Posters
Come meet the poster presenters to ask them questions and discuss their work
We would like to invite you to come and see the posters at our upcoming conference. The posters will showcase a diverse range of research topics, and will give delegates an opportunity to engage with the authors and learn more about their work. Whether you are a seasoned researcher or simply curious about the latest developments in your field, we believe that the posters will offer something of interest to everyone. So please join us at the conference and take advantage of this opportunity to learn and engage with your peers in industry and the academic community.
PO320: Optimizing wind farm bid creation with machine learning and generative AI
Jelena Uzunovic, Principal Solutions Architect, Amazon Web Services
Abstract
The offshore wind industry faces a critical transition from government-subsidized models to competitive market-based environments, with global capacity expected to surge from 75 GW to over 480 GW by 2033. Recent market dynamics highlight significant challenges, with over 10 GW of projects cancelled in 2023 due to inadequate business cases and rising capital costs. This presentation introduces an AI-powered solution that transforms wind farm bid creation through advanced machine learning and generative AI capabilities. The solution addresses three critical industry challenges: increasing scale and complexity of tender processes, sophisticated revenue forecasting in evolving markets, and integration of flexibility solutions like batteries into modern wind farm configurations. Our comprehensive architecture leverages cloud technologies through four integrated components: a robust data foundation consolidating cost, revenue, and market intelligence; advanced forecasting models using DeepAR algorithm for intraday price prediction; intelligent optimization engines for flexibility component configurations; and an agentic orchestration system powered by an multi-agent collaboration framework. The solution enables rapid bid iteration with sophisticated optimization while maintaining tender compliance. Through natural language interfaces and automated analysis, teams can evaluate multiple scenarios and make data-driven decisions faster than traditional manual approaches. Two demonstration agents were implemented: a Market Data Agent with direct ENTSO-E API integration and a Tender Knowledge Agent utilizing historical tender databases. This technological advancement is crucial as auction volumes increase and market complexity grows, enabling developers to evaluate more opportunities with greater sophistication while maintaining profitability in an increasingly competitive landscape.
No recording available for this poster.
