University of New Mexico Department of Electrical and Computer Engineering Ph.D. candidate Guillermo Terrén-Serrano and Professor Manel Martínez-Ramón, in association with the New Mexico New Mexico Established Program to Stimulate Competitive Research (NM EPSCoR), have developed a artificial intelligence algorithm that optimizes solar energy performance by predicting cloud cover.
On February 19, 2021, the United States officially gathered in 194 other countries as part of the Paris climate agreement. The 2016 US INDC presented by the Obama administration promises a 26-28% reduction in greenhouse gas emissions by 2025 (compared to 2005 emissions).
To achieve this, the United States will need to increase its use of renewable energy sources such as solar energy. However, more research and development is needed to improve the efficiency and reliability of clean energy. To pursue this goal, Terrén-Serrano and Martínez-Ramón are working to address some of the challenges associated with solar energy.
One of these challenges is reliability.
“The problem with solar energy is that it is stochastic in nature: it has a random component due to the presence of clouds. So what we want to do is reduce this randomness and when we know that we will not have enough solar energy, we will be ready to supply this energy with other sources “, explained Martínez-Ramón.
To reduce the randomness of solar energy it is necessary to know when the availability of solar radiation will decrease due to cloud cover. The artificial intelligence algorithm of Terrén-Serrano and Martínez-Ramón is able to learn cloud patterns and predict, based on recent cloud movement, the future output of a solar panel.
The algorithm was trained using cameras and a solar radiation sensor installed on the UNM campus. The camera system was designed by Terrén-Serrano and Martínez-Ramón to follow the sun during the day like a sunflower, simultaneously collecting cloud cover and solar radiation data. The device collects a visual image every 15 seconds and a sample of solar radiation every third of a second.
Managing the data collected by these cameras requires more storage capacity than a personal computer can provide. Terrén-Serrano and Martínez-Ramón used the resources of the Center for Advanced Research Computing to process the data collected by the camera system and train their artificial intelligence algorithm.
“Our work would not be possible without CARC. Also, it is very important to say that my students get a lot of support from the people who work there … so, I want to thank them, “Martínez-Ramón noted.
Once trained using the data collected by the camera, the algorithm will be able to predict future solar production based on current weather conditions. This allows enough time to ensure a backup power source before a power outage occurs.
Terrén-Serrano and Martínez-Ramón are currently preparing three more articles for the magazine for presentation. They plan to launch a website later this year that will allow anyone to see the data from their cameras in real time.
Photo courtesy of Manel Martínez-Ramón and Guillermo Terrén-Serrano
