EN基于混合经典量子并行网络的电力负荷预测算法
Power load forecasting algorithm based on hybrid classical quantum parallel Network
- 电力大数据 2026年第1期
- 作者机构：
1. 贵州电网有限责任公司电力科学研究院,贵州,贵阳
2. 贵州电网有限责任公司,贵州,贵阳
- 作者简介：
- 基金信息：
DOI：
中图分类号：-
纸质出版：2026
- 稿件说明：
移动端阅览
高正浩, 张历, 欧家祥, 等. 基于混合经典量子并行网络的电力负荷预测算法[J]. 电力大数据, 2026,(1).
Gao ZhengHao, Zhang Li, Ou Jiaxiang, et al. Power load forecasting algorithm based on hybrid classical quantum parallel Network[J]. 2026, (1).
摘要
电力负荷预测在能源领域中占据着至关重要的地位，它使电力公司及相关研究者能够基于现有信息进行准确预测，从而实现资源的优化配置并减少电力资源的浪费。本文采用了一种经典-量子并行混合神经网络架构，该架构结合了参数量子电路与传统前馈神经网络的优势，旨在针对工业环境中的时间序列预测任务进行深入探索。我们利用参数化量子变分电路构建了独立模块，专注于历史长期趋势的分解，同时结合短期趋势与周期性趋势，以提升未来电力负荷预测的准确性。本文所提混合框架算法，在 VQNet 量子模拟平台上进行训练，在性能上显著优于传统的经典 LSTM 和 Attention 模型。这些发现不仅拓宽了关于量子与经典机器学习技术如何整合以应对能源领域实际挑战的科学理解，也为优化发电厂的运营提供了新的视角和理论基础。
Abstract
Electric load forecasting plays a crucial role in the energy sector
enabling power companies and relevant researchers to make accurate predictions based on existing information
thereby achieving optimal resource allocation and reducing waste of electrical resources. This paper adopts a classical-quantum parallel hybrid neural network architecture that combines the advantages of parameterized quantum circuits and traditional feedforward neural networks
aiming to conduct an in-depth exploration of time series forecasting tasks in industrial environments. We constructed independent modules using parameterized quantum variational circuits
focusing on the decomposition of long-term historical trends while incorporating short-term and periodic trends to enhance the accuracy of future electric load forecasting. The hybrid framework algorithm proposed in this paper is trained on the VQNet quantum simulation platform and is significantly superior to the traditional classic LSTM and Attention models in performance. These findings not only broaden the scientific understanding of how quantum and classical machine learning techniques can be integrated to tackle real challenges in the energy field but also provide new perspectives and theoretical foundations for optimizing power plant operations.
关键词
Keywords
references
Zhou Yihong, Ding Zhaohao, Wen Qingsong, Wang Yi. Robust load forecasting towards adversarial attacks via bayesian learning[J]. IEEE Transactions on Power Systems, 2022.
孙超,吕琪,朱思彤,等。考虑多特征影响的双层 XGBoost 算法超短期电力负荷预测 [J]. 高电压技术,2021, 47 (08):2885-2898.
Dunjko V, Briegel H J. Machine learning and artificial intelligence in the quantum domain: a review of recent progress[J]. Reports on Progress in Physics, 2018, 81(07):074001.
Melnikov A, Kordzanganeh M, Alodjants A, Lee R K. Quantum machine learning: from physics to software engineering[J]. Advances in Physics: X, 2023, 08(01).
Benedetti M, Lloyd E, Sack S, Fiorentini M. Parameterized Quantum Circuits as Machine Learning Models[J]. Quantum Science and Technology, 2019, 04:043001.
Jerbi S, Gyurik C, Marshall S, Briegel H, Dunjko V. Parametrized quantum policies for reinforcement learning[J]. Advances in Neural Information Processing Systems, 2021, 34:28362-28375.
McClean J R, Boixo S, Smelyanskiy V N, Babbush R, Neven H. Barren plateaus in quantum neural network training landscapes[J]. Nature Communications, 2018, 09(01).
Kordzanganeh M, Sekatski P, Fedichkin L, Melnikov A. An exponentially-growing family of universal quantum circuits[J]. Machine Learning: Science and Technology, 2023.
Skolik A, Jerbi S, Dunjko V. Quantum agents in the gym: a variational quantum algorithm for deep Q-learning[J]. Quantum, 2022, 06:720.
McClean J R, Romero J, Babbush R, Aspuru-Guzik A. The theory of variational hybrid quantum-classical algorithms[J]. New Journal of Physics, 2016, 18(02):023023.
Mitarai K, Negoro M, Kitagawa M, Fujii K. Quantum circuit learning[J]. Physical Review A, 2018, 98(03).
Perelshtein M, Sagingalieva A, Pinto K, Shete V, Pakhomchik A, et al. Practical application-specific advantage through hybrid quantum computing[J]. arXiv preprint arXiv:2205.04858, 2022.
