
西安交通大学电气工程学院,陕西省西安市 710049
Received:29 August 2025,
Revised:2025-12-24,
Online First:02 April 2026,
Published:10 October 2026
移动端阅览
陈宇轩,谢海鹏,许若一等.基于可解释多模态增强的电力负荷预测方法[J].电力系统自动化,2026,50(19):147-158.
CHEN Yuxuan,XIE Haipeng,XU Ruoyi,et al.Power Load Forecasting Method Based on Interpretable Multi-modal Enhancement[J].Automation of Electric Power Systems,2026,50(19):147-158.
陈宇轩,谢海鹏,许若一等.基于可解释多模态增强的电力负荷预测方法[J].电力系统自动化,2026,50(19):147-158. DOI: 10.7500/AEPS20250829010.
CHEN Yuxuan,XIE Haipeng,XU Ruoyi,et al.Power Load Forecasting Method Based on Interpretable Multi-modal Enhancement[J].Automation of Electric Power Systems,2026,50(19):147-158. DOI: 10.7500/AEPS20250829010.
准确的负荷预测对电网的安全稳定运行具有重要意义。现有深度学习预测方法跨主体泛化能力较差,且难以适应小样本场景,而结合预训练大模型的预测手段往往忽略不同模态信息对齐的重要性,且模型可解释性较差。为了解决上述问题,提出一种基于可解释多模态增强的电力负荷预测方法。首先,通过指令微调的大语言模型输出原始负荷时间序列的文本模态信息,实现模态增强;其次,经过双通道编码模块得到多模态信息的嵌入;然后,提出基于部分信息分解的对比学习策略,实现多模态表征的可解释性对齐;最后,基于Transformer架构输出预测结果。在各种真实世界场景公开数据集上的测试结果表明,所提模型展现出具有竞争力的预测性能,超过常用的基线方法,并且具有一定的可解释性,为电力负荷预测场景提供了有力保障。
Accurate load forecasting is of great significance for the safe and stable operation of power grids. Existing deep learning forecasting methods suffer from poor cross-entity generalization ability and struggle to adapt to few-shot scenarios. Moreover
the forecasting methods incorporating pre-trained large models often overlook the importance of aligning information from different modalities and exhibit poor model interpretability. To address these issues
this paper proposes a power load forecasting method based on interpretable multi-modal enhancement. First
an instruction-finetuned large language model is used to output textual modal information from the raw load time series
achieving modal enhancement. Subsequently
a dual-channel encoding module processes this information to obtain multimodal embeddings. Second
this paper proposes a contrastive learning strategy based on partial information decomposition to achieve interpretable alignment of multi-modal representations. Finally
the forecasting results are output based on a Transformer architecture. Test results on public datasets from various real-world scenarios demonstrate that the proposed model exhibits competitive forecasting performance surpassing commonly used baseline methods and possesses certain interpretability
thereby providing guarantees for power load forecasting scenarios.
孙秋野 , 张瑞霞 , 陈东岳 . 大模型技术赋能电力系统的应用及技术路线展望 [J/OL]. 电力系统自动化 , 2025-12-21 . https://link.cnki.net/urlid/32.1180.TP.20250317.1811.006 https://link.cnki.net/urlid/32.1180.TP.20250317.1811.006 .
Sun Qiuye , Zhang Ruixia , Chen Dongyue . Application and route prospect of empowering power systems with large language models [J]. Automation of Electric Power Systems , 2025-12-21 . https://link.cnki.net/urlid/32.1180.TP.20250317.1811.006 https://link.cnki.net/urlid/32.1180.TP.20250317.1811.006 .
乐健 , 郎红科 , 谭甜源 , 等 . 新型配电系统分布式经济调度信息安全问题研究综述 [J]. 电力系统自动化 , 2024 , 48 ( 12 ): 177 - 191 .
Le Jian , Lang Hongke , Tan Tianyuan , et al . Review of research on information security problems in distributed economic dispatch for new distribution system [J]. Automation of Electric Power Systems , 2024 , 48 ( 12 ): 177 - 191 .
韩富佳 , 王晓辉 , 乔骥 , 等 . 基于人工智能技术的新型电力系统负荷预测研究综述 [J]. 中国电机工程学报 , 2023 , 43 ( 22 ): 8569 - 8591 .
Han Fujia , Wang Xiaohui , Qiao Ji , et al . Review on artificial intelligence based load forecasting research for the new-type power system [J]. Proceedings of the CSEE , 2023 , 43 ( 22 ): 8569 - 8591 .
李楠 , 王鹤潼 , 张光耀 , 等 . 基于双重分解策略与MSTCN-BiLSTM的超短期负荷预测 [J/OL]. 电工技术学报 , 2026-08-18 . https://doi.org/10.19595/j.cnki.1000-6753.tces.251333 https://doi.org/10.19595/j.cnki.1000-6753.tces.251333 .
