Scholarlink

The performance of solar thermal systems is enhanced by using Artificial Intelligence (AI) and Machine Learning (ML). The rise in the demand for renewable energy is coupled with AI and ML, which have strong abilities to improve its subsystems (like hybrid energy dispatch, thermal storage management, cooling, solar distillation, and smart grid integration). In this chapter, a detailed synthesis is provided of recent developments and real-world applications in the use of intelligent forecasting, predictive maintenance, as well as real-time operational control. It introduces a methodological framework that includes data collection, preprocessing, model training, and feedback-based optimization. The architecture is AI centric to ensure ongoing system learning and the capability to adapt to any changes in the environment or operation. Recent literature results also show large gains in energy efficiency, reliability, and cost-effectiveness, as well as measured reductions in greenhouse gas emissions. It is found that research has to continue and along with that, advancements in generative AI, reinforcement learning, and digital twins will be crucial for the development of next-generation smart and sustainable solar thermal energy systems.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Artificial Intelligence and Machine Learning Applications in High-Temperature Solar Thermal Systems

  • 章节

  • 发表日期：

    2025年

查看全文
  • Bharat Girdhani,
  • Nitin Barodia,
  • Yash Chaurasia,
  • Shan Mahto,
  • Deepak Kumar,
  • Meena Agrawal

摘要

The performance of solar thermal systems is enhanced by using Artificial Intelligence (AI) and Machine Learning (ML). The rise in the demand for renewable energy is coupled with AI and ML, which have strong abilities to improve its subsystems (like hybrid energy dispatch, thermal storage management, cooling, solar distillation, and smart grid integration). In this chapter, a detailed synthesis is provided of recent developments and real-world applications in the use of intelligent forecasting, predictive maintenance, as well as real-time operational control. It introduces a methodological framework that includes data collection, preprocessing, model training, and feedback-based optimization. The architecture is AI centric to ensure ongoing system learning and the capability to adapt to any changes in the environment or operation. Recent literature results also show large gains in energy efficiency, reliability, and cost-effectiveness, as well as measured reductions in greenhouse gas emissions. It is found that research has to continue and along with that, advancements in generative AI, reinforcement learning, and digital twins will be crucial for the development of next-generation smart and sustainable solar thermal energy systems.