Implementing a Hybrid Quantum Neural Network for Wind Speed Forecasting: Insights from Quantum Simulator Experiences

The intermittent nature of wind speed poses challenges for its widespread utilization as an electrical power generation source. As the integration of wind energy into the power system increases, accurate wind speed forecasting becomes crucial. The reliable scheduling of wind power generation heavily...

Full description

Saved in:
Bibliographic Details
Main Authors: Ying-Yi Hong, Jay Bhie D. Santos
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/18/7/1771
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849730333146087424
author Ying-Yi Hong
Jay Bhie D. Santos
author_facet Ying-Yi Hong
Jay Bhie D. Santos
author_sort Ying-Yi Hong
collection DOAJ
description The intermittent nature of wind speed poses challenges for its widespread utilization as an electrical power generation source. As the integration of wind energy into the power system increases, accurate wind speed forecasting becomes crucial. The reliable scheduling of wind power generation heavily relies on precise wind speed forecasts. This paper presents an extended work that focuses on a hybrid model for 24 h ahead wind speed forecasting. The proposed model combines residual Long Short-Term Memory (LSTM) and a quantum neural network that is studied by a quantum simulator, leveraging the support of NVIDIA Compute Unified Device Architecture (CUDA). To ensure the desired accuracy, a comparative analysis is conducted, examining the qubit count and quantum circuit depth of the proposed model. The execution time required for the model is significantly reduced when the GPU incorporates CUDA, accounting for only 8.29% of the time required by a classical CPU. In addition, different quantum embedding layers with various entangler layers in the quantum neural network are explored. The simulation results utilizing an offshore wind farm dataset demonstrate that the proper number of qubits and embedding layer can achieve favorable 24 h ahead wind speed forecasts.
format Article
id doaj-art-82db81665ac24b7da5dffa32161e4402
institution DOAJ
issn 1996-1073
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj-art-82db81665ac24b7da5dffa32161e44022025-08-20T03:08:55ZengMDPI AGEnergies1996-10732025-04-01187177110.3390/en18071771Implementing a Hybrid Quantum Neural Network for Wind Speed Forecasting: Insights from Quantum Simulator ExperiencesYing-Yi Hong0Jay Bhie D. Santos1Department of Electrical Engineering, Chung Yuan Christian University, Taoyuan City 320314, TaiwanDepartment of Electrical Engineering, Chung Yuan Christian University, Taoyuan City 320314, TaiwanThe intermittent nature of wind speed poses challenges for its widespread utilization as an electrical power generation source. As the integration of wind energy into the power system increases, accurate wind speed forecasting becomes crucial. The reliable scheduling of wind power generation heavily relies on precise wind speed forecasts. This paper presents an extended work that focuses on a hybrid model for 24 h ahead wind speed forecasting. The proposed model combines residual Long Short-Term Memory (LSTM) and a quantum neural network that is studied by a quantum simulator, leveraging the support of NVIDIA Compute Unified Device Architecture (CUDA). To ensure the desired accuracy, a comparative analysis is conducted, examining the qubit count and quantum circuit depth of the proposed model. The execution time required for the model is significantly reduced when the GPU incorporates CUDA, accounting for only 8.29% of the time required by a classical CPU. In addition, different quantum embedding layers with various entangler layers in the quantum neural network are explored. The simulation results utilizing an offshore wind farm dataset demonstrate that the proper number of qubits and embedding layer can achieve favorable 24 h ahead wind speed forecasts.https://www.mdpi.com/1996-1073/18/7/1771deep learninggraphical processing unitquantum approximate optimization algorithmresidual long short-term memorywind speed forecasting
spellingShingle Ying-Yi Hong
Jay Bhie D. Santos
Implementing a Hybrid Quantum Neural Network for Wind Speed Forecasting: Insights from Quantum Simulator Experiences
Energies
deep learning
graphical processing unit
quantum approximate optimization algorithm
residual long short-term memory
wind speed forecasting
title Implementing a Hybrid Quantum Neural Network for Wind Speed Forecasting: Insights from Quantum Simulator Experiences
title_full Implementing a Hybrid Quantum Neural Network for Wind Speed Forecasting: Insights from Quantum Simulator Experiences
title_fullStr Implementing a Hybrid Quantum Neural Network for Wind Speed Forecasting: Insights from Quantum Simulator Experiences
title_full_unstemmed Implementing a Hybrid Quantum Neural Network for Wind Speed Forecasting: Insights from Quantum Simulator Experiences
title_short Implementing a Hybrid Quantum Neural Network for Wind Speed Forecasting: Insights from Quantum Simulator Experiences
title_sort implementing a hybrid quantum neural network for wind speed forecasting insights from quantum simulator experiences
topic deep learning
graphical processing unit
quantum approximate optimization algorithm
residual long short-term memory
wind speed forecasting
url https://www.mdpi.com/1996-1073/18/7/1771
work_keys_str_mv AT yingyihong implementingahybridquantumneuralnetworkforwindspeedforecastinginsightsfromquantumsimulatorexperiences
AT jaybhiedsantos implementingahybridquantumneuralnetworkforwindspeedforecastinginsightsfromquantumsimulatorexperiences