Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

International SoC Design Conference

Quantum Battery Optimization through Quantum Machine Learning Techniques

Vu Tuan Hai, Vo Minh Kiet, Vu Trung Duong Le, Pham Hoai Luan, Le Bin Ho, Yasuhiko Nakashima

Published Aug 19, 2024• 2 citations
Publisher

Abstract

Quantum batteries are a promising technology that could surpass their classical counterparts and play a critical role in the advancement of quantum technologies. In this work, we develop a quantum machine learning algorithm to improve the charging power of quantum batteries. To model an N-cell quantum battery, we use a quantum circuit with N quantum bits. During the charging process, we apply a set of quantum gates with trainable parameters to the circuit. Next, we evaluate the power extraction and optimize it using a classical computer. We find a remarkable maximum power when increasing N. Our work has the potential to create sustainable and scalable energy storage technologies in the future

DOI
10.1109/isocc62682.2024.10762673

Related papers

Quantum machine learning approaches to state-of-health prediction and optimization in energy storage devices

Mojtaba Khakpour Komarsofla, Amirkianoosh Kiani

Energy storage devices such as lithium-ion batteries and supercapacitors are essential for portable electronics, electric vehicles, and renewable energy systems, yet their long-term reliability is limited by capacity degradation. Accurate prediction of state-of-health (SOH), state-of-charge (SOC), and capacity retention are therefore critical for extending device lifetimes and improving safety. Classical machine learning (ML) methods including LSTMs, CNNs, and ensemble approaches have achieved success in forecasting degradation trends, but they face limitations in scalability, data requirements, and capturing complex electrochemical behaviors. Quantum computing, and in particular quantum machine learning (QML), offers new opportunities by exploiting superposition and entanglement to process information more efficiently and compactly. This review surveys recent advances in applying QML to energy storage, with a focus on CQ approaches (classical data–quantum processing), distinguishing Hybrid-CQ architectures. Comparative analyses highlight trade-offs: CQ and Hybrid-CQ models achieve higher accuracy and parameter efficiency but are constrained by noise, limited qubits, and slower runtimes on real devices. Looking forward, integrating error-mitigation strategies, benchmarking on actual quantum hardware, and embedding physics-informed modeling are critical to closing the gap between theoretical promise and practical deployment. Beyond prediction tasks, quantum approaches hold potential for dynamic charging optimization, materials discovery, and quantum battery concepts. Collectively, these developments underscore how QML can complement and eventually surpass classical ML, paving the way toward more accurate, sustainable, and efficient energy storage systems.

Journal of Energy Storage•Feb 3, 2026•6 citations

Quantum Computing Machine Intelligence for Optimal Battery Performance

Pushpender Sarao, R. V. V. Krishna, Pasupuleti Subrahmanya Ranjit +1 more

This research improves batteries using AI and quantum processing. Quantum computing uses quantum physics to quickly search for many solutions to manage large amounts of data. Deep learning, reinforcement learning, and other machine intelligence use massive datasets to uncover patterns and improve algorithms for quantum computing. To test alternative configurations simultaneously, the authors record operating parameters, ambient variables, and battery attributes in a quantum state. They want to utilize reinforcement learning algorithms to improve charging and draining methods so they operate well and can be used in many situations. This research aims to reduce degradation, improve energy efficiency, and extend battery life. Machine intelligence and quantum computation are used to analyze batteries and optimize performance. Bringing together experts from different sectors could help construct strong, environmentally friendly power networks. This modification may affect energy storage technology greatly. The research's findings could impact electric cars, power grid security, and renewable energy.

