IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v18y2025i11p2907-d1670082.html
   My bibliography  Save this article

A Multimodal Interaction-Driven Feature Discovery Framework for Power Demand Forecasting

Author

Listed:
  • Zifan Ning

    (College of Computer Science and Electronic Engineering, Hunan University, Changsha 410082, China
    Department of Engineering, King’s College London, London WC2R 2LS, UK)

  • Min Jin

    (College of Computer Science and Electronic Engineering, Hunan University, Changsha 410082, China)

  • Pan Zeng

    (College of Computer Science and Electronic Engineering, Hunan University, Changsha 410082, China)

Abstract

Power demand forecasting is a critical and challenging task for modern power systems and integrated energy systems. Due to the absence of well-established theoretical frameworks and publicly available feature databases on power demand changes, the known interpretable features of power demand fluctuations are primarily derived from expert experience and remain significantly limited. This substantially hinders advancements in power demand forecasting accuracy. Emerging multimodal learning approaches have demonstrated great promise in machine learning and AI-generated content (AIGC). In this paper, we propose, for the first time, a textual-knowledge-guided numerical feature discovery (TKNFD) framework for short-term power demand forecasting by interacting text modal data—a potentially valuable yet long-overlooked resource in the field of power demand forecasting—with numerical modal data. TKNFD systematically and automatically aggregates qualitative textual knowledge, expands it into a candidate feature-type set, collects corresponding numerical data for these features, and ultimately constructs four-dimensional multivariate source-tracking databases (4DM-STDs). Subsequently, TKNFD introduces a two-stage quantitative feature identification strategy that operates independently of forecasting models. The essence of TKNFD lies in achieving reliable and comprehensive feature discovery by fully exploiting the dual relationships of synonymy and complementarity between text modal data and numerical modal data in terms of granularity, scope, and temporality. In this study, TKNFD identifies 38–50 features while further interpreting their contributions and dependency correlations. Benchmark experiments conducted in Maine, Texas, and New South Wales demonstrate that the forecasting accuracy using TKNFD-identified features consistently surpasses that of state-of-the-art feature schemes by up to 36.37% MAPE. Notably, driven by multimodal interaction, TKNFD can discover previously unknown interpretable features without relying on prior empirical knowledge. This study reveals 10–16 previously unknown interpretable features, particularly several dominant features in integrated energy and astronomical dimensions. These discoveries enhance our understanding of the origins of strong randomness and non-linearity in power demand fluctuations. Additionally, the 4DM-STDs developed for these three regions can serve as public baseline databases for future research.

