IDEAS home Printed from https://ideas.repec.org/a/eee/appene/v378y2025ipas030626192402169x.html
   My bibliography  Save this article

Learning global and local features of power load series through transformer and 2D-CNN: An image-based multi-step forecasting approach incorporating phase space reconstruction

Author

Listed:
  • Tang, Zihan
  • Ji, Tianyao
  • Kang, Jiaxi
  • Huang, Yunlin
  • Tang, Wenhu

Abstract

As modern power systems continue to evolve, accurate power load forecasting remains a critical issue in energy management. The phase space reconstruction (PSR) method can effectively retain the inner chaotic property of power load from a system dynamics perspective and thus is a promising knowledge-based method for power load forecasting. To fully leverage the PSR method’s capability in modeling this high-dimensional, non-stationary characteristics of power load data, and to address the challenges faced by its classical mathematical prediction algorithms in effectively solving contemporary prediction scenarios characterized by massive volumes of data. This study proposes a novel learning-based multi-step forecasting approach that utilizes an image-based modeling perspective for the reconstructed phase trajectories. Firstly, the feature engineering approach that simultaneously utilizes dynamic evolution features and temporal locality features in the trajectory image is proposed. Through mathematical derivation, the equivalent characterization of the PSR method and another time series modeling approach, patch segmentation (PS), is demonstrated for the first time. Building on this prior knowledge, a novel image-based modeling perspective incorporating a global and local feature extraction strategy is introduced to fully leverage these valuable features. Subsequently, within this framework, a novel deep learning model, termed PSR-GALIEN, is designed for end-to-end processing. This model employs a Transformer Encoder and 2D convolutional neural networks (CNNs) to extract global and local patterns from the image, while a multi-layer perceptron (MLP)-based predictor is utilized for efficient correlation modeling. Extensive experiments on five real-world datasets show that PSR-GALIEN consistently outperforms six state-of-the-art deep learning models in short-term load forecasting scenarios with varying characteristics, demonstrating its great robustness. Ablation studies further confirm that the image-based modeling approach captures more relevant features than traditional sequential methods, improving the overall forecasting accuracy. Additionally, the attributions of the forecasting results of PSR-GALIEN can be explained through the proposed visualization-based method, which significantly enhances its interpretability.

Suggested Citation

  • Tang, Zihan & Ji, Tianyao & Kang, Jiaxi & Huang, Yunlin & Tang, Wenhu, 2025. "Learning global and local features of power load series through transformer and 2D-CNN: An image-based multi-step forecasting approach incorporating phase space reconstruction," Applied Energy, Elsevier, vol. 378(PA).
  • Handle: RePEc:eee:appene:v:378:y:2025:i:pa:s030626192402169x
    DOI: 10.1016/j.apenergy.2024.124786
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S030626192402169X
    Download Restriction: Full text for ScienceDirect subscribers only

