The breakthrough targets one of the most persistent challenges in building decarbonization. Heating and cooling account for a substantial share of global building energy consumption, and demand is expected to grow as temperatures rise and air-conditioning becomes more widespread. Thermal energy storage can help shift energy use away from peak periods, but conventional storage systems often struggle to deliver heat or cold efficiently at the right time. Latent heat thermal energy storage, known as LHTES, offers a particularly attractive solution because it stores energy through a material’s phase change rather than simply raising its temperature.

In an LHTES system, a phase change material absorbs large quantities of heat as it melts and releases that energy as it solidifies. Wax-based materials are commonly used because they can store considerable amounts of thermal energy while maintaining an almost constant temperature during the phase transition. This behavior allows an LHTES unit to function like a rechargeable battery for heat, supplying thermal energy steadily instead of producing the fluctuating temperatures associated with many conventional systems. Previous studies have indicated that effective latent heat storage could reduce building heating and cooling energy consumption by as much as 45 percent.

The problem is that designing an efficient LHTES device requires engineers to balance several competing factors. The geometry of the pipes, the flow rate of the heat-transfer fluid, the size of the storage unit, the melting behavior of the phase change material and the pumping energy required by the system all influence performance. Heat transfer and fluid flow are tightly coupled, making the underlying physics difficult to reproduce with simple calculations. Laboratory experiments can provide reliable measurements, but they are usually limited to a small number of configurations. Computational fluid dynamics, or CFD, can simulate the detailed behavior, yet each simulation may require significant processing time, making it impractical to evaluate tens of thousands of potential designs.

To address this bottleneck, the Korean research team first built a laboratory-scale LHTES system and developed a corresponding high-fidelity CFD model. Experimental measurements were used to validate the numerical simulations, and the results showed strong agreement with only minor deviations. Once the model had been established as a reliable representation of the physical system, the researchers used it to generate 15 high-fidelity simulation cases. This dataset was sparse by conventional machine-learning standards, but the researchers designed their neural network to learn from physical laws rather than relying only on large volumes of examples.

The PINN framework incorporates the governing equations of the storage system directly into its training process. Instead of merely matching input-output data, the model is penalized when its predictions violate principles such as energy conservation. In this study, the network used a zero-dimensional physical model to represent the overall thermal behavior of the system. It also learned case-specific effective heat-transfer coefficients, which summarize the complex thermal interactions occurring inside the storage device. By learning these coefficients while enforcing the governing physics, the model could reproduce the behavior of the CFD simulations without needing to resolve every local flow and temperature detail.

The researchers added another important component: a response surface model, or RSM, to represent the influence of geometry and operating conditions. An RSM is a mathematical approximation that maps design variables to system behavior, allowing predictions to be made for configurations that were not explicitly included in the training dataset. In the new framework, the PINN and RSM work together as a rapid digital twin of the LHTES unit. The PINN captures the system’s physical rules, while the response surface model estimates how changes in pipe shape and flow conditions affect heat transfer. This combination allows the digital twin to examine previously unseen designs at a fraction of the cost of running new CFD simulations.

The digital twin was then linked to the Non-dominated Sorting Genetic Algorithm II, widely known as NSGA-II, a computational method designed for multi-objective optimization. Rather than searching for a single design judged by one performance measure, NSGA-II identifies a range of solutions that represent different compromises between competing goals. The researchers sought to maximize total discharged heat and average discharge power while minimizing pumping power. A design that releases heat very quickly may require stronger fluid circulation, for example, while a design that minimizes pumping energy may deliver heat more slowly. The algorithm reveals the trade-offs so engineers can select a configuration suited to a particular application.

In numerical testing, the PINN reproduced the CFD-predicted system behavior with excellent accuracy and enabled autonomous exploration of a large design space. The optimized configuration performed similarly to the strongest baseline design in terms of thermal output, but it required substantially less pumping power. The analysis also indicated that flatter pipes could provide more favorable performance, a finding that may help guide future physical prototypes. Because the system can evaluate many candidate designs rapidly, researchers can focus laboratory testing on the most promising options rather than repeatedly analyzing inefficient configurations.

The implications extend beyond building heating and cooling. The same physics-informed design strategy could be adapted for thermal management in electric-vehicle batteries, where temperature uniformity is essential for safety and battery life. It could also support cooling systems for data centers, temperature-controlled cold-chain logistics and solar thermal installations. Earlier research has suggested that intelligent control of latent heat storage could reduce electricity costs by more than 70 percent in suitable applications. By transforming LHTES design from a slow comparison of isolated cases into an automated search across a broad design space, the Hanbat National University team has demonstrated how artificial intelligence can accelerate the development of lower-energy thermal systems. The approach does not replace physical understanding; instead, it embeds that understanding into machine learning, creating a practical route toward faster, more efficient and more sustainable energy-storage technologies.

Subject of Research: Computational simulation/modeling

Article Title: Physics-informed neural networks for multi-objective design optimization of latent heat thermal energy storage systems

News Publication Date: 30 July 2026

Web References: https://doi.org/10.1016/j.est.2026.122514

References: 10.1016/j.est.2026.122514

Image Credits: Assistant Professor Joo Hyun Moon, Hanbat National University

Keywords

Latent heat thermal energy storage, phase change materials, physics-informed neural networks, artificial intelligence, thermal energy storage, building decarbonization, computational fluid dynamics, digital twins, NSGA-II, multi-objective optimization, heat transfer, energy efficiency

At the core of this research are the efforts of Akshay Ajagekar and Fengqi You of Cornell University, who have engineered a sophisticated adaptive quantum approximate optimization-based MPC strategy. This system targets buildings outfitted with integrated battery energy storage and renewable generation, specifically photovoltaic (PV) modules. Their work interlaces quantum computing paradigms with classical control theory, harnessing the advanced computational capabilities of quantum algorithms to tackle complex optimization problems inherent in energy management.

