A team of Chinese scientists has developed an artificial intelligence tool that can help find the best location to install double-sided solar panels, thereby filling a critical data gap in the green energy industry. their single-faced counterparts. According to the researchers, placing them in the eastern Tibetan Plateau and other places in northwest China could help maximize solar energy production. The energy production potential of a double-sided photovoltaic (PV) panel is highly dependent on how much diffuse solar radiation reaches its backside. , the team explained in a paper last month in the peer-reviewed Journal of Remote Sensing.
01:36
China’s largest photovoltaic power plant is driving the development of a new form of energy
China’s largest photovoltaic power plant is driving the development of a new form of energy
Under the right sunlight conditions, double-sided solar panels can produce more energy than conventional panels. However, they are difficult to transport and store, so finding the optimal location for them is critical to ensure the best use of resources.
However, there is no information to help determine the best locations to place double-sided solar panels.
There are a total of 17 radiation stations in the country that collect data on the amount and type of “solar energy” available at a given location. This includes information on direct radiation from the sun directly onto the front surface of the solar panel and diffuse radiation that is scattered by the atmosphere and more likely to be captured by the back face of the panel.
The equipment in these stations requires annual adjustment and regular maintenance, which leads to significant operating costs.
To overcome the lack of local data, researchers from Tsinghua University in Beijing and the National Tibetan Plateau Data Center created an artificial intelligence model based on sunlight data from 2,500 weather stations across China.
Artificial intelligence is trained on solar radiation data and surface meteorological data collected through ground observation or satellite remote sensing to predict the amount of direct and indirect radiation at any given point.
“In principle, this model can be applied globally without additional training with local data,” the team wrote.
According to the study, China needs 10 times more energy from solar and wind to become carbon neutral
Lead author Yang Kun, a professor in the department of earth system sciences at Tsinghua, said the lack of comprehensive radiation data means there is little information to help authorities and the solar industry plan areas for installing panels.
“Now, the output of an artificial intelligence model supported by satellite data can inform decision-making about where and what type of panels to place to take full advantage of solar energy,” Yang said.
Solar energy will account for about 5 percent of China’s electricity generation in 2022.
Yang said the AI system also revealed the solar potential of China’s remote areas without power line infrastructure, which could inspire future research and policy planning.
China generates half the amount of electricity in the western deserts as the United States
First author Shao Changkun, a PhD candidate at Tsinghua, said the area surrounding the Taklamakan Desert in the southwestern part of Xinjiang Autonomous Region and the eastern Tibetan Plateau is an ideal location for the double-sided panels.
“Direct solar radiation is high in the high altitude plateau where the air is thinner, while diffuse solar radiation is important due to the complex landscape and high cloud cover,” he said.
“Both sides of the solar panels will receive large amounts of radiation in these regions.”
The team compared their estimates with radiation data from around the world and found their AI model to be highly accurate, Shao said, adding that combining the input data with meteorological data from other countries could help the system be used for global solar radiation forecasts. can
Young added that the data could be applied to other fields, such as agriculture, because plants can perform photosynthesis more efficiently under diffuse light conditions.