In the quest to optimize hybrid power plants (HPPs), a groundbreaking study led by C. Assaad from the Technical University of Denmark’s Department of Wind and Energy Systems has introduced a novel approach that could revolutionize the energy sector. The research, published in Wind Energy Science, focuses on enabling efficient sizing of HPPs, which combine wind power plants and battery energy systems, to prevent financial losses from improper sizing relative to grid connection capacities.
The crux of the issue lies in the computational burden of high-fidelity energy management systems (EMSs). These systems are crucial for modeling bidding strategies and operations in electricity markets, ensuring precise operational revenues and costs. However, the heavy computational demands often lead to the use of low-fidelity EMS models, resulting in faulty sizing evaluations. Assaad’s research addresses this challenge by evaluating the potential of surrogate models to replace high-fidelity EMSs, thereby providing a computationally efficient and accurate solution.
“The goal was to develop a model that can accurately evaluate the operation of HPPs across various geographical locations,” Assaad explained. “This would enable us to address multiple sizing problems effectively.”
The study developed and compared four different surrogate models to approximate a state-of-the-art EMS model. The best-performing surrogate employed singular value decomposition for dimensionality reduction and a feed-forward neural network for regression. This model achieved an impressive normalized root mean square error of just 0.81% in approximating yearly revenues, proving its effectiveness in accurately evaluating HPP operations.
The implications of this research are vast. By enabling precise sizing of HPPs, energy companies can avoid the financial pitfalls of under- or over-sizing, leading to more efficient and profitable operations. This is particularly relevant in the context of the day-ahead electricity market in Denmark, where perfect forecasts are assumed. However, the methodology can be applied to other geographical locations, making it a versatile tool for the energy sector.
“The surrogate model we developed is not just about accuracy; it’s about providing a practical solution that can be implemented in real-world scenarios,” Assaad noted. “This can significantly impact the profitability and operational efficiency of HPPs.”
The research also evaluated the profitability of several HPP sizes using the surrogate model, achieving a root mean square error of 0.010 on the profitability index. This demonstrates the model’s suitability for HPP sizing under given cost and financial assumptions, paving the way for more informed decision-making in the energy sector.
As the energy sector continues to evolve, the need for accurate and efficient modeling tools becomes increasingly important. This research, published in Wind Energy Science, offers a promising solution that could shape future developments in the field. By enabling precise sizing of HPPs, energy companies can optimize their operations, reduce financial risks, and contribute to a more sustainable energy future. The work by Assaad and his team is a significant step forward in this direction, offering a glimpse into the future of energy management systems.
