Hybrid prediction model improves photovoltaic power output predictions in variable weather – AIP.ORG

Advancing Sustainable Development Goals through Innovative Solar Energy Prediction

Introduction: Enhancing Clean Energy Reliability for Sustainable Infrastructure

The transition to renewable energy sources is a cornerstone of achieving Sustainable Development Goal 7 (Affordable and Clean Energy) and SDG 13 (Climate Action). Solar energy, while a leading clean energy source, presents significant challenges to grid stability due to its inherent variability. This report details a new predictive model designed to mitigate these challenges, thereby supporting the development of resilient infrastructure (SDG 9) and sustainable communities (SDG 11).

• The intermittent nature of solar power, influenced by weather conditions, complicates the operation of safe and reliable power grids.
• Short-term fluctuations in power output from photovoltaic (PV) systems necessitate accurate forecasting to ensure grid stability and efficient energy management.
• Improving prediction accuracy is critical for integrating a higher share of renewables into the energy mix, directly contributing to SDG 7 targets.

A Novel Predictive Methodology for Photovoltaic Systems

Researchers Gaoxuan Chen and Lingwei Zheng have developed an innovative method for short-term PV power generation prediction. This approach leverages interdisciplinary theories to create a more robust forecasting tool, representing a significant technological innovation in support of sustainable energy systems.

1. The model employs a hybrid network that combines a graph neural network (GNN) with a long short-term memory (LSTM) network.
2. It applies chaotic system analysis methods, specifically phase space reconstruction, to model the evolution of the PV system’s power output.
3. This hybrid approach successfully preserves the complex, nonlinear dynamics of the system, leading to superior model performance and more reliable predictions.

Key Findings and Contributions to SDG 7

When tested on a photovoltaic microgrid system, the model demonstrated a significant improvement in prediction accuracy across various atmospheric conditions. These results have direct implications for enhancing the reliability and efficiency of clean energy infrastructure.

• The model substantially improved forecasting accuracy on clear, cloudy, and rainy days, addressing the core challenge of weather-dependent variability.
• By providing more accurate predictions, the model enables power system operators to better manage grid loads, reduce reliance on fossil-fuel backup generators, and facilitate a deeper penetration of solar energy, directly advancing the objectives of SDG 7 and SDG 13.

Broader Implications for Sustainable Development

The applications of this predictive model extend beyond solar energy, offering potential advancements in various fields critical to achieving the broader Sustainable Development Goals.

• Renewable Energy: The model can be adapted for other variable renewable sources, such as wind power.
• Climate Action (SDG 13): Improved meteorological and weather forecasting capabilities.
• Sustainable Cities and Communities (SDG 11): Applications in the Internet of Things (IoT) for managing urban infrastructure.
• Economic Growth (SDG 8): Potential use in financial market prediction.
• Good Health and Well-being (SDG 3): Applications in biomedicine for time series data analysis.

Future Directions and Challenges

While this innovation represents a significant step forward, further research is required to refine its capabilities. Overcoming current challenges will enhance prediction capabilities and accelerate the transition to sustainable systems.

• Addressing the instability of periodic orbits within chaotic systems remains an open challenge.
• Future work will focus on integrating physical constraints into the model’s calculations to improve accuracy and real-world applicability.

Source Reference

Chen, G., & Zheng, L. (2025). Short-term prediction method of PV output sequence based on the phase space reconstruction and GAT-LSTM hybrid model. Journal of Renewable and Sustainable Energy. https://doi.org/10.1063/5.0281896

1. Which SDGs are addressed or connected to the issues highlighted in the article?

SDG 7: Affordable and Clean Energy

• The article’s central theme is the improvement of solar energy, which it describes as a “premier renewable energy source.” This directly aligns with SDG 7, which aims to ensure access to affordable, reliable, sustainable, and modern energy for all. The research focuses on overcoming a key challenge of solar power—its “variable output”—to make it a more reliable component of the energy system.

SDG 9: Industry, Innovation and Infrastructure

• The article explicitly mentions the difficulty of operating “safe and reliable power grids” due to fluctuations in solar power output. The developed prediction model is designed to create more stable and resilient energy infrastructure. This connects directly to SDG 9’s goal of building resilient infrastructure, promoting inclusive and sustainable industrialization, and fostering innovation.

SDG 13: Climate Action

• Solar energy is a critical technology for mitigating climate change by reducing reliance on fossil fuels. By enhancing the viability and integration of solar power, the research contributes to climate action. Furthermore, the article notes the model’s potential applications in “weather forecasting,” which is essential for climate change adaptation and early warning systems, a key aspect of SDG 13.

2. What specific targets under those SDGs can be identified based on the article’s content?

SDG 7: Affordable and Clean Energy

• Target 7.2: By 2030, increase substantially the share of renewable energy in the global energy mix. The article’s focus on a new method to improve “power generation prediction” for solar energy directly supports this target. By making solar power more predictable and easier to manage, the technology facilitates its wider adoption and integration into power grids, thereby helping to increase its share in the energy mix.
• Target 7.a: By 2030, enhance international cooperation to facilitate access to clean energy research and technology, including renewable energy… and promote investment in energy infrastructure and clean energy technology. The research paper itself, titled “Short-term prediction method of PV output sequence…”, represents an advancement in clean energy technology and research, which is the core of this target.

SDG 9: Industry, Innovation and Infrastructure

• Target 9.1: Develop quality, reliable, sustainable and resilient infrastructure… to support economic development and human well-being. The article highlights that the goal of the new prediction model is to help “operate safe and reliable power grids.” This directly addresses the need for reliable and resilient energy infrastructure, which is a cornerstone of this target.

SDG 13: Climate Action

• Target 13.3: Improve education, awareness-raising and human and institutional capacity on climate change mitigation, adaptation, impact reduction and early warning. The article mentions that the model has applications in “weather forecasting.” Improved forecasting is a critical tool for early warning systems related to extreme weather events, which are intensifying due to climate change. This enhances institutional capacity for climate adaptation.

3. Are there any indicators mentioned or implied in the article that can be used to measure progress towards the identified targets?

SDG 7: Affordable and Clean Energy

• Indicator 7.2.1: Renewable energy share in the total final energy consumption. While the article does not state this indicator, its entire purpose is to solve a problem (“variable output”) that hinders the large-scale adoption of solar power. The success of such technologies can be measured by the resulting increase in the share of solar energy in the overall energy mix.

SDG 9: Industry, Innovation and Infrastructure

• Implied Indicator: Accuracy of power generation prediction. The article provides a direct measure of progress by stating that the model was “able to significantly improve predictions on clear, cloudy, and rainy days.” This improved accuracy is a direct indicator of the technology’s contribution to making power grids more reliable and resilient, as it allows operators to better prepare for and manage power fluctuations.

SDG 13: Climate Action

• Implied Indicator: Enhanced accuracy of meteorological forecasting. The article suggests the model’s applicability to “meteorological science” and “weather forecasting.” Progress could be measured by the degree to which this or similar models improve the accuracy and lead time of weather predictions, which are crucial for climate change adaptation and early warning systems.

4. Create a table with three columns titled ‘SDGs, Targets and Indicators” to present the findings from analyzing the article. In this table, list the Sustainable Development Goals (SDGs), their corresponding targets, and the specific indicators identified in the article.

Source: aip.org