-month test dataset, whereas the second setup randomly sampled 25% of data from each month from the one-year input dataset. Regardless of the setup, the DNN model generated superior forecast performance, as indicated by the lowest normalized mean absolute error (NMAE) and normalized root mean squared error (NRMSE) results in comparison to that of the support vector machine (SVM) and artificial neural network (ANN) models. The first setup results revealed that the visible (VIS) band yielded lower NMAE and NRMSE values, while COMS was found to be more influential for 1 h-ahead forecasts. For the second setup, however, the difference in NMAE results between COMS and H8 was not significant enough to distinguish a clear edge in performance. Nevertheless, this marginal difference and similarity of the results suggest that both satellite datasets can be used effectively for direct short-term PV forecasts. Ultimately, the comparative study between satellite datasets as well as spectral bands, time frames, forecast horizons, and forecast models confirms the superiority of the DNN and offers insights on the potential of transitioning to applying GK2A for future PV forecasts.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introduction To Meteorological Satellites For Photovoltaic Pmentioning

confidence: 99%

Direct Short-Term Forecast of Photovoltaic Power through a Comparative Study between COMS and Himawari-8 Meteorological Satellite Images in a Deep Neural Network

2020

View full text Add to dashboard Cite

show abstract

“…The commonly employed statistical measures for solar resource forecasting applications include RMSE, MAE and MAPE [29,30,55]. The accurate forecasting of solar irradiance is an intricate process due to the stochastic and intermittent nature of the solar irradiance [28,56]. The solar irradiance is only present during the daytime, whereas it has a very low or zero value during the night.…”

Section: E Statistical Measuresmentioning

confidence: 99%

“…The final forecasting result is based on summing the forecast of each learner [18]. DLMs comprising LSTM neural network and gated recurrent unit neural network also presented superior results in forecasting solar irradiance, compared to the other MLMs [26][27][28]. Qing et al [26] utilized the LSTM model for hourly day-ahead forecasting of solar irradiance.…”

Section: Introductionmentioning

confidence: 99%

A Multistage Hybrid Model ICEEMDAN-SE-VMD-RDPG for a Multivariate Solar Irradiance Forecasting

Sibtain

Saleem

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Accuracy of solar irradiance forecasting is imperative for the effective utilization and integration of solar energy into the power system. To forecast global horizontal irradiance based on a multivariate meteorological data; this study first evaluates five standalone models, including recurrent deterministic policy gradient (RDPG), long short term memory (LSTM) neural network, extreme gradient boosting (XGB), Gaussian process regression (GPR), and support vector regression (SVR). The RDPG model outperforms the standalone counterparts by demonstrating 2.485 W/m 2 , 20.591 W/m 2 , 18.316 W/m 2 , and 23.176 W/m 2 reductions in RMSE compared to the LSTM, XGB, GPR, and SVR models. Afterward, the performance of the RDPG model is further enhanced, by developing two-stage hybrid models, including improved complete ensemble empirical mode decomposition with additive noise-RDPG (ICEEMDAN-RDPG) and variational mode decomposition-RDPG (VMD-RDPG). The subsequent construction of the hybrid model ICEEMDAN-SE-VMD-RDPG (ISVR) results in the further improvement of the two-stage hybrid models. The ISVR surpasses all the established models including VMD-RDPG, ICEEMDAN-RDPG, RDPG, LSTM, XGB, GPR, and SVR by displaying 18.401 W/m 2 , 13.908 W/m 2 , 33.223 W/m 2 , 53.111 W/m 2 , 67.704 W/m 2 , 67.502 W/m 2 and 69.943 W/m 2 , respectively, decrease in RMSE. The overall results are enlightening and reveal the extension feasibility of the IVSR model for the other forecasting tasks, e.g., renewable energy integration and electrical load forecasting. INDEX TERMS Solar irradiance forecasting, decomposition techniques, sample entropy, correlation, deep reinforcement learning.

show abstract

“…The authors also concluded that GRU is less resource-intensive and faster compared to LSTM. The proposed work builds on our prior work [28], where we analyzed the performance of LSTM and GRU for GHI forecasting with and without using exogenous variables for one hour ahead forecasting [29]. Our observation in our prior work is that including weather variables particularly cloud cover significantly improved forecasting performance for both LSTM and GRU compared to univariate models.…”

Section: Introductionmentioning

confidence: 99%

Direct Normal Irradiance Forecasting Using Multivariate Gated Recurrent Units

et al. 2020

Self Cite

View full text Add to dashboard Cite

Power grid operators rely on solar irradiance forecasts to manage uncertainty and variability associated with solar power. Meteorological factors such as cloud cover, wind direction, and wind speed affect irradiance and are associated with a high degree of variability and uncertainty. Statistical models fail to accurately capture the dependence between these factors and irradiance. In this paper, we introduce the idea of applying multivariate Gated Recurrent Units (GRU) to forecast Direct Normal Irradiance (DNI) hourly. The proposed GRU-based forecasting method is evaluated against traditional Long Short-Term Memory (LSTM) using historical irradiance data (i.e., weather variables that include cloud cover, wind direction, and wind speed) to forecast irradiance forecasting over intra-hour and inter-hour intervals. Our evaluation on one of the sites from Measurement and Instrumentation Data Center indicate that both GRU and LSTM improved DNI forecasting performance when evaluated under different conditions. Moreover, including wind direction and wind speed can have substantial improvement in the accuracy of DNI forecasts. Besides, the forecasting model can accurately forecast irradiance values over multiple forecasting horizons.

show abstract

Hour-Ahead Solar Irradiance Forecasting Using Multivariate Gated Recurrent Units

Cited by 84 publications

References 30 publications

Direct Short-Term Forecast of Photovoltaic Power through a Comparative Study between COMS and Himawari-8 Meteorological Satellite Images in a Deep Neural Network

Direct Short-Term Forecast of Photovoltaic Power through a Comparative Study between COMS and Himawari-8 Meteorological Satellite Images in a Deep Neural Network

A Multistage Hybrid Model ICEEMDAN-SE-VMD-RDPG for a Multivariate Solar Irradiance Forecasting

Direct Normal Irradiance Forecasting Using Multivariate Gated Recurrent Units

Contact Info

Product

Resources

About