含分布式储能系统的主动配电网负荷预测模型构建

杨韵; 程永峰; 谢祥中; 涂炼; 廖晔

doi:10.19799/j.cnki.2095-4239.2026.0189

您当前的位置：

首页 >

文章列表页 >

含分布式储能系统的主动配电网负荷预测模型构建

储能系统与工程 | 更新时间：2026-04-29

- 含分布式储能系统的主动配电网负荷预测模型构建
- Construction of an active distribution network load forecasting model with distributed energy storage system
- 储能科学与技术 2026年15卷第4期页码：1302-1311
- 作者机构：
  
  1.广东电网有限责任公司电力调度控制中心，广东广州 510220
  2.北京清能互联科技有限公司，北京 100084
- 作者简介：
  
  杨韵（1989—），女，高级工程师，硕士，研究方向为电力负荷预测、电力市场分析，E-mail：768512457@qq.com；
  廖晔，工程师，研究方向为电力负荷预测、新能源调度运行，E-mail：407533191@qq.com。
- 基金信息：
  
  中国南方电网有限责任公司科技项目（036000KK52210065(GDKJXM20210096)
- DOI：10.19799/j.cnki.2095-4239.2026.0189
  中图分类号： TM 615
- 收稿：2026-03-05，
  
  修回：2026-03-19，
  
  纸质出版：2026-04-28
- 稿件说明：
移动端阅览
杨韵, 程永峰, 谢祥中, 等. 含分布式储能系统的主动配电网负荷预测模型构建[J]. 储能科学与技术, 2026, 15(4): 1302-1311.

YANG Yun, CHENG Yongfeng, XIE Xiangzhong, et al. Construction of an active distribution network load forecasting model with distributed energy storage system[J]. Energy Storage Science and Technology, 2026, 15(4): 1302-1311.
杨韵, 程永峰, 谢祥中, 等. 含分布式储能系统的主动配电网负荷预测模型构建[J]. 储能科学与技术, 2026, 15(4): 1302-1311. DOI： 10.19799/j.cnki.2095-4239.2026.0189.

YANG Yun, CHENG Yongfeng, XIE Xiangzhong, et al. Construction of an active distribution network load forecasting model with distributed energy storage system[J]. Energy Storage Science and Technology, 2026, 15(4): 1302-1311. DOI： 10.19799/j.cnki.2095-4239.2026.0189.

摘要

针对含分布式储能系统的主动配电网短期负荷预测中储能运行扰动显著、节点电压波动增强、负荷演化非平稳性突出的特点，本研究围绕储能接入条件下负荷预测精度与物理一致性难以兼顾的问题，构建了一种融合电压波动感知与拓扑约束的短期负荷预测模型。建模过程中，首先面向工程场景中储能充放电数据缺失、记录不连续等问题，结合节点功率平衡关系与时间连续性约束，对缺失时段储能功率进行重构，以提高关键输入变量的完整性与可用性；随后，针对储能调节引起的局部电压变化对负荷响应的影响，构建节点电压波动指标，并对电压特征进行修正，将历史负荷、重构后的储能功率、节点电压及其波动特征进行统一时间对齐和多变量融合；在此基础上，建立LSTM-PatchTST联合预测框架，由LSTM提取局部时序动态特征，PatchTST刻画长时段依赖关系，并通过残差修正与结果融合增强模型在复杂工况下的稳定性；同时，将储能接入线路状态和线路载流限制以拓扑约束损失项的形式嵌入训练过程，以提升预测结果对实际配电网运行边界的适配能力。以某含分布式储能系统的主动配电网半年运行数据为对象开展仿真分析，在15 min的时间尺度下构建训练集、验证集和测试集。结果表明，所建模型能够较准确跟踪储能调节活跃时段的负荷变化趋势，在负荷突升和回落区间均表现出较好的响应能力，综合平均绝对百分比误差为2.73%，较两种对比方法分别下降23.53%和32.43%。实验结果表明，通过协同引入储能功率重构、电压波动感知和拓扑约束训练，可有效增强模型对源网荷储耦合运行特征的表征能力，提高主动配电网短期负荷预测的精度、稳定性与工程适用性，并可为储能调度优化和配电网智能运行提供更可靠的数据支撑。

