• Atmosphere
• /
• v.34 no.2
• /
• pp.177-185
• /
• 2024

As increasing global interest in renewable energy due to the ongoing climate crisis, there is a growing need for efficient technologies to manage such resources. This study focuses on the predictive skill of daily solar power generation using weather observation and forecast data. Meteorological data from the Korea Meteorological Administration and solar power generation data from the Korea Power Exchange were utilized for the period from January 2017 to May 2023, considering both inland (Daejeon) and coastal (Busan) regions. Temperature, wind speed, relative humidity, and precipitation were selected as relevant meteorological variables for solar power prediction. All data was preprocessed by removing their systematic components to use only their residuals and the residual of solar data were further processed with weighted adjustments for homoscedasticity. Four models, MLR (Multiple Linear Regression), RF (Random Forest), DNN (Deep Neural Network), and RNN (Recurrent Neural Network), were employed for solar power prediction and their performances were evaluated based on predicted values utilizing observed meteorological data (used as a reference), 1-day-ahead forecast data (referred to as fore1), and 2-day-ahead forecast data (fore2). DNN-based prediction model exhibits superior performance in both regions, with RNN performing the least effectively. However, MLR and RF demonstrate competitive performance comparable to DNN. The disparities in the performance of the four different models are less pronounced than anticipated, underscoring the pivotal role of fitting models using residuals. This emphasizes that the utilized preprocessing approach, specifically leveraging residuals, is poised to play a crucial role in the future of solar power generation forecasting.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.10
• /
• pp.1423-1427
• /
• 2014

Quantity of the solar power generation is heavily influenced by weather. In other words, due to difference in insolation, different quantity may be generated. However, it does not mean all areas with identical insolation produces same quantity because of various environmental aspects. Additionally, geographic factors such as altitude, height of plant may have an impact on the quantity. Hence, through this research, we designed a system to predict efficiency of the solar power generation system by applying insolation, weather factor such as duration of sunshine, cloudiness parameter and location. By applying insolation, weather data that are collected from various places, we established a system that fits with our nation. Apart from, we produced a geographic model equation through utilizing generated data installed nationwide. To design a prediction model that integrates two factors, we apply fuzzy algorithm, and validate the performance of system by establishing simulation system.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.10
• /
• pp.353-360
• /
• 2016

Recently, solar photovoltaic(PV) power generation which generates electrical power from solar panels composed of multiple solar cells, showed the most prominent growth in the renewable energy sector worldwide. However, in spite of increased demand and need for a photovoltaic power generation, it is difficult to early detect defects of solar panels and equipments due to wide and irregular distribution of power generation. In this paper, we choose an optimal machine learning algorithm for estimating the generation amount of solar power by considering several panel information and climate information and develop a defect detection system by using the chosen algorithm generation. Also we apply the algorithm to a domestic solar photovoltaic power plant as a case study.

• Convergence Security Journal
• /
• v.22 no.2
• /
• pp.99-104
• /
• 2022

This study provided a prediction model for solar energy production in Yeongam province, Jeollanam-do. The model was derived from the correlation between climate changes and solar power production in Yeongam province, Jeollanam-do, and presented a prediction of solar power generation through the regression analysis of 6 parameters related to weather and solar power generation. The data used in this study were the weather and photovoltaic production data from January in 2016 to December in 2019 provided by public data. Based on the data, the machine learning technique was used to analyzed the correlation between weather change and solar energy production and derived to the prediction model. The model showed that the photovoltaic production can be categorized by the three-stage production index and will be used as an important barometer in the agriculture activity and the use of photovoltaic electricity.

• Journal of Internet of Things and Convergence
• /
• v.8 no.3
• /
• pp.55-61
• /
• 2022

In order to reduce greenhouse gases, the main culprit of global warming, the United Nations signed the Climate Change Convention in 1992. Korea is also pursuing a policy to expand the supply of renewable energy to reduce greenhouse gas emissions. The expansion of renewable energy development using solar power led to the expansion of wind power and solar power generation. The expansion of renewable energy development, which is greatly affected by weather conditions, is creating difficulties in managing the supply and demand of the power system. To solve this problem, the power brokerage market was introduced. Therefore, in order to participate in the power brokerage market, it is necessary to predict the amount of power generation. In this paper, the prediction system was used to analyze the Yonchuk solar power plant. As a result of applying solar insolation from on-site (Model 1) and the Korea Meteorological Administration (Model 2), it was confirmed that accuracy of Model 2 was 3% higher. As a result of comparative analysis of the DNN and RNN models, it was confirmed that the prediction accuracy of the DNN model improved by 1.72%.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.2
• /
• pp.383-388
• /
• 2024