梁凌宇,赵翔宇,黄文琦,等。融合多类人工智能模型的电力系统负荷短期预测技术研究 [J]. 电力大数据,2022, 25 (06):16-23.
Kordzanganeh M, Kosichkina D, Melnikov A. Parallel Hybrid Networks: an interplay between quantum and classical neural networks[J]. arXiv preprint arXiv:10.34133/icomputing.0028, 2023.
Kurkin A, Hegemann J, Kordzanganeh M, Melnikov A. Forecasting the steam mass flow in a powerplant using the parallel hybrid network[J]. arXiv preprint arXiv:2307.09483, 2024.
Wang S, Wu H, Shi X, Hu T, Luo H, Ma L, Zhang J Y, Zhou J. TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting[J]. arXiv preprint arXiv:2405.14616, 2024.
Almazrouee A I, Almeshal A M, Almutairi A S, Alenezi M R, Alhajeri S N. Long-term forecasting of electrical loads in Kuwait using prophet and holt-winters models[J]. Applied Sciences, 2020, 10(16):5627.
Wang Y, Sun S, Chen X, Zeng X, Kong Y, Chen J, Guo Y, Wang T. Short-term load forecasting of industrial customers based on svmd and xgboost[J]. International Journal of Electrical Power and Energy Systems, 2021, 129:106830.
Gupta A, Kumar A. Mid Term Daily Load Forecasting using ARIMA, Wavelet-ARIMA and Machine Learning[C]. 2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I CPS Europe), Madrid, 2020:1-5.
Ke G, Meng Q, Finley T, Wang T, Chen W, Ma W, Ye Q, Liu T Y. LightGBM: A highly efficient gradient boosting decision tree[C]. NeurIPS, 2017:3146-3154.
韩叶林,张展耀,俞伊丽,等。基于 LSTM 及分位数回归理论的配电变压器重过载概率预测 [J]. 电力大数据,2023, 26 (06):1-8.
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez A N, Kaiser L, Polosukhin I. Attention Is All You Need[C]. Advances in Neural Information Processing Systems (NeurIPS), vol. 30, 2017:5998-6008.
Liu H, Ma Z, Yang L, Zhou T, Xia R, Wang Y, Wen Q. SADI: A Self-Adaptive Decomposed Interpretable Framework for Electric Load Forecasting Under Extreme Events[C]. ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, 2023:1-5.
Kordzanganeh M, Kosichkina D, Melnikov A. Parallel Hybrid Networks: An Interplay between Quantum and Classical Neural Networks[J]. Intelligent Computing, 2023, 02. doi:10.34133/icomputing.0028.
Chai T, Draxler R R. Root mean square error (RMSE) or mean absolute error (MAE)?–Arguments against avoiding RMSE in the literature[J]. Geoscientific Model Development, 2014, 07:1247-1250.
Yang S, Ma W, Pi X, Qian S. A deep learning approach to real-time parking occupancy prediction in transportation networks incorporating multiple spatio-temporal data sources[J]. Transportation Research Part C: Emerging Technologies, 2019, 107:248-265.
李焱,李磊,贾雅君,等。基于随机森林算法的短期电力负荷预测 [J]. 电力系统保护与控制,2020, 48 (21):117-124.
Liu H, Ma Z, Yang L, Zhou T, Xia R, Wang Y, Wen Q. SADI: A Self-Adaptive Decomposed Interpretable Framework for Electric Load Forecasting Under Extreme Events[C]. ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023:1-5.
Zhou Yihong, Ding Zhaohao, Wen Qingsong, Wang Yi. Robust load forecasting towards adversarial attacks via bayesian learning[J]. IEEE Transactions on Power Systems, 2022.
孙超,吕琪,朱思彤,等。考虑多特征影响的双层 XGBoost 算法超短期电力负荷预测 [J]. 高电压技术,2021, 47 (08):2885-2898.
Dunjko V, Briegel H J. Machine learning and artificial intelligence in the quantum domain: a review of recent progress[J]. Reports on Progress in Physics, 2018, 81(07):074001.
Melnikov A, Kordzanganeh M, Alodjants A, Lee R K. Quantum machine learning: from physics to software engineering[J]. Advances in Physics: X, 2023, 08(01).
Benedetti M, Lloyd E, Sack S, Fiorentini M. Parameterized Quantum Circuits as Machine Learning Models[J]. Quantum Science and Technology, 2019, 04:043001.
Jerbi S, Gyurik C, Marshall S, Briegel H, Dunjko V. Parametrized quantum policies for reinforcement learning[J]. Advances in Neural Information Processing Systems, 2021, 34:28362-28375.
McClean J R, Boixo S, Smelyanskiy V N, Babbush R, Neven H. Barren plateaus in quantum neural network training landscapes[J]. Nature Communications, 2018, 09(01).
