An in-depth study reveals the impact of integrating AI into solar photovoltaics
Artificial intelligence will enhance photovoltaic systems by improving the efficiency, reliability and predictability of solar energy generation.
In their paper, published May 8 in CAAI Artificial Intelligence Research, a research team from Chinese and Malaysian universities examined the impact of artificial intelligence (AI) technology on photovoltaic (PV) power generation systems and their applications worldwide.
“The overall message is an optimistic view of how AI can lead to more sustainable and efficient energy solutions,” said Xiaoyun Tian of Beijing University of Technology. “By improving the efficiency and deployment of renewable energy sources through AI, there is significant potential to reduce global CO2 emissions and make clean energy more accessible and reliable to a broader population.”
The team, consisting of researchers from Beijing University of Technology, Chinese Academy of Sciences, Hebei University and Universiti Tunku Abdul Rahman, focused their research on key applications of AI in maximum power point tracking, power prediction and fault detection within PV systems. .
The maximum power point (MPP) refers to the specific operating point where a PV cell or an entire PV array delivers its peak power under the prevailing lighting conditions. Tracking and utilizing the point of maximum power by adjusting the operating point of the PV array to maximize output power is a critical issue in solar PV systems. Traditional methods have flaws, resulting in reduced efficiency, hardware wear and suboptimal performance during sudden weather changes.
The researchers reviewed publications that show how AI techniques can achieve high performance in solving the MPP tracking problem. They compiled methods that presented both single and hybrid AI methods to solve the tracking problem, examining the pros and cons of each approach.
The team reviewed publications presenting AI algorithms applied to PV power prediction and defect detection technologies. Power forecasting, which predicts PV energy production over time, is critical for PV grid integration as the share of solar energy in the mix increases annually. Fault detection in PV systems can identify various types of faults, such as changes in the environment, damage to panels and wiring errors. For large-scale PV systems, traditional manual inspection is virtually impossible. AI algorithms can identify deviations from normal operating conditions that can proactively indicate errors or anomalies.
The research team compared AI-driven techniques and examined and presented the pros and cons of each approach.
Although the integration of AI technology optimizes the operational efficiency of PV systems, new challenges continue to arise. These challenges are driven by issues such as revised standards for achieving carbon neutrality, interdisciplinary collaboration and emerging smart grids.
The researchers highlighted a number of emerging challenges and the need for advanced solutions in AI, such as transfer learning, few-shot learning and edge computing.
According to the paper’s authors, next steps should focus on further research aimed at advancing AI techniques that address the unique challenges of PV systems; practical implementation of AI solutions in existing PV infrastructure on a larger scale; scaling successful AI integration; developing supportive policy frameworks that encourage the use of AI in renewable energy; increasing awareness of the benefits of AI in improving the efficiency of PV systems; and ultimately align these technological advances with global sustainability goals.
“AI-driven techniques are essential for the future development and widespread adoption of solar energy technologies worldwide,” said Tian.
The research was supported by the National Key R and D Program of China and the Fundamental Research Grant Scheme of Malaysia. The grants are part of the China-Malaysia Intergovernmental Science, Technology and Innovation Cooperative Program 2023.
Other contributors include Jiaming Hu, Kang Wang and Dachuan Xu from Beijing University of Technology; Boon-Han Lim from Universiti Tunku Abdul Rahman; Feng Zhang from Hebei University; and Yong Zhang of Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences.
Research report:A comprehensive overview of applications of artificial intelligence in photovoltaic systems