Suggested Citation

  • Zifan Ning & Min Jin & Pan Zeng, 2025. "A Multimodal Interaction-Driven Feature Discovery Framework for Power Demand Forecasting," Energies, MDPI, vol. 18(11), pages 1-25, June.
    • Handle: RePEc:gam:jeners:v:18:y:2025:i:11:p:2907-:d:1670082
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/18/11/2907/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1996-1073/18/11/2907/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Hatice Burcu Eskici & Necmettin Alpay Kocak, 2018. "A text mining application on monthly price developments reports," Central Bank Review, Research and Monetary Policy Department, Central Bank of the Republic of Turkey, vol. 18(2), pages 51-60.
    2. You, Minglei & Wang, Qian & Sun, Hongjian & Castro, Iván & Jiang, Jing, 2022. "Digital twins based day-ahead integrated energy system scheduling under load and renewable energy uncertainties," Applied Energy, Elsevier, vol. 305(C).
    3. Zhu, Jizhong & Dong, Hanjiang & Zheng, Weiye & Li, Shenglin & Huang, Yanting & Xi, Lei, 2022. "Review and prospect of data-driven techniques for load forecasting in integrated energy systems," Applied Energy, Elsevier, vol. 321(C).
    4. Alipour, Panteha & Mukherjee, Sayanti & Nateghi, Roshanak, 2019. "Assessing climate sensitivity of peak electricity load for resilient power systems planning and operation: A study applied to the Texas region," Energy, Elsevier, vol. 185(C), pages 1143-1153.
    5. 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).
    6. Achraf Saadaoui & Mohammed Ouassaid & Mohamed Maaroufi, 2023. "Overview of Integration of Power Electronic Topologies and Advanced Control Techniques of Ultra-Fast EV Charging Stations in Standalone Microgrids," Energies, MDPI, vol. 16(3), pages 1-21, January.
    7. Ruijin Zhu & Weilin Guo & Xuejiao Gong, 2019. "Short-Term Load Forecasting for CCHP Systems Considering the Correlation between Heating, Gas and Electrical Loads Based on Deep Learning," Energies, MDPI, vol. 12(17), pages 1-18, August.
    8. Cheng, Fang & Liu, Hui, 2024. "Multi-step electric vehicles charging loads forecasting: An autoformer variant with feature extraction, frequency enhancement, and error correction blocks," Applied Energy, Elsevier, vol. 376(PB).
    9. Ellen Hughes-Cromwick & Julia Coronado, 2019. "The Value of US Government Data to US Business Decisions," Journal of Economic Perspectives, American Economic Association, vol. 33(1), pages 131-146, Winter.
    10. Dixon, Robert K. & McGowan, Elizabeth & Onysko, Ganna & Scheer, Richard M., 2010. "US energy conservation and efficiency policies: Challenges and opportunities," Energy Policy, Elsevier, vol. 38(11), pages 6398-6408, November.
    11. Wang, Shaomin & Wang, Shouxiang & Chen, Haiwen & Gu, Qiang, 2020. "Multi-energy load forecasting for regional integrated energy systems considering temporal dynamic and coupling characteristics," Energy, Elsevier, vol. 195(C).
    12. Spyros Giannelos & Alexandre Moreira & Dimitrios Papadaskalopoulos & Stefan Borozan & Danny Pudjianto & Ioannis Konstantelos & Mingyang Sun & Goran Strbac, 2023. "A Machine Learning Approach for Generating and Evaluating Forecasts on the Environmental Impact of the Buildings Sector," Energies, MDPI, vol. 16(6), pages 1-37, March.
    13. Son, Hyojoo & Kim, Changwan, 2017. "Short-term forecasting of electricity demand for the residential sector using weather and social variables," Resources, Conservation & Recycling, Elsevier, vol. 123(C), pages 200-207.
    14. Amado, Alexandra & Cortez, Paulo & Rita, Paulo & Moro, Sérgio, 2018. "Research Trends On Big Data In Marketing: A Text Mining And Topic Modeling Based Literature Analysis," European Research on Management and Business Economics (ERMBE), Academia Europea de Dirección y Economía de la Empresa (AEDEM), vol. 24(1), pages 1-7.
    15. Jin Zhao & Fangxing Li & Qiwei Zhang, 2024. "Impacts of renewable energy resources on the weather vulnerability of power systems," Nature Energy, Nature, vol. 9(11), pages 1407-1414, November.
    16. Türkoğlu, A. Selim & Erkmen, Burcu & Eren, Yavuz & Erdinç, Ozan & Küçükdemiral, İbrahim, 2024. "Integrated Approaches in Resilient Hierarchical Load Forecasting via TCN and Optimal Valley Filling Based Demand Response Application," Applied Energy, Elsevier, vol. 360(C).
    Full references (including those not matched with items on IDEAS)

