Estimating Solar Insolation and Power Generation of Photovoltaic Systems Using Previous Day Weather Data

Chung, Min Hee

doi:10.1155/2020/8701368

Cited by 14 publications

(7 citation statements)

References 42 publications

(55 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Unlike previous papers that predicted daily insolation, this study has a high utilization in EMS by establishing a model for predicting hourly insolation [24][25][26][27][28][29]. It also has the advantage of being the basis for future studies or being applied in practice using only the weather observation data generally provided by the Meteorological Agency and calculated value.…”

Section: Prediction Results Analysis and Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Predictive Model for Solar Insolation Using the Deep Learning Technique

Park

Hong

Yeon

et al. 2023

International Journal of Energy Research

View full text Add to dashboard Cite

In this study, prediction performances of a regression model and deep learning-based predictive models were comparatively analyzed for the prediction of hourly insolation in regions located at the temperate climate and microthermal climate with high precipitation. Unlike linear regression models, artificial neural networks (ANN) and long short-term memory- (LSTM-) based models achieved reliable predictive performances with CV(RMSE) of 14.0% and 15.8%, respectively. This study proposed the direction of future research by improving the performance of predicting insolation at 1 hour after the current time-step, which has time-dependent characteristics, by utilizing insolation at 24 hours before the current time-step and insolation at the current time-step in addition to the forecasted weather data. In the proposed models, a large error occurred at sunrise and sunset times, suggesting the possibility of improving predictive performance by utilizing variables related to sunrise and sunset in the future. Along with Cheongju, the proposed model could properly predict the hourly insolation in other regions around the world. The results of predicting other regions derived slightly higher prediction errors than Cheongju. However, it is expected that it will be possible to predict the hourly insolation in other regions with better prediction performance if variables related to geographical location are additionally considered in the future.

show abstract

Section: Prediction Results Analysis and Discussionmentioning

confidence: 99%

“…The optimal prediction model has a prediction performance of 51.35 W/m 2 of root mean square error (RMSE) [24]. Chung constructed an ANN-based model based on weather data to predict daily insolation [25]. Husein and Chung constructed a long short-term memory (LSTM) model to predict daily insolation based on weather data [26].…”

Section: Introductionmentioning

confidence: 99%

Predictive Model for Solar Insolation Using the Deep Learning Technique

Park

Hong

Yeon

et al. 2023

International Journal of Energy Research

View full text Add to dashboard Cite

show abstract

“…Weather features: Weather is one of the important factors when forecasting PV generation and load demand. Similar to [35], [36], three parameters that are frequently used as exogenous variables are considered here. It is also compelling to assess their impact on forecasting 𝐿 𝑡+48 and 𝑃 𝑡+48 .…”

Section: B Stage-2: Feature Generation and Selection (Fgs)mentioning

confidence: 99%

A Data-Driven Short-Term PV Generation and Load Forecasting Approach for Microgrid Applications

Trivedi

Patra

Khadem

2022

IEEE J. Emerg. Sel. Top. Ind. Electron.

View full text Add to dashboard Cite

The data-driven (DD) is a systematic approach to improve the data and model by deriving/adding features to address the problem identified during the iterative loop of forecasting model development. This article proposes a DD framework for forecasting short-term PV generation and load demand. A framework of 3 stages with a unique contribution in each stage, such as generalising data pre-processing steps (stage-1), multivariate feature generation and selection (stage-2) and model hyperparameter tuning (stage-3) for further improvement in forecasting is proposed. It focuses on data as well as forecasting models. The whole process is analysed using the time series measured data collected from a real-life demonstration project in Ireland. Data pre-processing is generalised for both generation and demand forecasting under the same framework. The relevant features are selected with the help of the proposed random forest sequential forward feature selection (RF-SFS) algorithm. Hyperparameters are tuned through Tree-structured Parzen Estimator (TPE) algorithm for further improvement. In addition, the performance of the classical ARIMA model is compared with the machine learning-based GRU, LSTM, RNN and CNN models. Results show that the data-driven forecasting model framework systematically improves the model performance. The seasonal variation has also a high impact on the model performances.

show abstract

“…The global extraterrestrial and terrestrial horizontal irradiance were calculated for Baghdad city every 10 days in 2019. The calculations of the extraterrestrial irradiance were based on Equation ( 12) while the calculations of terrestrial irradiance were based on Equations (13)(14)(15)(16). The latter calculated values were compared with the observed values obtained from the automatic weather station.…”

Section: Calculation Of Extraterrestrial and Terrestrial Global Horiz...mentioning

confidence: 99%

A Model to Compute the Solar Parameters in Relation to Determining the Optimal Angles for Solar Panels in Many Locations in Iraq

Roomi

Nemah²,

Shubbar³

2021

eijs

View full text Add to dashboard Cite

Directing solar panels in a way that collects the largest possible amount of solar energy is still attracting a lot of attention due to the continuous need to get clean, inexpensive renewable energy. Iraq is one of the countries characterized by the abundance of solar energy but the investment in this field has been far below ambition. In this study, an application developed with the visual basic programing language was used to compute precisely various solar angles and parameters , as a powerful tool for engineers and researchers. The outputs of the model were tested and discussed in detail. The air mass values were also computed for three cities: Mosul, Baghdad, and Basra. The results showed that the best time to acquire the solar radiation would be from 10 am to 2 pm (local time), the period that has the lowest values of air mass. Additional useful calculations that can be estimated by the application were the terrestrial irradiances from four empirical models for the clear sky: Roledo-Soler, Adnot, Kasten – Czeplak, and Berger-Duffie. The calculated values of terrestrial irradiance were compared with observed data measured by automatic weather station. The application simulated the actual values with some deviations due to the existence of clouds and aerosols. Kasten – Czeplak model was recommended to be used in Iraq since it was the best model to simulate the measured values. The comparison between the model’s output and the measured values on a daily basis on the 21st of June showed good agreement. The study suggested that the solar panels should face the south direction with a change of the tilt angle of the panels from 25o in June to a value of 60o each month towards the coldest months by an increment of 5 degrees.

show abstract

Estimating Solar Insolation and Power Generation of Photovoltaic Systems Using Previous Day Weather Data

Cited by 14 publications

References 42 publications

Predictive Model for Solar Insolation Using the Deep Learning Technique

Predictive Model for Solar Insolation Using the Deep Learning Technique

A Data-Driven Short-Term PV Generation and Load Forecasting Approach for Microgrid Applications

A Model to Compute the Solar Parameters in Relation to Determining the Optimal Angles for Solar Panels in Many Locations in Iraq

Contact Info

Product

Resources

About