Advances in computational intelligence and robotics book series•Aug 5, 2024•0 citations

A Quantum Neural Network Regression for Modeling Lithium-ion Battery Capacity Degradation

Anh Phuong Ngo, Nhat Le, Hieu Trong Nguyen +2 more

Given their high power density, low discharge rate, and decreasing cost, rechargeable lithium-ion batteries (LiBs) have found a wide range of applications such as power grid-level storage systems, electric vehicles (EVs), and mobile devices. Developing a framework to accurately model the nonlinear degradation process of LiBs, which is indeed a supervised learning problem, becomes an important research topic. This paper presents a classical-quantum hybrid machine learning approach to capture the LiB degradation model that assesses the loss of battery cell life from the operating profiles. Our work is motivated by recent advances in quantum computers as well as the similarity between neural networks and quantum circuits. Similarly to adjusting weight parameters in conventional neural networks, the parameters of the quantum circuit, namely, the degree of freedom of the qubits, can be tuned to learn a nonlinear function in a supervised learning fashion. As a proof of concept paper, our obtained numerical results with the battery dataset provided by NASA demonstrate the ability of the quantum neural networks in modeling the nonlinear relationship between the degraded capacity and the operating cycles. We also discuss the potential advantage of the quantum approach compared to conventional neural networks in classical computers in dealing with massive data, especially in the context of future penetration of EVs and energy storage.

arXiv:2302.02547•IEEE Green Technologies Conference (GreenTech)•Apr 19, 2023•18 citations

A Review of Quantum Modeling and Simulation Approaches for Lithium-ion Batteries

Deniz Çetinkaya, Amr M. Abdelkader

Lithium-ion batteries (LIBs) are critical in modern energy storage systems, powering everything from portable electronics to electric vehicles. However, optimizing their performance and longevity remains a significant challenge. Quantum simulation has emerged as a promising tool to model the complex electrochemical processes within LIBs, offering insights into charging mechanisms and degradation pathways th'at classical methods struggle to capture. This paper presents a systematic literature review of quantum simulation techniques applied to LIBs, focusing on charging and degradation modeling. We analyze the current state-of-the-art, identify key techniques, and discuss the potential of quantum computing to revolutionize battery research. Our findings highlight the advantages of quantum simulations in capturing quantum mechanical and quantum chemistry effects which are critical for accurate battery modeling. Trends in the literature suggest a move toward algorithm optimization, integration with classical methods, and the development of quantum-inspired techniques.

•Aug 19, 2025•0 citations

Quantum Computing for Power Electronics: Quantum Machine Learning Approaches for IoT-Enabled Grid Optimization

Seepuram Srinivas Kumar, Heena Kausar

The increasing complexity of modern power grids, driven by the integration of renewable energy sources, decentralized energy generation, and dynamic load variations, necessitates advanced computational approaches for efficient grid optimization. Conventional algorithms often struggle with the high-dimensionality and computational intensity of power system optimization problems, prompting the exploration of quantum computing as a transformative alternative. Quantum computing, particularly quantum machine learning (QML) and quantum optimization algorithms, has demonstrated significant potential in accelerating grid stability analysis, energy dispatch, and fault detection. This chapter provides a comprehensive investigation into quantum computing applications for power electronics, focusing on quantum-inspired machine learning models and hybrid quantum-classical frameworks for IoT-enabled smart grids. The potential advantages of quantum algorithms, including the Quantum Approximate Optimization Algorithm (QAOA), Variational Quantum Eigensolver (VQE), and Grover’s search algorithm, are analyzed in the context of grid optimization, fault detection, and cybersecurity. Additionally, a comparative analysis of classical and quantum machine learning techniques highlights key performance differences and the challenges associated with practical quantum implementations. Despite the promising advancements, several challenges, including quantum hardware limitations, noise susceptibility, and scalability issues, must be addressed for real-world deployment. Future directions emphasize the need for noise-resilient quantum algorithms, efficient hybrid architectures, and quantum-inspired classical methods to bridge the gap between existing computational techniques and next-generation quantum solutions for power grid management.