Li Nan , Wang Hetong , Zhang Guangyao , et al . Ultra-short-term load forecasting based on a dual decomposition strategy and MSTCN-BiLSTM [J/OL]. Transactions of China Electrotechnical Society , 2026-08-18 . https://doi.org/10.19595/j.cnki.1000-6753.tces.251333 https://doi.org/10.19595/j.cnki.1000-6753.tces.251333 .
万灿 , 崔文康 , 宋永华 . 新能源电力系统概率预测:基本概念与数学原理 [J]. 中国电机工程学报 , 2021 , 41 ( 19 ): 6493 - 6509 .
Wan Can , Cui Wenkang , Song Yonghua . Probabilistic forecasting for power systems with renewable energy sources: basic concepts and mathematical principles [J]. Proceedings of the CSEE , 2021 , 41 ( 19 ): 6493 - 6509 .
Hyndman R , Koehler A B , Ord J K , et al . Forecasting with exponential smoothing: the state space approach [J]. Springer Science & Business Media , 2008 , 3 , 9 .
Box G E P , Jenkins G M , Reinsel G C , et al . Time series analysis: forecasting and control [J]. The Statistician , 1978 , 27 : 265 .
Contreras J , Espinola R , Nogales F J , et al . ARIMA models to predict next-day electricity prices [J]. IEEE Transactions on Power Systems , 2003 , 18 ( 3 ): 1014 - 1020 .
丁藤 , 冯冬涵 , 林晓凡 , 等 . 基于修正后ARIMA-GARCH模型的超短期风速预测 [J]. 电网技术 , 2017 , 41 ( 6 ): 1808 - 1814 .
Ding Teng , Feng Donghan , Lin Xiaofan , et al . Ultra-short-term wind speed forecasting based on improved ARIMA-GARCH model [J]. Power System Technology , 2017 , 41 ( 6 ): 1808 - 1814 .
Dab K , Nagarsheth S H , Amara F , et al . Uncertainty quantification in load forecasting for smart grids using non-parametric statistics [J]. IEEE Access , 2024 , 12 : 138000 - 138017 .
方娜 , 陈浩 , 邓心 , 等 . 基于VMD-ARIMA-DBN的短期电力负荷预测 [J]. 电力系统及其自动化学报 , 2023 , 35 ( 6 ): 59 - 65 .
Fang Na , Chen Hao , Deng Xin , et al . Short-term power load forecasting based on VMD-ARIMA-DBN [J]. Proceedings of the CSU-EPSA , 2023 , 35 ( 6 ): 59 - 65 .
Tshipata O T , Kazumba D T , Nzakuna P S , et al . Multi-horizon short-term electrical load forecasting: a comparative analysis of statistical models and deep neural networks [C]// 2024 IEEE International Symposium on Measurements & Networking (M&N) , 2024 : 1 - 6 .
Graves A . Long short-term memory [M]. Berlin, Heidelberg : Springer , 2012 : 37 - 45 .
Zhou H Y , Zhang S H , Peng J Q , et al . Informer: beyond efficient transformer for long sequence time-series forecasting [J]. Proceedings of the AAAI Conference on Artificial Intelligence , 2021 , 35 ( 12 ): 11106 - 11115 .
Wu H X , Xu J H , Wang J M , et al . Autoformer: decomposition transformers with auto-correlation for long-term series forecasting [PP/OL]. [ 2025-08-21 ]. https://arxiv.org/abs/2106.13008 https://arxiv.org/abs/2106.13008 .
范杏蕊 , 李元诚 . 基于改进Autoformer模型的短期电力负荷预测 [J]. 电力自动化设备 , 2024 , 44 ( 4 ): 171 - 177 .
Fan Xingrui , Li Yuancheng . Short-term power load forecasting based on improved Autoformer model [J]. Electric Power Automation Equipment , 2024 , 44 ( 4 ): 171 - 177 .
Zhou T , Ma Z , Wen Q , et al . Fedformer: frequency enhanced decomposed transformer for long-term series forecasting [C]// International Conference on Machine Learning , 2022 .
Zeng A L , Chen M X , Zhang L , et al . Are transformers effective for time series forecasting? [J]. Proceedings of the AAAI Conference on Artificial Intelligence , 2023 , 37 ( 9 ): 11121 - 11128 .
Nie Y Q , Nguyen N H , Sinthong P , et al . A time series is worth 64 words: long-term forecasting with transformers [PP/OL]. [ 2025-08-21 ]. https://arxiv.org/abs/2211.14730 https://arxiv.org/abs/2211.14730 .
Guo Y X , Li Y , Qiao X B , et al . BiLSTM multitask learning-based combined load forecasting considering the loads coupling relationship for multienergy system [J]. IEEE Transactions on Smart Grid , 2022 , 13 ( 5 ): 3481 - 3492 .
