An official website of the United States government
Variation in solar irradiance causes power generation fluctuations in solar power plants. Power grid operators need accurate irradiance forecasts to manage this variability. Many factors affect irradiance, including the time of year, weather and time of day. Cloud cover is one of the most important variables that affects solar power generation, but is also characterized by a high degree of variability and uncertainty. Deep learning methods have the ability to learn long-term dependencies within sequential data. We investigate the application of Gated Recurrent Units (GRU) to forecast solar irradiance and present the results of applying multivariate GRU to forecast hourly solar irradiance in Phoenix, Arizona. We compare and evaluate the performance of GRU against Long Short-Term Memory (LSTM) using strictly historical solar irradiance data as well as the addition of exogenous weather variables and cloud cover data. Based on our results, we found that the addition of exogenous weather variables and cloud cover data in both GRU and LSTM significantly improved forecasting accuracy, performing better than univariate and statistical models.
more »
« less
This content will become publicly available on August 1, 2026
Climate change impacts on solar energy generation in the continental United States, forecasts from deep learning
Large-scale solar promises a low-carbon energy alternative. However, solar production in North America given anticipated climate change has been studied only seasonally in terms of solar irradiance. This work integrates more of the predictive potential of climate-change models by exploring other environmental variables, such as humidity and temperature. Here, a Continental US (CONUS) model is produced by deep learning using 2593 NREL simulated solar power stations. Daily forecasts using 17 Global Climate Models (GCM’s) through 2099 are summarized monthly. Results suggest power production factors change between +4 % and 19 % over 93 years. These results suggest more, but still modest, potential declines than previous solar irradiance-based studies. The modest impact is encouraging. For some areas, climate model variability unfortunately yielded statistically insignificant trends and practical application is less clear. For future evaluations, this work suggests the potential importance of additional variables, monthly interval summary, and accounting for model variability.
more »
« less
- Award ID(s):
- 1856084
- PAR ID:
- 10610524
- Publisher / Repository:
- Elsevier
- Date Published:
- Journal Name:
- Environmental Modelling & Software
- Volume:
- 192
- Issue:
- C
- ISSN:
- 1364-8152
- Page Range / eLocation ID:
- 106535
- Subject(s) / Keyword(s):
- Climate Change Impact Deep Learning Environmental Modeling Machine Learning Solar Energy Solar Energy Forecasting Photovoltaic Systems United States
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
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.more » « less
-
Cloud cover estimation from images taken by sky-facing cameras can be an important input for analyzing current weather conditions and estimating photovoltaic power generation. The constant change in position, shape, and density of clouds, however, makes the development of a robust computational method for cloud cover estimation challenging. Accurately determining the edge of clouds and hence the separation between clouds and clear sky is difficult and often impossible. Toward determining cloud cover for estimating photovoltaic output, we propose using machine learning methods for cloud segmentation. We compare several methods including a classical regression model, deep learning methods, and boosting methods that combine results from the other machine learning models. To train each of the machine learning models with various sky conditions, we supplemented the existing Singapore whole sky imaging segmentation database with hazy and overcast images collected by a camera-equipped Waggle sensor node. We found that the U-Net architecture, one of the deep neural networks we utilized, segmented cloud pixels most accurately. However, the accuracy of segmenting cloud pixels did not guarantee high accuracy of estimating solar irradiance. We confirmed that the cloud cover ratio is directly related to solar irradiance. Additionally, we confirmed that solar irradiance and solar power output are closely related; hence, by predicting solar irradiance, we can estimate solar power output. This study demonstrates that sky-facing cameras with machine learning methods can be used to estimate solar power output. This ground-based approach provides an inexpensive way to understand solar irradiance and estimate production from photovoltaic solar facilities.more » « less
-
Abstract Climate change threatens the resource adequacy of future power systems. Existing research and practice lack frameworks for identifying decarbonization pathways that are robust to climate‐related uncertainty. We create such an analytical framework, then use it to assess the robustness of alternative pathways to achieving 60% emissions reductions from 2022 levels by 2040 for the Western U.S. power system. Our framework integrates power system planning and resource adequacy models with 100 climate realizations from a large climate ensemble. Climate realizations drive electricity demand; thermal plant availability; and wind, solar, and hydropower generation. Among five initial decarbonization pathways, all exhibit modest to significant resource adequacy failures under climate realizations in 2040, but certain pathways experience significantly less resource adequacy failures at little additional cost relative to other pathways. By identifying and planning for an extreme climate realization that drives the largest resource adequacy failures across our pathways, we produce a new decarbonization pathway that has no resource adequacy failures under any climate realizations. This new pathway is roughly 5% more expensive than other pathways due to greater capacity investment, and shifts investment from wind to solar and natural gas generators. Our analysis suggests modest increases in investment costs can add significant robustness against climate change in decarbonizing power systems. Our framework can help power system planners adapt to climate change by stress testing future plans to potential climate realizations, and offers a unique bridge between energy system and climate modeling.more » « less
-
Abstract The United States (U.S.) West Coast power system is strongly influenced by variability and extremes in air temperatures (which drive electricity demand) and streamflows (which control hydropower availability). As hydroclimate changes across the West Coast, a combination of forces may work in tandem to make its bulk power system more vulnerable to physical reliability issues and market price shocks. In particular, a warmer climate is expected to increase summer cooling (electricity) demands and shift the average timing of peak streamflow (hydropower production) away from summer to the spring and winter, depriving power systems of hydropower when it is needed the most. Here, we investigate how climate change could alter interregional electricity market dynamics on the West Coast, including the potential for hydroclimatic changes in one region (e.g., Pacific Northwest (PNW)) to “spill over” and cause price and reliability risks in another (e.g., California). We find that the most salient hydroclimatic risks for the PNW power system are changes in streamflow, while risks for the California system are driven primarily by changes in summer air temperatures, especially extreme heat events that increase peak system demand. Altered timing and amounts of hydropower production in the PNW do alter summer power deliveries into California but show relatively modest potential to impact prices and reliability there. Instead, our results suggest future extreme heat in California could exert a stronger influence on prices and reliability in the PNW, especially if California continues to rely on its northern neighbor for imported power to meet higher summer demands.more » « less