Abstract

Short-term load forecasting (STLF) in active distribution networks (ADNs) with distributed energy storage systems (DESS) is complicated by operational disturbances

pronounced voltage fluctuations

and highly non-stationary load patterns. To improve forecasting accuracy while ensuring physical consistency under DESS integration

a short-term load forecasting model integrating voltage fluctuation awareness and topological constraints is proposed. First

to handle missing or discontinuous DESS data in practical engineering scenarios

a power reconstruction method is developed based on nodal power balance and temporal continuity constraints

thereby improving the completeness of key input variables. Second

to capture the influence of DESS-induced local voltage variations on load response

a nodal voltage fluctuation index is constructed to refine voltage features

followed by the fusion of historical load

reconstructed DESS power

and time-aligned voltage characteristics. A hybrid LSTM-PatchTST framework is then established

in which LSTM captures local temporal dynamics and PatchTST characterizes long-term dependencies

while residual correction and ensemble learning further improve model stability. In addition

DESS capacity boundaries and line flow limits are incorporated into the training process as topological constraint loss terms to enhance model adaptability to the physical operating limits of the grid. Simulation results based on half-year operational data from a real ADN demonstrate that the proposed model accurately tracks load trends during active DESS regulation. At a 15-minute resolution

the model achieves a mean absolute percentage error (MAPE) of 2.73%

corresponding to a reduction of 23.53% and 32.43% compared with two benchmark methods. The results indicate that the synergistic integration of power reconstruction

voltage awareness

and topological constraints significantly enhances the ability of the model to represent source-network-load-storage coupling and provides reliable data support for DESS dispatch and smart grid operation.

关键词

Keywords

references

朱海南, 李丰硕, 孙华忠, 等. 基于改进AlexNet-GRU深度学习网络的配电网短期负荷预测方法[J]. 电力电容器与无功补偿, 2023, 44(4): 48-54, 61. DOI:10.14044/j.1674-1757.pcrpc.2023.04.008.

ZHU H N, LI F S, SUN H Z, et al. Short-term load prediction method of distribution network based on improved AlexNet-GRU deep learning network[J]. Power Capacitor & Reactive Power Compensation, 2023, 44(4): 48-54, 61. DOI:10.14044/j.1674-1757.pcrpc.2023.04.008.

侯磊, 孔玉辉, 王赛豪, 等. 综合能源系统主动配电网常规负荷预测模型[J]. 信息技术, 2021(4): 46-51.

HOU L, KONG Y H, WANG S H, et al. Conventional load forecasting model for active distribution network of integrated energy system[J]. Information Technology, 2021(4): 46-51.

MISHRA K, YADAV A, LONDHE N D. Load demand forecasting of chhattisgarh state for demand management system with optimal feature selection using XGBOOST approach[J]. Electric Power Systems Research, 2026, 253: 112567. DOI:10.1016/j.epsr.2025.112567.

于越, 葛磊蛟, 金朝阳, 等. 考虑天气特征与多变量相关性的配电网短期负荷预测[J]. 电力系统保护与控制, 2024, 52(6): 131-141. DOI:10.19783/j.cnki.pspc.231329.

YU Y, GE L J, JIN Z Y, et al. Short-term load prediction method of distribution networks considering weather features and multivariate correlations[J]. Power System Protection and Control, 2024, 52(6): 131-141. DOI:10.19783/j.cnki.pspc.231329.

张怀天,贾东梨,王帅,等.基于Transformer-集成学习的配电网短期负荷预测方法[J/OL].中国电力,1-13[2026-02-13].https://link.cnki.net/urlid/11.3265.TM.20260128.1616.004.

