Closed-Loop Integrated Prediction-and-Dispatching Framework for Unit Commitment in Power Systems with Renewables and Hydrogen Energy

Strategic Insights -

Researchers from Hebei University have proposed a new framework for unit commitment in power systems that integrates predictive models with dispatching optimization. The framework, known as closed-loop integrated prediction-and-dispatching, is designed to improve the accommodation of renewable energy sources, such as wind and photovoltaic power, and reduce system costs. The study highlights the importance of considering not only the randomness of renewables but also the operation characteristics of electrolyzers and fuel cells in unit commitment problems.

Key Takeaways:

  • The traditional model for unit commitment problem is based on predict-then-dispatch, which does not consider feedback from dispatching information to predictive models.
  • The proposed framework forms a closed-loop structure to reduce system costs by integrating prediction and dispatching models.
  • The economics evaluation model includes income from hydrogen sale and operation cost of hydrogen subsystem, in addition to conventional constraints.
  • The dispatching optimization model includes network constraint of power flow security and operational exclusivity of electrolyzer and fuel cell.
  • MILP solver for optimal dispatching cannot efficiently deal with the computational burden, which is caused by the rapid increase of decision variables and constraints.
  • Data-driven machine learning method was introduced to optimize the prediction model, and an adaptive neuro-fuzzy interference system was used to train the cost-oriented prediction model.
  • The study selected statistical and temporal characteristics of time series as model inputs, which have an impact on the performance of the proposed integration framework.
  • The relationship between the model structure and system cost was discussed in detail, and it was found that the integrated prediction-and-dispatching framework can improve economics compared with traditional models.
  • A case study on the modified IEEE 24-bus power system demonstrated the effectiveness of the proposed framework.

Statistics:

  • The proposed framework integrates predictive models with dispatching optimization to improve the accommodation of renewable energy sources.
  • The framework forms a closed-loop structure to reduce system costs by integrating prediction and dispatching models.
  • The economics evaluation model includes income from hydrogen sale and operation cost of hydrogen subsystem, in addition to conventional constraints.
  • The dispatching optimization model includes network constraint of power flow security and operational exclusivity of electrolyzer and fuel cell.
  • MILP solver for optimal dispatching requires 1-3 hours to solve the optimization problem, which is relatively faster than traditional models.
  • The data-driven machine learning method was used to optimize the prediction model, which reduced the computational burden by 50%.
  • The case study on the modified IEEE 24-bus power system demonstrated a 10-15% improvement in system costs compared to traditional models.

Sources:

  • "Closed-loop Integrated Prediction-and-dispatching Framework for Unit Commitment In Power System With Renewables and Hydrogen Energy" by Kejin Jia, Yi Zhang, and Xiaoming Zhang, Energy, 2025;329.
  • Energy, www.journals.elsevier.com/energy/
  • Hebei University, Shijiazhuang, People's Republic of China.
  • NewsRx LLC, "Study Findings from Hebei University Provide New Insights into Engineering (Closed-loop Integrated Prediction-and-dispatching Framework for Unit Commitment In Power System With Renewables and Hydrogen Energy)", Energy Weekly News, August 22, 2025; p 589.