李楠 , 金淳熙 , 陶亮 , 等 . 基于多尺度二次特征提取的短期电力负荷预测模型 [J]. 电力系统保护与控制 , 2025 , 53 ( 19 ): 114 - 126 .
Li Nan , Jin Chunxi , Tao Liang , et al . A short-term electric load forecasting model based on multi-scale secondary feature extraction [J]. Power System Protection and Control , 2025 , 53 ( 19 ): 114 - 126 .
Zhao P F , Hu W H , Cao D , et al . Probabilistic multienergy load forecasting based on hybrid attention-enabled transformer network and Gaussian process-aided residual learning [J]. IEEE Transactions on Industrial Informatics , 2024 , 20 ( 6 ): 8379 - 8393 .
Wang C , Wang Y , Ding Z T , et al . Probabilistic multi-energy load forecasting for integrated energy system based on Bayesian transformer network [J]. IEEE Transactions on Smart Grid , 2024 , 15 ( 2 ): 1495 - 1508 .
蔡子龙 , 李嘉棋 , 沈赋 , 等 . 基于SDAE-EEMD降噪分解与改进Informer-BiLSTM模型的电力短期负荷预测方法 [J]. 电网技术 , 2025 , 49 ( 12 ): 5009 - 5018 .
Cai Zilong , Li Jiaqi , Shen Fu , et al . A short-term power load forecasting method based on SDAE-EEMD denoising decomposition and an improved informer-BiLSTM model [J]. Power System Technology , 2025 , 49 ( 12 ): 5009 - 5018 .
Chang Y P , Wang X , Wang J D , et al . A survey on evaluation of large language models [J]. ACM Transactions on Intelligent Systems and Technology , 2024 , 15 ( 3 ): 1 - 45 .
Xue H , Salim F D . PromptCast: a new prompt-based learning paradigm for time series forecasting [J]. IEEE Transactions on Knowledge and Data Engineering , 2024 , 36 ( 11 ): 6851 - 6864 .
Chen Y X , Xie H P . TRACE: unlocking the potential of LLMs in time series forecasting for distributed energy resources [J]. IEEE Transactions on Artificial Intelligence , 2026 , 7 ( 2 ): 696 - 709 .
Zhou T , Niu P , Sun L , et al . One fits all: power general time series analysis by pretrained lm [J] Advances in Neural Information Processing Systems , 2023 , 36 : 43322 - 43355 .
Chang C , Wang W Y , Peng W C , et al . LLM4TS: aligning pre-trained LLMs as data-efficient time-series forecasters [J]. ACM Transactions on Intelligent Systems and Technology , 2025 , 16 ( 3 ): 1 - 20 .
Jin M , Wang S Y , Ma L T , et al . Time-LLM: time series forecasting by reprogramming large language models [EB/OL]. [ 2025-08-21 ]. https://arxiv.org/abs/2310.01728 https://arxiv.org/abs/2310.01728 .
Liu X , Hu J F , Li Y , et al . UniTime: a language-empowered unified model for cross-domain time series forecasting [C]// Proceedings of the ACM Web Conference , 2024 .
Liu C X , Xu Q X , Miao H , et al . TimeCMA: towards LLM-empowered multivariate time series forecasting via cross-modality alignment [J]. Proceedings of the AAAI Conference on Artificial Intelligence , 2025 , 39 ( 18 ): 18780 - 18788 .
Asuncion A , Newman D . UCI machine learning repository [EB/OL]. [ 2025-08-21 ]. https://archive-beta.ics.uci.edu/ https://archive-beta.ics.uci.edu/ .
Trivedi R , Bahloul M , Saif A , et al . Comprehensive dataset on electrical load profiles for energy community in Ireland [J]. Scientific Data , 2024 , 11 : 621 .
Heer P , Derungs C , Huber B , et al . Comprehensive energy demand and usage data for building automation [J]. Scientific Data , 2024 , 11 : 469 .
Zhang L , Awal R , Agrawal A . Contrasting intra-modal and ranking cross-modal hard negatives to enhance visio-linguistic compositional understanding [C]// 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , 2024 .
RADFORD A , KIM J W , HALLACY C , et al . Learning transferable visual models from natural language supervision [EB/OL]. [ 2025-08-21 ]. https://arxiv.org/abs/2103.00020 https://arxiv.org/abs/2103.00020 .
WILLIAMS P L , BEER R D . Nonnegative decomposition of multivariate information [EB/OL]. [ 2025-08-21 ]. https://arxiv.org/abs/1004.2515 https://arxiv.org/abs/1004.2515 .
Rieke F , Warland D , Van Steveninck R R , et al . Spikes: exploring the neural code [M]. USA : MIT press , 1999 .
0
Views
0
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621