Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Digital Twin for Wind Energy: Latest updates from the NorthWind project

Adil Rasheed, Florian Stadtmann, Eivind Fonn, Mandar Tabib, Vasileios Tsiolakis, Balram Panjwani, Kjetil Andre Johannessen, Trond Kvamsdal, Omer San, John Olav Tande, Idar Barstad, Tore Christiansen, Elling Rishoff, Lars Frøyd, Tore Rasmussen

TL;DR

The paper addresses the challenge of creating scalable digital twins for wind energy by presenting a data-centric NorthWind methodology that combines data acquisition from diverse sources, an asset information model, and a data integration framework with computation-efficient models. It introduces component-based reduced order models and GAN-based superresolution to enable real-time or near real-time operation, validated on onshore and offshore reference wind farms, and augmented by VR/MR visualization for stakeholder engagement. Key contributions include an asset information model, ROM-based speedups up to roughly 10^4, GAN-driven wind field upscaling with up to 100x speedups, and a framework for wind farm layout optimization that aligns with regulatory energy density constraints. The work demonstrates a path toward practical, scalable digital twins that support design, operation, and public decision making in wind energy, across capability levels from descriptive to autonomous.

Abstract

NorthWind, a collaborative research initiative supported by the Research Council of Norway, industry stakeholders, and research partners, aims to advance cutting-edge research and innovation in wind energy. The core mission is to reduce wind power costs and foster sustainable growth, with a key focus on the development of digital twins. A digital twin is a virtual representation of physical assets or processes that uses data and simulators to enable real-time forecasting, optimization, monitoring, control and informed decision-making. Recently, a hierarchical scale ranging from 0 to 5 (0 - Standalone, 1 - Descriptive, 2 - Diagnostic, 3 - Predictive, 4 - Prescriptive, 5 - Autonomous has been introduced within the NorthWind project to assess the capabilities of digital twins. This paper elaborates on our progress in constructing digital twins for wind farms and their components across various capability levels.

Digital Twin for Wind Energy: Latest updates from the NorthWind project

TL;DR

The paper addresses the challenge of creating scalable digital twins for wind energy by presenting a data-centric NorthWind methodology that combines data acquisition from diverse sources, an asset information model, and a data integration framework with computation-efficient models. It introduces component-based reduced order models and GAN-based superresolution to enable real-time or near real-time operation, validated on onshore and offshore reference wind farms, and augmented by VR/MR visualization for stakeholder engagement. Key contributions include an asset information model, ROM-based speedups up to roughly 10^4, GAN-driven wind field upscaling with up to 100x speedups, and a framework for wind farm layout optimization that aligns with regulatory energy density constraints. The work demonstrates a path toward practical, scalable digital twins that support design, operation, and public decision making in wind energy, across capability levels from descriptive to autonomous.

Abstract

NorthWind, a collaborative research initiative supported by the Research Council of Norway, industry stakeholders, and research partners, aims to advance cutting-edge research and innovation in wind energy. The core mission is to reduce wind power costs and foster sustainable growth, with a key focus on the development of digital twins. A digital twin is a virtual representation of physical assets or processes that uses data and simulators to enable real-time forecasting, optimization, monitoring, control and informed decision-making. Recently, a hierarchical scale ranging from 0 to 5 (0 - Standalone, 1 - Descriptive, 2 - Diagnostic, 3 - Predictive, 4 - Prescriptive, 5 - Autonomous has been introduced within the NorthWind project to assess the capabilities of digital twins. This paper elaborates on our progress in constructing digital twins for wind farms and their components across various capability levels.
Paper Structure (30 sections, 15 figures)

This paper contains 30 sections, 15 figures.

Table of Contents

  1. Introduction
  2. Digital twin
  3. Methodology
  4. Data acquisition and generation
  5. Reverse engineering
  6. Synthetic data generation
  7. Structural simulation
  8. Flow around airfoils
  9. High fidelity wind flow in complex terrain
  10. High fidelity wake simulation
  11. Data standardization and management
  12. Asset information model
  13. Data integration framework
  14. Computaionally efficient modeling
  15. Component based reduced order models
  16. ...and 15 more sections

Figures (15)

  • Figure 1: Digital twin concept
  • Figure 2: Capability levels of digital twins
  • Figure 3: High resolution wind field in complex terrain
  • Figure 4: wakes-generated by turbine
  • Figure 5: Data integration framework
  • ...and 10 more figures