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 Conference on Innovation & Growth in Next-Gen Intelligent Technology & Engineering (IGNITE)

A Hybrid Quantum-Classical Framework for Smart Grid Load Balancing

Ssanidhya Barraptay, Deepali Misal

Published Jun 1, 2026• 0 citations
Publisher

Abstract

In the case of a smart grid operation, countless interacting variables change unpredictably. The interaction of these variables causes the exponential growth of the system configuration. Conventional computational techniques cannot explore it fully due to the large decision space. In such cases, these techniques fail to generate an optimised solution. The limitations of classical approaches prompted researchers to seek a different computational approach for complex autonomous systems. This paper presents a hybrid Quantum-Classical framework for smart grid load balancing. It demonstrates the use of AI agents for managing the energy usage of a local grid load, especially during a sudden high power demand. This is the case when a microgrid approaches its operational limits. The quantum agents decide which particular household load is to be disconnected temporarily. The major optimization tasks are framed as Quadratic Unconstrained Binary Optimization (QUBO) problems. The objective terms and system constraints are encoded in a single expression. The Quadratic Approximation Optimization Algorithm (QAOA) generates several quantum states and checks which particular state is more suitable for the given problem. The experiments were performed using a quantum simulator environment. For every test, this model was more accurate in reducing the target load.

DOI
10.1109/ignite69592.2026.11705828

Related papers

Quantum Computing for Enhancing Power System Stability in Smart Grids

Sandip D. Satav, Mahendra Kumar B, P. Lakshmi Prabha +3 more

The quick incorporation of renewable energy resources into smart grid has exacerbated issues with voltage stability, frequency variations and cascading failures due to unpredictable renewable energy generation and extreme weather. The conventional classical approaches of power flow analysis and stability assessment face the challenge of computational complexity, and are not so useful in real-time decision making under large-scale systems. In this paper, a hybrid quantum/classical approach is introduced, comprising quantum-enhanced forecasting, an efficient power flow computation using the Harrow-Hassidim-Lloyd (HHL) algorithm and a quadratic unconstrained binary optimization (QUBO) for stability-constrained distributed energy resource allocation. The proposed approach allows to put all these parts together in a single pipeline and manage contingencies proactively and optimize resource deployment. Results using simulation on typical test systems have revealed significant advantages such as 15 times faster execution time than conventional fast decoupled load flow, 52% load shedding reduction, 56% lower mean absolute error on bus voltage magnitude and improved minimum bus voltage level (above 0.95 p.u.) under severe contingencies. The results demonstrate the potential of the framework to be a major contribution towards power system resilience and to reliably integrate the renewables in the future smart grid.

•Sep 1, 2026•0 citations

Quantum Machine Learning for Smart Grid Load Balancing

Guan Yue Hong, Alvis C. M. Fong

The modernization of power grids, transitioning into smart grids, demands innovative technologies to manage and optimize energy distribution effectively. As power systems continue to evolve into smart grids with distributed and dynamic architectures, efficient load balancing becomes critical. Classical methods often prove inadequate in handling the complexity and variability of smart grid data. Increasing popularity of renewable energy sources adds another layer of complexity. The integration of renewable energy sources and increasing demand volatility pose significant challenges for smart grid load balancing. Traditional machine learning (ML) methods, while promising, face limitations in real-time optimization and scalability. Quantum Machine Learning (QML), which leverages quantum computing principles like superposition and entanglement, offers a promising frontier for optimizing energy distribution and load balancing by enhancing established ML algorithms. This paper surveys and compares current research on the application of QML to smart grid load balancing, exploring quantum neural networks (QNNs), quantum support vector machines (QSVM), as well as quantum optimization algorithms like Quantum Approximate Optimization Algorithm (QAOA), to improve various aspects of load-balancing efficiency in smart grids. By encoding classical grid data into quantum states, QML models exploit superposition and entanglement to process high-dimensional datasets faster than classical methods.

