Optimization of Collaborative Vessel Scheduling for Offshore Wind Farm Installation Under Weather Uncertainty

Shengguan Qu, Changmao Yu, Yang Zhou, Y. Thomas Hou, J Wang, Fenglei LiJournal of Marine Science and Engineering 2026 · DOI

TL;DR

This paper tackles the complex challenge of scheduling vessels for offshore wind farm installations, a process heavily impacted by weather and the coordination of multiple vessel types. They introduce a novel hierarchical optimization framework that effectively balances cost, efficiency, and weather resilience, achieving significant cost reductions in real-world case studies.

What Problem Does This Paper Address?

Building offshore wind farms (OWFs) is a massive undertaking, and a significant chunk of its cost comes down to logistics. Specifically, the scheduling of specialized installation vessels (IVs) and transport vessels (TVs) is critical. This isn't just about getting from point A to point B; it involves intricate coordination to deliver components, position massive turbines, and perform installations within tight weather windows. The inherent uncertainty of weather, especially wind speed, can cause costly delays and disruptions. Existing approaches often struggle to simultaneously optimize the routes for multiple vessel types, account for complex operational constraints, and robustly handle weather variability. This paper aims to bridge that gap by providing a comprehensive framework for collaborative vessel scheduling that is both efficient and resilient to unpredictable weather.

Methods

The authors propose a constraint-driven hierarchical optimization framework. This approach breaks down the complex problem into manageable parts:

  1. Mixed-Integer Linear Programming (MILP) Model: They first formulate a detailed MILP model to capture all operational constraints, including the tight coupling between installation and transport vessels.
  2. Decomposition into Sub-problems: To overcome the computational burden of the MILP, the problem is decomposed into two main stages:
  3. Vessel Path Planning: This is framed as a Multiple Traveling Salesman Problem (MTSP). To ensure balanced workloads among installation vessels, they employ a tailored three-stage heuristic that combines balanced sweep clustering with penalized local search.
  4. Scheduling Optimization: Here, they use a hybrid Earliest Deadline First (EDF)-Simulated Annealing (SA) strategy. EDF provides a quick, feasible baseline schedule, which SA then refines to find a globally optimal or near-optimal solution.
  5. Stochastic Optimization: To address weather uncertainty, historical meteorological data is integrated. This allows the framework to generate schedules that are robust against varying weather conditions, rather than assuming ideal weather.

Datasets

The study utilizes data from two real-world offshore wind farm projects:

  • Zhuhai Jinwan Wind Farm (Wind Farm 1): A 55-turbine project.
  • Swedish Poseidon Wind Farm (Wind Farm 2): A 61-turbine project.

Specific input data, including charter costs, operational durations, and sailing speeds, were derived from actual project data and expert consultations. Wind speed data for the South China Sea region (March-May and September-November) was sourced from the EPW MAP for the stochastic analysis.

Key Insights and Ideas

  • The Power of Decomposition: Breaking down the complex MILP into path planning and scheduling sub-problems, and then using specialized heuristics and metaheuristics for each, is crucial for tackling large-scale, real-world problems.
  • Balancing Workloads is Key: Modeling the problem as an MTSP and explicitly aiming for balanced fleet workloads prevents bottlenecks and ensures smoother project execution.
  • EDF-SA Synergy: Using EDF to generate a strong initial feasible solution significantly speeds up and improves the performance of the Simulated Annealing algorithm, leading to better optimization.
  • Weather is Not an Afterthought: Integrating stochastic weather modeling is essential for creating truly resilient and cost-effective installation plans, moving beyond deterministic assumptions.
  • Fleet Size as a Hedge: For smaller projects, increasing fleet size can be a critical strategy to mitigate weather-induced delays. For larger projects, a slightly larger fleet offers robust resilience that can outweigh increased rental costs.

Key Results

  • Significant Cost Reductions: The proposed framework achieved substantial cost savings. For the deterministic case, reductions of 17.18% and 14.81% were observed for Wind Farm 1 and Wind Farm 2, respectively.
  • Weather Resilience: Under stochastic weather conditions, the framework still delivered impressive cost reductions of 15.44% for Wind Farm 1 and 13.20% for Wind Farm 2.
  • Algorithm Performance: Comparative analysis showed that the EDF-SA hybrid approach offered an optimal trade-off between solution quality and computational efficiency, outperforming pure SA and Genetic Algorithms.
  • Proxy Objective Validation: The study validated a proxy objective function for optimization, showing a strong positive correlation (R² of 0.971 and 0.980) with actual project costs, confirming its effectiveness.

Limitations and Future Work

  • Focus on Wind Speed: While acknowledging other metocean factors, the study primarily focuses on wind speed as the main source of weather uncertainty. Future work could incorporate more complex weather models that include wave height and tides.
  • Simplified Component Handling: The study assumes pre-assembled nacelles and focuses on three core component categories (towers, nacelles, blades). More granular component handling could be explored.
  • Deterministic TV Assignment: While the IV routes are optimized, the initial TV assignment is somewhat rigid. The paper mentions a mixed-loading approach that shows promise for further cost reduction.
  • Future Research Directions: The authors suggest incorporating additional cost factors like inventory management and human resource scheduling to further align the model with practical engineering requirements. They also note the scalability of the methodology to other scheduling problems, such as maintenance scheduling for OWFs.

Summary updated

Abstract

The construction cost of offshore wind farms (OWFs) is heavily influenced by vessel scheduling and meteorological uncertainties. To address these challenges, this paper proposes a constraint-driven hierarchical optimization framework for the coordinated scheduling of installation vessels (IVs) and transport vessels (TVs). First, a Mixed-Integer Linear Programming (MILP) model is established to describe the operational constraints, which is then decomposed into two interrelated sub-problems: vessel path planning and scheduling optimization. For path planning, the problem is modeled as a Multiple Traveling Salesman Problem (MTSP) to ensure balanced fleet workloads. This stage is solved via a tailored three-stage heuristic combining balanced sweep clustering and penalized local search. For scheduling optimization, a hybrid Earliest Deadline First (EDF)-Simulated Annealing (SA) strategy is employed, where EDF generates a strictly feasible baseline to warm-start the SA optimization. Furthermore, a stochastic optimization approach integrates historical meteorological data to ensure schedule robustness against weather uncertainty. The validity of the framework is supported by two real-world OWF cases, which demonstrate total cost reductions of 15.44% and 13.20%, respectively, under stochastic weather conditions. These results demonstrate its effectiveness in solving high-constraint offshore engineering problems.
BibTeX
@article{qu2026optimization,
  author = {Shengguan Qu and Changmao Yu and Yang Zhou and Y. Thomas Hou and J Wang and Fenglei Li},
  title = {{Optimization of Collaborative Vessel Scheduling for Offshore Wind Farm Installation Under Weather Uncertainty}},
  journal = {Journal of Marine Science and Engineering},
  year = {2026},
  doi = {10.3390/jmse14020223},
}
Figure