Artificial Intelligence-Based Optimal Power Flow under Renewable Uncertainty

Unofficial AI-generated summary based on the public title and abstract. Not an official translation.

🔬研究者:Provides a structured overview of AI-based OPF methods and identifies key research gaps for future work.

🏢実務担当者:Offers insights into how AI can improve power system operation with renewable uncertainty, relevant for grid operators.

🏛政策担当者:Highlights the potential of AI to support renewable integration and reduce emissions, informing energy policy on grid modernization.

<title>Abstract</title> <p>The swift worldwide shift to the low-carbon energy regimes has resulted in the significant growth in the utilisation of renewable energy sources, including wind and solar energy. Although this change is necessary to reach the sustainability and climate goals, it provides the power system operators with a considerable challenge because of the existing uncertainty, variability, and intermittency of renewable generation. Optimal power flow is a key focus of providing a secure, economical and reliable operation of power systems, but the traditional optimization-based OPF methods cannot effectively address large scale nonlinearity, nonconvexity and real time uncertainty presented by renewable-rich grids. Artificial intelligence has recently become a viable alternative and supplementary measure to deal with such issues. The paper is a systematic review of how artificial intelligence techniques are applied to optimal power flow issues when there is uncertainty regarding renewable. The systematic review procedure is used, and the literature that was found in the major scientific databases within the last decade is covered. The review incorporates the current studies on AI-based OPF formulations, uncertainty modelling approaches, and performance evaluation practises. The major conclusions made are that AI-based methods have significant benefits in terms of computational efficiency, scalability, and ability to adapt to uncertain operating conditions, but there are still generalisation, interpretability, and data dependency challenges involved. The paper also addresses the implications of sustainability whereby AI-enabled OPF contributes to higher combine of renewable, cut operational emission and emerges as a power system operation resilience. Lastly, possible critical research gaps and future directions are also determined to inform the design of reliable and sustainable AI-based OPF solutions.</p>

• Research Square https://doi.org/10.21203/rs.3.rs-9293029/v1first seen 2026-06-04 04:24:11 · last seen 2026-06-16 04:30:26