Power Electronics and Power System Conference (PEPSC)•Nov 13, 2025•0 citations

Distributed Quantum Computing Framework for Smart Grid Optimization

Agata Jolanta Jachowa, Ludwik Kłos

Optimization models for large smart grids need to consider network constraints, renewable energy uncertainty, storage dynamics and flexible demand simultaneously. The mixed discrete-continuous nature of these problems is not suitable for the operational time constraints, and a single quantum processor cannot yet handle real grid instances. A distributed quantum computing framework for an electrical network is proposed in this paper, which divides the network into coupled regions, assigns compact quadratic unconstrained binary optimisation subproblems to heterogeneous quantum workers, and employs an asynchronous classical coordinator to enforce boundary consensus. The four components of the framework are adaptive penalty encoding, warm-started variational circuits, confidence-aware result aggregation and projection-based feasibility repair. A reproducible simulation study is constructed for modified 33-bus, 118-bus, 300-bus and 1354-bus systems with renewable generation, batteries and responsive loads. In all the test cases, the proposed method reduced the operating cost and constraint violation compared with centralised QAOA, quantum annealing, ADMM, and mixed-integer programming under the same time budget. It still performs reasonably well under high worker latency and depolarising noise. Based on the above results, near-term quantum resources will be more credible as coordinated regional accelerators than as a single grid optimizer. Therefore, it will be presented as an engineering architecture, an explicit optimisation map and a multi-metric evaluation system for scalable quantum-assisted smart grid operation.

Journal of Applied Automation Technologies•Apr 14, 2024•0 citations

Quantum Computing–Enhanced Intelligence for Sustainable Power Systems: Toward Next-Generation Smart Grid Architectures

Sahibzada Muhammad Ali, Abdul Jabbar Ehsan, Abdur Rahman +3 more

Transitioning to resilient, renewable, and EV-integrated power systems demands computational frameworks capable of handling high uncertainty, distributed decision-making, and large-scale dynamics. Classical AI and optimisation struggle with high-dimensional interactions among generators, storage, EV fleets, and real-time grid states. This paper proposes a quantum–AI smart grid architecture combining quantum machine learning, quantum-inspired combinatorial optimisation, and hybrid quantum–classical control. Grid states are encoded in variational quantum circuits and Quadratic unconstrained binary optimisation models, accelerating dispatch, scheduling, congestion management, and optimal power flow. A layered design integrates edge-level classical controllers with cloud-based quantum solvers for utility-compatible deployment. Evaluations on a high-fidelity quantum-assisted digital twin of a renewable- and EV-rich IEEE 14-bus network show 40–60% faster optimisation, improved stability, and enhanced solution robustness over classical baselines, demonstrating quantum–AI as a transformative enabler for next-generation power systems.

International Conference on Integrated Intelligence and Cognitive Engineering (ICIICE)•Apr 18, 2026•1 citation

A Penalty-Based QUBO Formulation for Quantum Unit Commitment: Mitigating Slack Variable Constraints in QAOA

Aayush Sharma, Rashi Sinha, P. V. Manitha

The advent of renewable integration to modernize the electric grid has introduced unprecedented complexities in power system operation. Solving the Unit Commitment (UC) problem requires searching vast combinatorial spaces that usually limit classical deterministic solvers. This paper presents a Hybrid Quantum-Classical Framework for solving the UC problem with a rigid Quadratic Unconstrained Binary Optimization (QUBO) formulation. The results of a classical metaheuristic solver (Simulated Annealing) were benchmarked against a variational quantum algorithm (QAOA) implemented with IBM Qiskit. The framework was tested on the standard IEEE 14-Bus system. To accommodate current quantum hardware limits, the quantum execution was localized to a 3-hour, 215statespace peak-load window. Within this comparative window, the classical solver outperformed on execution time (1.2 s) and cost (Rs. 65,000). However, the QAOA implementation (Rs. 69,000 within 45.5 s) provided a mathematically viable pathway for quantum-native grid dispatch. Furthermore, this paper highlights quantum hardware scaling issues caused by inequality-driven slack variables, developing a strict quadratic penalty approach to eliminate auxiliary variables and formulate an initial framework for future quantum grid utility control.