    File URL: https://libkey.io/10.1016/j.apenergy.2024.124786?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Fan, Guo-Feng & Peng, Li-Ling & Hong, Wei-Chiang, 2018. "Short term load forecasting based on phase space reconstruction algorithm and bi-square kernel regression model," Applied Energy, Elsevier, vol. 224(C), pages 13-33.
    2. Xu, Xuefang & Hu, Shiting & Shi, Peiming & Shao, Huaishuang & Li, Ruixiong & Li, Zhi, 2023. "Natural phase space reconstruction-based broad learning system for short-term wind speed prediction: Case studies of an offshore wind farm," Energy, Elsevier, vol. 262(PA).
    3. Huang, Yanmei & Hasan, Najmul & Deng, Changrui & Bao, Yukun, 2022. "Multivariate empirical mode decomposition based hybrid model for day-ahead peak load forecasting," Energy, Elsevier, vol. 239(PC).
    4. Wang, Deyun & Luo, Hongyuan & Grunder, Olivier & Lin, Yanbing, 2017. "Multi-step ahead wind speed forecasting using an improved wavelet neural network combining variational mode decomposition and phase space reconstruction," Renewable Energy, Elsevier, vol. 113(C), pages 1345-1358.
    5. Wang, Lei & Wang, Xinyu & Zhao, Zhongchao, 2024. "Mid-term electricity demand forecasting using improved multi-mode reconstruction and particle swarm-enhanced support vector regression," Energy, Elsevier, vol. 304(C).
    6. Li, Weiwei & Qian, Tong & Zhang, Yin & Shen, Yueqing & Wu, Chenghu & Tang, Wenhu, 2023. "Distributionally robust chance-constrained planning for regional integrated electricity–heat systems with data centers considering wind power uncertainty," Applied Energy, Elsevier, vol. 336(C).
    7. Hafeez, Ghulam & Khan, Imran & Jan, Sadaqat & Shah, Ibrar Ali & Khan, Farrukh Aslam & Derhab, Abdelouahid, 2021. "A novel hybrid load forecasting framework with intelligent feature engineering and optimization algorithm in smart grid," Applied Energy, Elsevier, vol. 299(C).
    8. Xie, Xuehua & Qian, Tong & Li, Weiwei & Tang, Wenhu & Xu, Zhao, 2024. "An individualized adaptive distributed approach for fast energy-carbon coordination in transactive multi-community integrated energy systems considering power transformer loading capacity," Applied Energy, Elsevier, vol. 375(C).
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Zhanpeng Gao & Wenjun Yi, 2025. "Prediction of Projectile Interception Point and Interception Time Based on Harris Hawk Optimization–Convolutional Neural Network–Support Vector Regression Algorithm," Mathematics, MDPI, vol. 13(3), pages 1-19, January.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Meng, Anbo & Zhu, Zibin & Deng, Weisi & Ou, Zuhong & Lin, Shan & Wang, Chenen & Xu, Xuancong & Wang, Xiaolin & Yin, Hao & Luo, Jianqiang, 2022. "A novel wind power prediction approach using multivariate variational mode decomposition and multi-objective crisscross optimization based deep extreme learning machine," Energy, Elsevier, vol. 260(C).
    2. Wang, Jianzhou & Gao, Jialu & Wei, Danxiang, 2022. "Electric load prediction based on a novel combined interval forecasting system," Applied Energy, Elsevier, vol. 322(C).
    3. Ihab Taleb & Guillaume Guerard & Frédéric Fauberteau & Nga Nguyen, 2022. "A Flexible Deep Learning Method for Energy Forecasting," Energies, MDPI, vol. 15(11), pages 1-16, May.
    4. Laouafi, Abderrezak & Laouafi, Farida & Boukelia, Taqiy Eddine, 2022. "An adaptive hybrid ensemble with pattern similarity analysis and error correction for short-term load forecasting," Applied Energy, Elsevier, vol. 322(C).
    5. Jianguo Zhou & Dongfeng Chen, 2021. "Carbon Price Forecasting Based on Improved CEEMDAN and Extreme Learning Machine Optimized by Sparrow Search Algorithm," Sustainability, MDPI, vol. 13(9), pages 1-20, April.
    6. Zhao, Baining & Qian, Tong & Li, Weiwei & Xin, Yanli & Zhao, Wei & Lin, Zekang & Tang, Wenhu & Jin, Xin & Cao, Wangzhang & Pan, Tingzhe, 2024. "Fast distributed co-optimization of electricity and natural gas systems hedging against wind fluctuation and uncertainty," Energy, Elsevier, vol. 298(C).
    7. Jihoon Moon & Junhong Kim & Pilsung Kang & Eenjun Hwang, 2020. "Solving the Cold-Start Problem in Short-Term Load Forecasting Using Tree-Based Methods," Energies, MDPI, vol. 13(4), pages 1-37, February.
    8. Andreas Lenk & Marcus Vogt & Christoph Herrmann, 2024. "An Approach to Predicting Energy Demand Within Automobile Production Using the Temporal Fusion Transformer Model," Energies, MDPI, vol. 18(1), pages 1-34, December.
    9. Li, Weiwei & Qian, Tong & Zhao, Wei & Huang, Wenwei & Zhang, Yin & Xie, Xuehua & Tang, Wenhu, 2023. "Decentralized optimization for integrated electricity–heat systems with data center based energy hub considering communication packet loss," Applied Energy, Elsevier, vol. 350(C).
    10. Kailai Ni & Jianzhou Wang & Guangyu Tang & Danxiang Wei, 2019. "Research and Application of a Novel Hybrid Model Based on a Deep Neural Network for Electricity Load Forecasting: A Case Study in Australia," Energies, MDPI, vol. 12(13), pages 1-30, June.
    11. Wu, Han & Liang, Yan & Heng, Jiani, 2023. "Pulse-diagnosis-inspired multi-feature extraction deep network for short-term electricity load forecasting," Applied Energy, Elsevier, vol. 339(C).
    12. Deyun Wang & Yanling Liu & Zeng Wu & Hongxue Fu & Yong Shi & Haixiang Guo, 2018. "Scenario Analysis of Natural Gas Consumption in China Based on Wavelet Neural Network Optimized by Particle Swarm Optimization Algorithm," Energies, MDPI, vol. 11(4), pages 1-16, April.
    13. Qi, Wei & Qin, Wenhu & Yun, Zhonghua, 2024. "Closed-loop state of charge estimation of Li-ion batteries based on deep learning and robust adaptive Kalman filter," Energy, Elsevier, vol. 307(C).
    14. Qu, Zhijian & Xu, Juan & Wang, Zixiao & Chi, Rui & Liu, Hanxin, 2021. "Prediction of electricity generation from a combined cycle power plant based on a stacking ensemble and its hyperparameter optimization with a grid-search method," Energy, Elsevier, vol. 227(C).
    15. Wang, Jianzhou & An, Yining & Li, Zhiwu & Lu, Haiyan, 2022. "A novel combined forecasting model based on neural networks, deep learning approaches, and multi-objective optimization for short-term wind speed forecasting," Energy, Elsevier, vol. 251(C).
    16. Mei-Li Shen & Cheng-Feng Lee & Hsiou-Hsiang Liu & Po-Yin Chang & Cheng-Hong Yang, 2021. "An Effective Hybrid Approach for Forecasting Currency Exchange Rates," Sustainability, MDPI, vol. 13(5), pages 1-29, March.
    17. Chabouni, Naima & Belarbi, Yacine & Benhassine, Wassim, 2020. "Electricity load dynamics, temperature and seasonality Nexus in Algeria," Energy, Elsevier, vol. 200(C).
    18. Wang, Lei & Wang, Xinyu & Zhao, Zhongchao, 2024. "Mid-term electricity demand forecasting using improved multi-mode reconstruction and particle swarm-enhanced support vector regression," Energy, Elsevier, vol. 304(C).
    19. Jing Bai & Jiahui Wang & Jin Ran & Xingyuan Li & Chuang Tu, 2024. "An Improved Neural Network Algorithm for Energy Consumption Forecasting," Sustainability, MDPI, vol. 16(21), pages 1-19, October.
    20. Dai, Yeming & Yang, Xinyu & Leng, Mingming, 2022. "Forecasting power load: A hybrid forecasting method with intelligent data processing and optimized artificial intelligence," Technological Forecasting and Social Change, Elsevier, vol. 182(C).

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:appene:v:378:y:2025:i:pa:s030626192402169x. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/description#description .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.