•Mar 17, 2025•1 citation

Cavity-Heisenberg spin- j chain quantum battery and reinforcement learning optimization

Peng-Yu Sun, Hang Zhou, Fu-Quan Dou

Abstract In the realm of quantum batteries (QBs), model construction and performance optimization are central tasks which can be addressed by exploiting machine learning algorithms. Here, we propose a cavity-Heisenberg spin chain QB model with spin- j ( j = 1 / 2 , 1 , 3 / 2 ) and investigate the charging performance under both closed and open quantum cases, considering spin–spin interactions, ambient temperature, and cavity dissipation. By employing a reinforcement learning (RL) algorithm to modulate the cavity-battery coupling, we further optimize the QB performance, enhancing the charging capability of the spin chain. It is shown that the charging energy and the power of the QB are significantly improved with the spin size. In particular, the use of a RL algorithm in case of large spin ( j = 3 / 2 ) in presence of cavity losses allows for more stability in the optimization of the cavity-spin coupling strength, which in perspective makes an experimental realization more feasible. We analyze the optimization mechanism and find an intrinsic relationship between cavity-spin entanglement and charging performance: while in the closed-system scenario the charging energy increases together with the cavity-spin entanglement, in the open-system scenario the increase of the charging energy can be accompanied by a decrease of entanglement. Our results provide a possible scheme for design and optimization of QBs.