International Conference on Ambient Intelligence, Knowledge Informatics and Industrial Electronics (AIKIIE)•Aug 1, 2026•0 citations

Optimizing Smart Grids with a Hybrid Classical-Quantum Architecture: Efficiency, Scalability, and Real-Time Resilience

Binghao Li

Modern smart grids demand robust computational solutions to manage real-time data processing, complex optimization, and fault resilience, especially with the integration of distributed and renewable energy resources (DERs). This study introduces a hybrid classical-quantum architecture tailored for these needs, leveraging classical computing for routine processing while employing quantum computing for high-complexity tasks. Experimental simulations demonstrate that the hybrid architecture reduces computation time by 40–41% and enhances energy efficiency by approximately 30% compared to traditional configurations. Additionally, its task allocation system improves scalability and resilience, making this architecture a viable solution for optimizing dynamic, large-scale smart grids. The findings offer a pathway toward a scalable and sustainable grid management system, bridging classical reliability with quantum advancements.

International Conference on New Energy and Power Engineering (ICNEPE)•Nov 8, 2024•5 citations
In the case of a smart grid operation, countless interacting variables change unpredictably. The interaction of these variables causes the exponential growth of the system configuration. Conventional computational techniques cannot explore it fully due to the large decision space. In such cases, these techniques fail to generate an optimised solution. The limitations of classical approaches prompted researchers to seek a different computational approach for complex autonomous systems. This paper presents a hybrid Quantum-Classical framework for smart grid load balancing. It demonstrates the use of AI agents for managing the energy usage of a local grid load, especially during a sudden high power demand. This is the case when a microgrid approaches its operational limits. The quantum agents decide which particular household load is to be disconnected temporarily. The major optimization tasks are framed as Quadratic Unconstrained Binary Optimization (QUBO) problems. The objective terms and system constraints are encoded in a single expression. The Quadratic Approximation Optimization Algorithm (QAOA) generates several quantum states and checks which particular state is more suitable for the given problem. The experiments were performed using a quantum simulator environment. For every test, this model was more accurate in reducing the target load.
The quick incorporation of renewable energy resources into smart grid has exacerbated issues with voltage stability, frequency variations and cascading failures due to unpredictable renewable energy generation and extreme weather. The conventional classical approaches of power flow analysis and stability assessment face the challenge of computational complexity, and are not so useful in real-time decision making under large-scale systems. In this paper, a hybrid quantum/classical approach is introduced, comprising quantum-enhanced forecasting, an efficient power flow computation using the Harrow-Hassidim-Lloyd (HHL) algorithm and a quadratic unconstrained binary optimization (QUBO) for stability-constrained distributed energy resource allocation. The proposed approach allows to put all these parts together in a single pipeline and manage contingencies proactively and optimize resource deployment. Results using simulation on typical test systems have revealed significant advantages such as 15 times faster execution time than conventional fast decoupled load flow, 52% load shedding reduction, 56% lower mean absolute error on bus voltage magnitude and improved minimum bus voltage level (above 0.95 p.u.) under severe contingencies. The results demonstrate the potential of the framework to be a major contribution towards power system resilience and to reliably integrate the renewables in the future smart grid.
The modernization of power grids, transitioning into smart grids, demands innovative technologies to manage and optimize energy distribution effectively. As power systems continue to evolve into smart grids with distributed and dynamic architectures, efficient load balancing becomes critical. Classical methods often prove inadequate in handling the complexity and variability of smart grid data. Increasing popularity of renewable energy sources adds another layer of complexity. The integration of renewable energy sources and increasing demand volatility pose significant challenges for smart grid load balancing. Traditional machine learning (ML) methods, while promising, face limitations in real-time optimization and scalability. Quantum Machine Learning (QML), which leverages quantum computing principles like superposition and entanglement, offers a promising frontier for optimizing energy distribution and load balancing by enhancing established ML algorithms. This paper surveys and compares current research on the application of QML to smart grid load balancing, exploring quantum neural networks (QNNs), quantum support vector machines (QSVM), as well as quantum optimization algorithms like Quantum Approximate Optimization Algorithm (QAOA), to improve various aspects of load-balancing efficiency in smart grids. By encoding classical grid data into quantum states, QML models exploit superposition and entanglement to process high-dimensional datasets faster than classical methods.