Kordzanganeh M, Sekatski P, Fedichkin L, Melnikov A. An exponentially-growing family of universal quantum circuits[J]. Machine Learning: Science and Technology, 2023.
Skolik A, Jerbi S, Dunjko V. Quantum agents in the gym: a variational quantum algorithm for deep Q-learning[J]. Quantum, 2022, 06:720.
McClean J R, Romero J, Babbush R, Aspuru-Guzik A. The theory of variational hybrid quantum-classical algorithms[J]. New Journal of Physics, 2016, 18(02):023023.
Mitarai K, Negoro M, Kitagawa M, Fujii K. Quantum circuit learning[J]. Physical Review A, 2018, 98(03).
Perelshtein M, Sagingalieva A, Pinto K, Shete V, Pakhomchik A, et al. Practical application-specific advantage through hybrid quantum computing[J]. arXiv preprint arXiv:2205.04858, 2022.
梁凌宇,赵翔宇,黄文琦,等。融合多类人工智能模型的电力系统负荷短期预测技术研究 [J]. 电力大数据,2022, 25 (06):16-23.
Kordzanganeh M, Kosichkina D, Melnikov A. Parallel Hybrid Networks: an interplay between quantum and classical neural networks[J]. arXiv preprint arXiv:10.34133/icomputing.0028, 2023.
Kurkin A, Hegemann J, Kordzanganeh M, Melnikov A. Forecasting the steam mass flow in a powerplant using the parallel hybrid network[J]. arXiv preprint arXiv:2307.09483, 2024.
Wang S, Wu H, Shi X, Hu T, Luo H, Ma L, Zhang J Y, Zhou J. TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting[J]. arXiv preprint arXiv:2405.14616, 2024.
Almazrouee A I, Almeshal A M, Almutairi A S, Alenezi M R, Alhajeri S N. Long-term forecasting of electrical loads in Kuwait using prophet and holt-winters models[J]. Applied Sciences, 2020, 10(16):5627.
Wang Y, Sun S, Chen X, Zeng X, Kong Y, Chen J, Guo Y, Wang T. Short-term load forecasting of industrial customers based on svmd and xgboost[J]. International Journal of Electrical Power and Energy Systems, 2021, 129:106830.
Gupta A, Kumar A. Mid Term Daily Load Forecasting using ARIMA, Wavelet-ARIMA and Machine Learning[C]. 2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I CPS Europe), Madrid, 2020:1-5.
Ke G, Meng Q, Finley T, Wang T, Chen W, Ma W, Ye Q, Liu T Y. LightGBM: A highly efficient gradient boosting decision tree[C]. NeurIPS, 2017:3146-3154.
韩叶林,张展耀,俞伊丽,等。基于 LSTM 及分位数回归理论的配电变压器重过载概率预测 [J]. 电力大数据,2023, 26 (06):1-8.
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez A N, Kaiser L, Polosukhin I. Attention Is All You Need[C]. Advances in Neural Information Processing Systems (NeurIPS), vol. 30, 2017:5998-6008.
Liu H, Ma Z, Yang L, Zhou T, Xia R, Wang Y, Wen Q. SADI: A Self-Adaptive Decomposed Interpretable Framework for Electric Load Forecasting Under Extreme Events[C]. ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, 2023:1-5.
Kordzanganeh M, Kosichkina D, Melnikov A. Parallel Hybrid Networks: An Interplay between Quantum and Classical Neural Networks[J]. Intelligent Computing, 2023, 02. doi:10.34133/icomputing.0028.
Chai T, Draxler R R. Root mean square error (RMSE) or mean absolute error (MAE)?–Arguments against avoiding RMSE in the literature[J]. Geoscientific Model Development, 2014, 07:1247-1250.
Yang S, Ma W, Pi X, Qian S. A deep learning approach to real-time parking occupancy prediction in transportation networks incorporating multiple spatio-temporal data sources[J]. Transportation Research Part C: Emerging Technologies, 2019, 107:248-265.
李焱,李磊,贾雅君,等。基于随机森林算法的短期电力负荷预测 [J]. 电力系统保护与控制,2020, 48 (21):117-124.
Liu H, Ma Z, Yang L, Zhou T, Xia R, Wang Y, Wen Q. SADI: A Self-Adaptive Decomposed Interpretable Framework for Electric Load Forecasting Under Extreme Events[C]. ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023:1-5.
0
浏览量
2
下载量
0
CSCD
- Meta-XML下载
- BibTeX下载
- Endnote下载
- RefMan 下载
- NoteExpress下载
- NoteFirst下载
关联资源
相关文章
相关作者
相关机构
AI问答- 技术支持由北京北大方正电子有限公司提供 京ICP备09064830号-19
京公网安备11010802024621 - 本系统建议在Chrome、 IE9+ 以上版本浏览器阅读本站内容，360浏览器请切换至极速模式
- Cookies帮助我们提供服务并提供个性化体验。使用本网站，即表示您同意我们使用Cookies