AI-driven solutions in renewable energy: A review of data science applications in solar and wind energy optimization

In recent years, renewable energy technologies (RETs) have become increasingly popular worldwide to achieve energy sufficiency, reduce reliance on conventional fuels, and mitigate their devastating environmental impact. Nonetheless, more appears to have stayed the same in emerging economies, such as Tunisia, as various barriers hampered the implementation of these technologies. Hence, the prime objective of this article is to conduct a thoughtful assessment of four prominent renewable energy options for electricity generation and explore the most potential barriers hindering their development in Tunisia. To do so, a two-stage approach was applied. First, CRiteria Importance Through Inter-Criteria Correlation (CRITIC) and Evaluation based on Distance from Average Solution (EDAS) were used to evaluate the considered alternatives, namely solar PV, concentrated solar power (CSP), onshore wind, and biomass. Then, an integrated step-wise assessment ratio analysis and decision-making trial and evaluation laboratory approach (SWARA-DEMATEL) was developed to identify the most relevant barriers. The related criteria and barriers were determined based on an exhaustive literature review and experts’ feedback. The obtained results indicated that solar PV and wind were the most promising renewable technologies, while biomass was the worst option. To validate the outcome and demonstrate the effect of changing input data on the final results, a sensitivity analysis has been carried out. As for the key obstacles, political instability, high upfront costs, and market access mechanisms were the most influential barriers. Hence, prioritizing different RETs and analyzing the inherent barriers to their utilization would offer insightful guidance to policymakers, enabling them to establish efficient strategies for overcoming these obstacles, and accelerating the deployment of these technologies in the country.

show abstract

Exploring the Intersection of Sustainable Energy, AI, and Ethical Considerations

Jayasutha,

Vijaya Prabhu,

Sassirekha

et al. 2024

Practice, Progress, and Proficiency in Sustainability

View full text Add to dashboard Cite

Renewable energy, machine learning (ML), artificial intelligence (AI), and sustainable energy ethics are explored in this study. It explores salinity gradient, blue, osmotic, and hydrogen storage renewable energy sources, green mobility, and power production to minimise fossil fuel consumption and carbon emissions. AI and ML improve energy, blue energy, industrial efficiency, and infrastructure. The chapter emphasises openness, accountability, and justice in AI and ML ethics. Sustainable energy and SDG alignment need strong policy and governance frameworks. AI is being studied in climate forecasting, ocean precision modelling, and environmental monitoring. Inclusivity, justice, and equality are ethical. This chapter continues with an overview of AI, ML, green energy, and ethics, covering trends, problems, and legal frameworks for sustainable energy.

show abstract

AI-driven solutions in renewable energy: A review of data science applications in solar and wind energy optimization

Cited by 3 publications

References 22 publications

Indicators to Digitization Footprint and How to Get Digitization Footprint (Part 2)

Indicators to Digitization Footprint and How to Get Digitization Footprint (Part 2)

Prioritizing sustainable renewable energy systems in Tunisia: An integrated approach using hybrid multi-criteria decision analysis

Exploring the Intersection of Sustainable Energy, AI, and Ethical Considerations

Contact Info

Product

Resources

About