Optimization models for large smart grids need to consider network constraints, renewable energy uncertainty, storage dynamics and flexible demand simultaneously. The mixed discrete-continuous nature of these problems is not suitable for the operational time constraints, and a single quantum processor cannot yet handle real grid instances. A distributed quantum computing framework for an electrical network is proposed in this paper, which divides the network into coupled regions, assigns compact quadratic unconstrained binary optimisation subproblems to heterogeneous quantum workers, and employs an asynchronous classical coordinator to enforce boundary consensus. The four components of the framework are adaptive penalty encoding, warm-started variational circuits, confidence-aware result aggregation and projection-based feasibility repair. A reproducible simulation study is constructed for modified 33-bus, 118-bus, 300-bus and 1354-bus systems with renewable generation, batteries and responsive loads. In all the test cases, the proposed method reduced the operating cost and constraint violation compared with centralised QAOA, quantum annealing, ADMM, and mixed-integer programming under the same time budget. It still performs reasonably well under high worker latency and depolarising noise. Based on the above results, near-term quantum resources will be more credible as coordinated regional accelerators than as a single grid optimizer. Therefore, it will be presented as an engineering architecture, an explicit optimisation map and a multi-metric evaluation system for scalable quantum-assisted smart grid operation.
Transitioning to resilient, renewable, and EV-integrated power systems demands computational frameworks capable of handling high uncertainty, distributed decision-making, and large-scale dynamics. Classical AI and optimisation struggle with high-dimensional interactions among generators, storage, EV fleets, and real-time grid states. This paper proposes a quantum–AI smart grid architecture combining quantum machine learning, quantum-inspired combinatorial optimisation, and hybrid quantum–classical control. Grid states are encoded in variational quantum circuits and Quadratic unconstrained binary optimisation models, accelerating dispatch, scheduling, congestion management, and optimal power flow. A layered design integrates edge-level classical controllers with cloud-based quantum solvers for utility-compatible deployment. Evaluations on a high-fidelity quantum-assisted digital twin of a renewable- and EV-rich IEEE 14-bus network show 40–60% faster optimisation, improved stability, and enhanced solution robustness over classical baselines, demonstrating quantum–AI as a transformative enabler for next-generation power systems.
The advent of renewable integration to modernize the electric grid has introduced unprecedented complexities in power system operation. Solving the Unit Commitment (UC) problem requires searching vast combinatorial spaces that usually limit classical deterministic solvers. This paper presents a Hybrid Quantum-Classical Framework for solving the UC problem with a rigid Quadratic Unconstrained Binary Optimization (QUBO) formulation. The results of a classical metaheuristic solver (Simulated Annealing) were benchmarked against a variational quantum algorithm (QAOA) implemented with IBM Qiskit. The framework was tested on the standard IEEE 14-Bus system. To accommodate current quantum hardware limits, the quantum execution was localized to a 3-hour, 215statespace peak-load window. Within this comparative window, the classical solver outperformed on execution time (1.2 s) and cost (Rs. 65,000). However, the QAOA implementation (Rs. 69,000 within 45.5 s) provided a mathematically viable pathway for quantum-native grid dispatch. Furthermore, this paper highlights quantum hardware scaling issues caused by inequality-driven slack variables, developing a strict quadratic penalty approach to eliminate auxiliary variables and formulate an initial framework for future quantum grid utility control.
Modern smart grids demand robust computational solutions to manage real-time data processing, complex optimization, and fault resilience, especially with the integration of distributed and renewable energy resources (DERs). This study introduces a hybrid classical-quantum architecture tailored for these needs, leveraging classical computing for routine processing while employing quantum computing for high-complexity tasks. Experimental simulations demonstrate that the hybrid architecture reduces computation time by 40–41% and enhances energy efficiency by approximately 30% compared to traditional configurations. Additionally, its task allocation system improves scalability and resilience, making this architecture a viable solution for optimizing dynamic, large-scale smart grids. The findings offer a pathway toward a scalable and sustainable grid management system, bridging classical reliability with quantum advancements.