Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Data-Driven Evolutionary Game-Based Model Predictive Control for Hybrid Renewable Energy Dispatch in Autonomous Ships

Yaoze Liu, Zhen Tian, Jinming Yang, Zhihao Lin

TL;DR

This work tackles autonomous-ship energy management under uncertain renewable generation by proposing a data-driven Evolutionary Game-Based Model Predictive Control (EG-MPC). It couples a linear, regression-based renewable-generation model derived from real HOMER data with a receding-horizon MPC, and enhances the search with evolutionary game dynamics to yield near-optimal dispatch actions. The approach integrates battery degradation and diesel-backup costs, ensuring SOC safety while minimizing total energy costs. Simulation results show that EG-MPC outperforms rule-based and standard MPC schemes, delivering lower backup usage and tighter cost control under varying conditions, with strong practical implications for offshore and remote maritime operations.

Abstract

In this paper, we propose a data-driven Evolutionary Game-Based Model Predictive Control (EG-MPC) framework for the energy dispatch of a hybrid renewable energy system powering an autonomous ship. The system integrates solar photovoltaic and wind turbine generation with battery energy storage and diesel backup power to ensure reliable operation. Given the uncertainties in renewable generation and dynamic energy demands, an optimal dispatch strategy is crucial to minimize operational costs while maintaining system reliability. To address these challenges, we formulate a cost minimization problem that considers both battery degradation costs and diesel fuel expenses, leveraging real-world data to enhance modeling accuracy. The EG-MPC approach integrates evolutionary game dynamics within a receding-horizon optimization framework, enabling adaptive and near-optimal control solutions in real time. Simulation results based on site-specific data demonstrate that the proposed method achieves cost-effective, reliable, and adaptive energy dispatch, outperforming conventional rule-based and standard MPC approaches, particularly under uncertainty.

Data-Driven Evolutionary Game-Based Model Predictive Control for Hybrid Renewable Energy Dispatch in Autonomous Ships

TL;DR

This work tackles autonomous-ship energy management under uncertain renewable generation by proposing a data-driven Evolutionary Game-Based Model Predictive Control (EG-MPC). It couples a linear, regression-based renewable-generation model derived from real HOMER data with a receding-horizon MPC, and enhances the search with evolutionary game dynamics to yield near-optimal dispatch actions. The approach integrates battery degradation and diesel-backup costs, ensuring SOC safety while minimizing total energy costs. Simulation results show that EG-MPC outperforms rule-based and standard MPC schemes, delivering lower backup usage and tighter cost control under varying conditions, with strong practical implications for offshore and remote maritime operations.

Abstract

In this paper, we propose a data-driven Evolutionary Game-Based Model Predictive Control (EG-MPC) framework for the energy dispatch of a hybrid renewable energy system powering an autonomous ship. The system integrates solar photovoltaic and wind turbine generation with battery energy storage and diesel backup power to ensure reliable operation. Given the uncertainties in renewable generation and dynamic energy demands, an optimal dispatch strategy is crucial to minimize operational costs while maintaining system reliability. To address these challenges, we formulate a cost minimization problem that considers both battery degradation costs and diesel fuel expenses, leveraging real-world data to enhance modeling accuracy. The EG-MPC approach integrates evolutionary game dynamics within a receding-horizon optimization framework, enabling adaptive and near-optimal control solutions in real time. Simulation results based on site-specific data demonstrate that the proposed method achieves cost-effective, reliable, and adaptive energy dispatch, outperforming conventional rule-based and standard MPC approaches, particularly under uncertainty.

Paper Structure

This paper contains 21 sections, 14 equations, 9 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. System Framework
  3. Methodology
  4. Battery Storage Dynamics
  5. Cost Function
  6. MPC Optimization Problem
  7. Real-World Data Fitting using Linear Models
  8. Real-World Data Fitting Process
  9. Load Demand and Energy Balance
  10. Rationale Selection of Linear Model
  11. MPC Optimization Formulation with Renewable Power
  12. MPC Optimization Formulation with Renewable Power
  13. Candidate Control Sequence Generation
  14. Cost Evaluation of a Candidate Sequence
  15. Evolutionary Game Dynamics
  16. ...and 6 more sections

Figures (9)

  • Figure 1: Illustration of autonomous ship.
  • Figure 2: The proposed framework using EG-MPC based on real-world data.
  • Figure 3: Flowchart of Autonomous Ship Dispatching and the EG--MPC Process
  • Figure 4: The comparison of load power and renewable power among 12 months based on HOMER-generated synthetic resource datasets.
  • Figure 5: Surface plot of total renewable energy generation as a function of wind speed and solar irradiance.
  • ...and 4 more figures