The identification of user segments based on their energy consumption characteristics is useful for a wide range of modern electrical engineering applications, from microgrid design to energy market forecasts. Numerous machine learning models have been applied to this problem, with varying levels of success. In this paper, a state-of-the-art quantum machine learning model known as variational quantum classifier, is applied as a proof of concept to tackle this issue. A dataset consisting of $\mathbf{1. 1}$ million measurements from Italian users was adapted for being use, the performance obtained was not on par with classical machine learning model but it shows promising characteristics.The identification of user segments based on their energy consumption characteristics is useful for a wide range of modern electrical engineering applications, from microgrid design to energy market forecasts. Numerous machine learning models have been applied to this problem, with varying levels of success. In this paper, a state-of-the-art quantum machine learning model known as variational quantum classifier, is applied as a proof of concept to tackle this issue. A dataset consisting of $\mathbf{1. 1}$ million measurements from Italian users was adapted for being use, the performance obtained was not on par with classical machine learning model but it shows promising characteristics.

International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME)Oct 16, 20251 citation

Quantum Machine Learning based Framework for Green and Sustainable Power Grids

S. Naganandhini, Rabiyathul Bachiriya, M. Sowmiya +1 more

The rising global need for renewable energy systems entails the constants call for research in ideal methodologies to enhance energy systems. As the problem of energy distribution, consumption and forecasting forecasting involves a number of inherent and intricate processes, conventional methods fail to combine with the dynamics of present day energy systems. With the help of efficient solutions by Quantum Machine Learning (QML), this paper aims to understand how QML solutions can transform Energy Management. The broad spectrum of QML techniques we consider includes quantum-enhanced optimization algorithms and quantum-assisted data analysis to discuss the use of the approaches in predicting energy demand, managing energy distribution, and enhancing consumption rates. In this work, we validate QML algorithms in simulation studies and consider real-world examples with other machine learning and optimization methods. They imply that, under certain circumstances, QML can produce notably higher performance with respect to the classical ML approaches in tasks of optimization, including the ones addressed in this paper at large datasets and complex, non-linear dependencies. The quantum algorithms demonstrated substantial gains in terms of energy prediction and the optimal use of energy with minimum lag, especially in situations where volatility and uncertainty are high. In addition, the possibility to identify the connections in mass energy consumption data that could not be found by using classical methods is one of the main advantages of QML in the activities of the company.The rising global need for renewable energy systems entails the constants call for research in ideal methodologies to enhance energy systems. As the problem of energy distribution, consumption and forecasting forecasting involves a number of inherent and intricate processes, conventional methods fail to combine with the dynamics of present day energy systems. With the help of efficient solutions by Quantum Machine Learning (QML), this paper aims to understand how QML solutions can transform Energy Management. The broad spectrum of QML techniques we consider includes quantum-enhanced optimization algorithms and quantum-assisted data analysis to discuss the use of the approaches in predicting energy demand, managing energy distribution, and enhancing consumption rates. In this work, we validate QML algorithms in simulation studies and consider real-world examples with other machine learning and optimization methods. They imply that, under certain circumstances, QML can produce notably higher performance with respect to the classical ML approaches in tasks of optimization, including the ones addressed in this paper at large datasets and complex, non-linear dependencies. The quantum algorithms demonstrated substantial gains in terms of energy prediction and the optimal use of energy with minimum lag, especially in situations where volatility and uncertainty are high. In addition, the possibility to identify the connections in mass energy consumption data that could not be found by using classical methods is one of the main advantages of QML in the activities of the company.

International Conference on Smart Electronics and Communication (ICOSEC)Sep 24, 20250 citations

Recent advancements in quantum machine learning applications: A review from smart grid viewpoint

Mohammad Hossein Shaabani, Seyed Pouria Miri, Seyed Reza Moghadasi +3 more

Applied Soft ComputingJul 10, 20260 citations

On the Use of Quantum Reinforcement Learning in Energy-Efficiency Scenarios

Eva Andrés, Manuel Pegalájar Cuéllar, Gabriel Navarro

In the last few years, deep reinforcement learning has been proposed as a method to perform online learning in energy-efficiency scenarios such as HVAC control, electric car energy management, or building energy management, just to mention a few. On the other hand, quantum machine learning was born during the last decade to extend classic machine learning to a quantum level. In this work, we propose to study the benefits and limitations of quantum reinforcement learning to solve energy-efficiency scenarios. As a testbed, we use existing energy-efficiency-based reinforcement learning simulators and compare classic algorithms with the quantum proposal. Results in HVAC control, electric vehicle fuel consumption, and profit optimization of electrical charging stations applications suggest that quantum neural networks are able to solve problems in reinforcement learning scenarios with better accuracy than their classical counterpart, obtaining a better cumulative reward with fewer parameters to be learned.In the last few years, deep reinforcement learning has been proposed as a method to perform online learning in energy-efficiency scenarios such as HVAC control, electric car energy management, or building energy management, just to mention a few. On the other hand, quantum machine learning was born during the last decade to extend classic machine learning to a quantum level. In this work, we propose to study the benefits and limitations of quantum reinforcement learning to solve energy-efficiency scenarios. As a testbed, we use existing energy-efficiency-based reinforcement learning simulators and compare classic algorithms with the quantum proposal. Results in HVAC control, electric vehicle fuel consumption, and profit optimization of electrical charging stations applications suggest that quantum neural networks are able to solve problems in reinforcement learning scenarios with better accuracy than their classical counterpart, obtaining a better cumulative reward with fewer parameters to be learned.

EnergiesAug 19, 202228 citations

Quantum Machine Learning for Solar Power Generation Forecasting

Abdul Rehman, Muhammad Aurangzeb, Sheeraz Iqbal +2 more

International Conference on Electrical, Computer and Energy Technologies (ICECET)Jul 1, 20260 citations

\mathbf{1. 1}

million measurements from Italian users was adapted for being use, the performance obtained was not on par with classical machine learning model but it shows promising characteristics.