This paper is a study to derive the predicted value of power generation based on the photovoltaic power generation data measured in Jeollanam-do, South Korea. Multivariate variables such as direct current, alternating current, and environmental data were measured in the inverter to measure the amount of power generation, and pre-processing was performed to ensure the stability and reliability of the measured values. Correlation analysis used only data with high correlation with power generation in time series data for prediction using partial autocorrelation function (PACF). Deep learning models were used to measure the amount of power generation to predict the amount of photovoltaic power generation, and the results of correlation analysis of each multivariate variable were used to increase the prediction accuracy. Learning using refined data was more stable than when existing data were used as it was, and the solar power generation prediction algorithm was improved by using only highly correlated variables among multivariate variables by reflecting the correlation analysis results.

• Journal of Digital Convergence
• /
• v.18 no.12
• /
• pp.267-278
• /
• 2020

ESS is an essential requirement for resolving power shortages and power demand management and promoting renewable energy at a time when the energy paradigm changes. In this paper, we propose a cost-effective ESS Peak-Shaving operation plan through load and solar power generation forecast. For the ESS operation plan, electric load and solar power generation were predicted through RMS, which is a statistical measure, and a target load reduction guideline for one hour was set through the predicted electric load and solar power generation amount. The load and solar power generation amount from May 6th to 10th, 2019 was predicted by simulation of load and photovoltaic power generation using real data of the target customer for one year, and an hourly guideline was set. The average error rate for predicting load was 7.12%, and the average error rate for predicting solar power generation amount was 10.57%. Through the ESS operation plan, it was confirmed that the hourly guide-line suggested in this paper contributed to the peak-shaving maximization of customers.Through the results of this paper, it is expected that future energy problems can be reduced by minimizing environmental problems caused by fossil energy in connection with solar power and utilizing new and renewable energy to the maximum.

• Current Photovoltaic Research
• /
• v.5 no.1
• /
• pp.33-37
• /
• 2017

Today, photovoltaic power generation mostly uses Si crystalline solar cell modules. The most vulnerable part of the Si solar cell module is that the power generation decreases due to the temperature rise. But, it is widely used because of low installation cost. In the solar market, where Si crystalline solar cell modules are widely used. The CPV (Concentrated Photovoltaic) module appeared in the solar market. The CPV module reduces the manufacturing cost of the solar cell by using non-Si in the solar cell. Also, there is an advantage that a rise in temperature does not cause a drop in power generation. But this requires high technology to install and has a disadvantage that the initial installation cost is expensive compared to normal Si solar cell module. So that we built a testbed to see these characteristics. The testbed was used to measure the amount of power generation in a long-term outdoor environment and compared with the general Si solar cell module.

• Journal of the Korean Solar Energy Society
• /
• v.33 no.6
• /
• pp.62-69
• /
• 2013

In this paper, Korea Institute of Energy Research, building integrated renewable energy monitoring system that utilizes solar power generation forecast data forecast model is proposed. Renewable energy integration of real-time monitoring system based on monitoring data were building a database and the database of the weather conditions and to study the correlation structure was tailoring. The weather forecast cloud cover data, generation data, and solar radiation data, a data mining and time series analysis using the method developed models to forecast solar power. The development of solar power in order to forecast model of weather forecast data it is important to secure. To this end, in three hours, including a three-day forecast today Meteorological data were used from the KMA(korea Meteorological Administration) site offers. In order to verify the accuracy of the predicted solar circle for each prediction and the actual environment can be applied to generation and were analyzed.

• Communications for Statistical Applications and Methods
• /
• v.29 no.6
• /
• pp.709-719
• /
• 2022

Recently, as the importance of environmental protection has emerged, interest in new and renewable energy is also increasing worldwide. In particular, the solar energy sector accounts for the highest production rate among new and renewable energy in Korea due to its infinite resources, easy installation and maintenance, and eco-friendly characteristics such as low noise emission levels and less pollutants during power generation. However, although climate prediction is essential since solar power is affected by weather and climate change, solar radiation, which is closely related to solar power, is not currently forecasted by the Korea Meteorological Administration. Solar radiation prediction can be the basis for establishing a reasonable new and renewable energy operation plan, and it is very important because it can be used not only in solar power but also in other fields such as power consumption prediction. Therefore, this study was conducted for the purpose of improving the accuracy of solar radiation. Solar radiation was predicted by a total of three weather variables, temperature, humidity, and cloudiness, and solar radiation outside the atmosphere, and the results were compared using various models. The CatBoost model was best obtained by fitting and comparing the Boosting series (XGB, CatBoost) and RNN series (Simple RNN, LSTM, GRU) models. In addition, the results were further improved through Time series cross-validation.