arXiv:2412.01442•New Journal of Physics•Dec 1, 2025•24 citations
Quantum batteries are a promising technology that could surpass their classical counterparts and play a critical role in the advancement of quantum technologies. In this work, we develop a quantum machine learning algorithm to improve the charging power of quantum batteries. To model an N-cell quantum battery, we use a quantum circuit with N quantum bits. During the charging process, we apply a set of quantum gates with trainable parameters to the circuit. Next, we evaluate the power extraction and optimize it using a classical computer. We find a remarkable maximum power when increasing N. Our work has the potential to create sustainable and scalable energy storage technologies in the future
Energy storage devices such as lithium-ion batteries and supercapacitors are essential for portable electronics, electric vehicles, and renewable energy systems, yet their long-term reliability is limited by capacity degradation. Accurate prediction of state-of-health (SOH), state-of-charge (SOC), and capacity retention are therefore critical for extending device lifetimes and improving safety. Classical machine learning (ML) methods including LSTMs, CNNs, and ensemble approaches have achieved success in forecasting degradation trends, but they face limitations in scalability, data requirements, and capturing complex electrochemical behaviors. Quantum computing, and in particular quantum machine learning (QML), offers new opportunities by exploiting superposition and entanglement to process information more efficiently and compactly. This review surveys recent advances in applying QML to energy storage, with a focus on CQ approaches (classical data–quantum processing), distinguishing Hybrid-CQ architectures. Comparative analyses highlight trade-offs: CQ and Hybrid-CQ models achieve higher accuracy and parameter efficiency but are constrained by noise, limited qubits, and slower runtimes on real devices. Looking forward, integrating error-mitigation strategies, benchmarking on actual quantum hardware, and embedding physics-informed modeling are critical to closing the gap between theoretical promise and practical deployment. Beyond prediction tasks, quantum approaches hold potential for dynamic charging optimization, materials discovery, and quantum battery concepts. Collectively, these developments underscore how QML can complement and eventually surpass classical ML, paving the way toward more accurate, sustainable, and efficient energy storage systems.
This research improves batteries using AI and quantum processing. Quantum computing uses quantum physics to quickly search for many solutions to manage large amounts of data. Deep learning, reinforcement learning, and other machine intelligence use massive datasets to uncover patterns and improve algorithms for quantum computing. To test alternative configurations simultaneously, the authors record operating parameters, ambient variables, and battery attributes in a quantum state. They want to utilize reinforcement learning algorithms to improve charging and draining methods so they operate well and can be used in many situations. This research aims to reduce degradation, improve energy efficiency, and extend battery life. Machine intelligence and quantum computation are used to analyze batteries and optimize performance. Bringing together experts from different sectors could help construct strong, environmentally friendly power networks. This modification may affect energy storage technology greatly. The research's findings could impact electric cars, power grid security, and renewable energy.
Given their high power density, low discharge rate, and decreasing cost, rechargeable lithium-ion batteries (LiBs) have found a wide range of applications such as power grid-level storage systems, electric vehicles (EVs), and mobile devices. Developing a framework to accurately model the nonlinear degradation process of LiBs, which is indeed a supervised learning problem, becomes an important research topic. This paper presents a classical-quantum hybrid machine learning approach to capture the LiB degradation model that assesses the loss of battery cell life from the operating profiles. Our work is motivated by recent advances in quantum computers as well as the similarity between neural networks and quantum circuits. Similarly to adjusting weight parameters in conventional neural networks, the parameters of the quantum circuit, namely, the degree of freedom of the qubits, can be tuned to learn a nonlinear function in a supervised learning fashion. As a proof of concept paper, our obtained numerical results with the battery dataset provided by NASA demonstrate the ability of the quantum neural networks in modeling the nonlinear relationship between the degraded capacity and the operating cycles. We also discuss the potential advantage of the quantum approach compared to conventional neural networks in classical computers in dealing with massive data, especially in the context of future penetration of EVs and energy storage.
Lithium-ion batteries (LIBs) are critical in modern energy storage systems, powering everything from portable electronics to electric vehicles. However, optimizing their performance and longevity remains a significant challenge. Quantum simulation has emerged as a promising tool to model the complex electrochemical processes within LIBs, offering insights into charging mechanisms and degradation pathways th'at classical methods struggle to capture. This paper presents a systematic literature review of quantum simulation techniques applied to LIBs, focusing on charging and degradation modeling. We analyze the current state-of-the-art, identify key techniques, and discuss the potential of quantum computing to revolutionize battery research. Our findings highlight the advantages of quantum simulations in capturing quantum mechanical and quantum chemistry effects which are critical for accurate battery modeling. Trends in the literature suggest a move toward algorithm optimization, integration with classical methods, and the development of quantum-inspired techniques.
The increasing complexity of modern power grids, driven by the integration of renewable energy sources, decentralized energy generation, and dynamic load variations, necessitates advanced computational approaches for efficient grid optimization. Conventional algorithms often struggle with the high-dimensionality and computational intensity of power system optimization problems, prompting the exploration of quantum computing as a transformative alternative. Quantum computing, particularly quantum machine learning (QML) and quantum optimization algorithms, has demonstrated significant potential in accelerating grid stability analysis, energy dispatch, and fault detection. This chapter provides a comprehensive investigation into quantum computing applications for power electronics, focusing on quantum-inspired machine learning models and hybrid quantum-classical frameworks for IoT-enabled smart grids. The potential advantages of quantum algorithms, including the Quantum Approximate Optimization Algorithm (QAOA), Variational Quantum Eigensolver (VQE), and Grover’s search algorithm, are analyzed in the context of grid optimization, fault detection, and cybersecurity. Additionally, a comparative analysis of classical and quantum machine learning techniques highlights key performance differences and the challenges associated with practical quantum implementations. Despite the promising advancements, several challenges, including quantum hardware limitations, noise susceptibility, and scalability issues, must be addressed for real-world deployment. Future directions emphasize the need for noise-resilient quantum algorithms, efficient hybrid architectures, and quantum-inspired classical methods to bridge the gap between existing computational techniques and next-generation quantum solutions for power grid management.
Abstract In the realm of quantum batteries (QBs), model construction and performance optimization are central tasks which can be addressed by exploiting machine learning algorithms. Here, we propose a cavity-Heisenberg spin chain QB model with spin- j ( j = 1 / 2 , 1 , 3 / 2 ) and investigate the charging performance under both closed and open quantum cases, considering spin–spin interactions, ambient temperature, and cavity dissipation. By employing a reinforcement learning (RL) algorithm to modulate the cavity-battery coupling, we further optimize the QB performance, enhancing the charging capability of the spin chain. It is shown that the charging energy and the power of the QB are significantly improved with the spin size. In particular, the use of a RL algorithm in case of large spin ( j = 3 / 2 ) in presence of cavity losses allows for more stability in the optimization of the cavity-spin coupling strength, which in perspective makes an experimental realization more feasible. We analyze the optimization mechanism and find an intrinsic relationship between cavity-spin entanglement and charging performance: while in the closed-system scenario the charging energy increases together with the cavity-spin entanglement, in the open-system scenario the increase of the charging energy can be accompanied by a decrease of entanglement. Our results provide a possible scheme for design and optimization of QBs.