    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. Zhu, Jizhong & Dong, Hanjiang & Zheng, Weiye & Li, Shenglin & Huang, Yanting & Xi, Lei, 2022. "Review and prospect of data-driven techniques for load forecasting in integrated energy systems," Applied Energy, Elsevier, vol. 321(C).
    2. Dong, Hanjiang & Zhu, Jizhong & Li, Shenglin & Wu, Wanli & Zhu, Haohao & Fan, Junwei, 2023. "Short-term residential household reactive power forecasting considering active power demand via deep Transformer sequence-to-sequence networks," Applied Energy, Elsevier, vol. 329(C).
    3. Wang, Danhao & Peng, Daogang & Huang, Dongmei & Zhao, Huirong & Qu, Bogang, 2025. "MMEMformer: A multi-scale memory-enhanced transformer framework for short-term load forecasting in integrated energy systems," Energy, Elsevier, vol. 322(C).
    4. Hu, Rong & Zhou, Kaile & Lu, Xinhui, 2025. "Integrated loads forecasting with absence of crucial factors," Energy, Elsevier, vol. 322(C).
    5. Zhiyuan Zhang & Zhanshan Wang, 2023. "Multi-Objective Prediction of Integrated Energy System Using Generative Tractive Network," Mathematics, MDPI, vol. 11(20), pages 1-18, October.
    6. Li, Ke & Mu, Yuchen & Yang, Fan & Wang, Haiyang & Yan, Yi & Zhang, Chenghui, 2023. "A novel short-term multi-energy load forecasting method for integrated energy system based on feature separation-fusion technology and improved CNN," Applied Energy, Elsevier, vol. 351(C).
    7. Li, Chuang & Li, Guojie & Wang, Keyou & Han, Bei, 2022. "A multi-energy load forecasting method based on parallel architecture CNN-GRU and transfer learning for data deficient integrated energy systems," Energy, Elsevier, vol. 259(C).
    8. Tan, Mao & Liao, Chengchen & Chen, Jie & Cao, Yijia & Wang, Rui & Su, Yongxin, 2023. "A multi-task learning method for multi-energy load forecasting based on synthesis correlation analysis and load participation factor," Applied Energy, Elsevier, vol. 343(C).
    9. Liao, Chengchen & Tan, Mao & Li, Kang & Chen, Jie & Wang, Rui & Su, Yongxin, 2024. "Sequence signal prediction and reconstruction for multi-energy load forecasting in integrated energy systems: A bi-level multi-task learning method," Energy, Elsevier, vol. 313(C).
    10. Fan, Pengdan & Wang, Dan & Wang, Wei & Zhang, Xiuyu & Sun, Yuying, 2024. "A novel multi-energy load forecasting method based on building flexibility feature recognition technology and multi-task learning model integrating LSTM," Energy, Elsevier, vol. 308(C).
    11. Lin, Zhengyang & Lin, Tao & Li, Jun & Li, Chen, 2025. "A novel short-term multi-energy load forecasting method for integrated energy system based on two-layer joint modal decomposition and dynamic optimal ensemble learning," Applied Energy, Elsevier, vol. 378(PA).
    12. Jiao, Dingyu & Su, Huai & He, Yuxuan & Zhang, Li & Yang, Zhaoming & Peng, Shiliang & Zuo, Lili & Zhang, Jinjun, 2024. "A systematic method of long-sequence prediction of natural gas supply in IES based on spatio-temporal causal network of multi-energy," Applied Energy, Elsevier, vol. 376(PA).
    13. Xu, Jing & Wang, Xiaoying & Gu, Yujiong & Ma, Suxia, 2023. "A data-based day-ahead scheduling optimization approach for regional integrated energy systems with varying operating conditions," Energy, Elsevier, vol. 283(C).
    14. Ge Zhang & Songyang Zhu & Xiaoqing Bai, 2022. "Federated Learning-Based Multi-Energy Load Forecasting Method Using CNN-Attention-LSTM Model," Sustainability, MDPI, vol. 14(19), pages 1-14, October.
    15. Yan, Qin & Lu, Zhiying & Liu, Hong & He, Xingtang & Zhang, Xihai & Guo, Jianlin, 2024. "Short-term prediction of integrated energy load aggregation using a bi-directional simple recurrent unit network with feature-temporal attention mechanism ensemble learning model," Applied Energy, Elsevier, vol. 355(C).
    16. Guo, Hongxia & Chen, Lingxuan & Wang, Zhaocai & Li, Lin, 2025. "Day-ahead prediction of electric vehicle charging demand based on quadratic decomposition and dual attention mechanisms," Applied Energy, Elsevier, vol. 381(C).
    17. Che, Jinxing & Yuan, Fang & Zhu, Suling & Yang, Youlong, 2022. "An adaptive ensemble framework with representative subset based weight correction for short-term forecast of peak power load," Applied Energy, Elsevier, vol. 328(C).
    18. Abrardi, Laura & Cambini, Carlo, 2015. "Tariff regulation with energy efficiency goals," Energy Economics, Elsevier, vol. 49(C), pages 122-131.
    19. Boyu Xiang & Zhengyang Zhou & Shukun Gao & Guoping Lei & Zefu Tan, 2024. "A Planning Method for Charging Station Based on Long-Term Charging Load Forecasting of Electric Vehicles," Energies, MDPI, vol. 17(24), pages 1-20, December.
    20. Tian, Zhirui & Liu, Weican & Zhang, Jiahao & Sun, Wenpu & Wu, Chenye, 2025. "EDformer family: End-to-end multi-task load forecasting frameworks for day-ahead economic dispatch," Applied Energy, Elsevier, vol. 383(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:gam:jeners:v:18:y:2025:i:11:p:2907-:d:1670082. 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: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    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.