The research hinges on utilizing the Quantum Approximate Optimization Algorithm (QAOA), a promising quantum algorithm designed for combinatorial optimization problems. By embedding the building control problem within a quadratic unconstrained binary optimization (QUBO) framework, they translate the MPC challenge—characterized by nonlinear dynamics and stochastic disturbances—into a form amenable to quantum solvers. This approach not only enables the real-time computation of optimal energy control decisions but also reduces reliance on exhaustive classical computations that often hinder scalability.

A novel element introduced by the researchers is a learning-based parameter transfer scheme that improves QAOA’s efficiency. This scheme employs Bayesian optimization alongside Gaussian processes to intelligently predict initial quantum circuit parameters, dramatically shortening the iterative search time typically required. This design allows the quantum algorithm to adapt dynamically to time-varying building states and external environmental factors, enhancing robustness and responsiveness in real-world applications.

To validate the effectiveness of their approach, the team conducted computational experiments using data drawn from two representative buildings located on Cornell’s campus. Their comparative analysis measured the performance of the adaptive quantum MPC against traditional deterministic MPC methods and quantum annealing algorithms. The results were compelling: the quantum-enhanced strategy yielded an average improvement of 6.8% in energy efficiency compared to classical deterministic control, showcasing the tangible benefits of integrating quantum techniques into energy optimization processes.

Beyond energy savings, the study reveals a significant environmental impact. The proposed quantum-based control method achieved a remarkable 41.2% reduction in annual carbon emissions by optimizing the coordination between renewable energy generation, battery storage management, and building load demands. This advancement demonstrates the method’s potential to contribute meaningfully to climate change mitigation efforts by facilitating smarter, cleaner building operations.

Importantly, the quantum MPC system showcased impressive adaptability to fluctuating ambient temperatures and varying load conditions. By fine-tuning heating and cooling outputs in real time, it ensures occupant comfort without sacrificing energy efficiency. Such adaptability arises from the responsive nature of the learning-driven QAOA, which refines control parameters on the fly to accommodate unforeseen environmental disturbances, a key attribute for practical deployment.

In terms of computational demands, while the learning-based QAOA necessitated a larger number of iterations during the initial learning phase, the system quickly converged as it accumulated operating experience. This translates to a reduction in quantum computational overhead over time, outperforming competing techniques like quantum annealing in convergence speed and scalability. The results underpin the potential of hybrid quantum-classical strategies in surmounting current quantum hardware limitations.

The research also candidly discusses the method’s current limitations. Given the simplicity of the tested building energy model, scaling the technique to more intricate systems presents challenges due to the exponential growth in optimization variables, which could strain present-day quantum hardware capabilities. Furthermore, although the approach implicitly accounts for uncertainties through its adaptive framework, explicitly integrating uncertainty quantification methods could further improve reliability and robustness against unpredictable real-world conditions.

Nevertheless, the findings open intriguing pathways for the future of intelligent building management. The authors point to several directions for advancing this technology, including incorporating real-time carbon intensity metrics to align energy use with low-carbon grid periods, extending the framework to diverse building types and climates, and refining quantum algorithms to better handle larger, more complex control scenarios. Such progress promises not only efficiency gains but also tangible strides toward sustainable urban environments.

The convergence of quantum computing and adaptive MPC exemplifies a paradigm shift in how buildings interact with energy resources. By embedding quantum-assisted decision-making into operational controls, buildings can dynamically respond to supply variability and demand uncertainties while minimizing environmental footprint. This represents a significant leap forward in smart infrastructure technology, potentially revolutionizing the energy landscape of urban centers worldwide.

As quantum hardware continues to mature and hybrid computational frameworks become more sophisticated, the integration of adaptive quantum MPC strategies may soon become standard practice in building energy systems. This study lays a robust foundation for such a future, illustrating how emerging quantum technologies can transcend theoretical interest to deliver practical, impactful solutions for energy sustainability and climate action.

For those deeply interested in the technical exposition of this promising research, the full open-access article titled “Decarbonization of Building Operations with Adaptive Quantum Computing-Based Model Predictive Control,” authored by Akshay Ajagekar and Fengqi You, expands in meticulous detail on the algorithmic frameworks, system modeling, and experimental results. The study signals a transformative moment for the energy management sector, highlighting how quantum-enhanced control methodologies can unlock new frontiers in efficiency and environmental stewardship.

Subject of Research: Adaptive quantum computing and model predictive control for building energy management and decarbonization.

Article Title: Decarbonization of Building Operations with Adaptive Quantum Computing-Based Model Predictive Control

News Publication Date: 13-Feb-2025

Web References:
https://doi.org/10.1016/j.eng.2025.02.002
https://www.sciencedirect.com/journal/engineering

Image Credits: Akshay Ajagekar, Fengqi You

Keywords: Quantum information science, Thermal energy, Quantum computing, Renewable energy, Adaptive control