JIANG H, DONG Y W, DONG Y, et al. Power load forecasting based on spatial-temporal fusion graph convolution network[J]. Technological Forecasting and Social Change, 2024, 204: 123435. DOI:10.1016/j.techfore.2024.123435.

吴军英, 路欣, 刘宏, 等. 基于Spearman-GCN-GRU模型的超短期多区域电力负荷预测[J]. 中国电力, 2024, 57(6): 131-140. DOI:10.11930/j.issn.1004-9649.202306094.

WU J Y, LU X, LIU H, et al. Ultra-short-term multi-region power load forecasting based on Spearman-GCN-GRU model[J]. Electric Power, 2024, 57(6): 131-140. DOI:10.11930/j.issn.1004-9649.202306094.

张鹏飞, 胡博, 何金松, 等. 基于时空图卷积网络的短期空间负荷预测方法[J]. 电力系统自动化, 2023, 47(13): 78-85. DOI:10.7500/AEPS20220929019.

ZHANG P F, HU B, HE J S, et al. Short-term spatial load forecasting method based on spatio-temporal graph convolutional network[J]. Automation of Electric Power Systems, 2023, 47(13): 78-85. DOI:10.7500/AEPS20220929019.

冯桂玲, 郑鹭洲, 蒋宏烨, 等. 基于云计算和改进极限学习机的电网负荷预测[J]. 科学技术与工程, 2021, 21(22): 9411-9417. DOI:10.3969/j.issn.1671-1815.2021.22.033.

FENG G L, ZHENG L Z, JIANG H Y, et al. A power grid load forecasting model combining cloud computing and improved extreme learning machine under massive data acquisition[J]. Science Technology and Engineering, 2021, 21(22): 9411-9417. DOI:10.3969/j.issn.1671-1815.2021.22.033.

LI J Z, ZHAO Z W, JIN T. Short-term load forecasting in smart grids: A CGAN-self data reconstruction and BiTCN-BiGRU-self attention model with demand response optimization[J]. Expert Systems with Applications, 2025, 292: 128553. DOI:10.1016/j.eswa.2025.128553.

黄冬梅, 张宁宁, 胡安铎, 等. 基于双层XGBoost和数据增强的空间负荷预测方法[J]. 电力工程技术, 2023, 42(1): 201-208. DOI:10.12158/j.2096-3203.2023.01.024.

HUANG D M, ZHANG N N, HU A D, et al. Spatial load forecasting method based on double-layer XGBoost and data enhancement[J]. Jiangsu Electrical Engineering, 2023, 42(1): 201-208. DOI:10.12158/j.2096-3203.2023.01.024.

林嘉伟, 王志新, 张永. 独立直流微电网中考虑不同容量的分布式储能系统能量控制策略[J]. 电力自动化设备, 2020, 40(10): 139-146. DOI:10.16081/j.epae.202009025.

LIN J W, WANG Z X, ZHANG Y. Energy control strategy of distributed energy storage system considering different capacities in isolated DC microgrid[J]. Electric Power Automation Equipment, 2020, 40(10): 139-146. DOI:10.16081/j.epae.202009025.

王一飞, 董新伟, 杨飞, 等. 基于配电网电压质量的分布式储能系统优化配置研究[J]. 热力发电, 2020, 49(8): 126-133. DOI:10.19666/j.rlfd.202003082.

WANG Y F, DONG X W, YANG F, et al. Optimal configuration of distributed energy storage system based on voltage quality of distribution network[J]. Thermal Power Generation, 2020, 49(8): 126-133. DOI:10.19666/j.rlfd.202003082.

孟祥福, 石皓源. 基于Transformer模型的时序数据预测方法综述[J]. 计算机科学与探索, 2025, 19(1): 45-64. DOI:10.3778/j.issn.1673-9418.2403070.

MENG X F, SHI H Y. Survey of Transformer-based model for time series forecasting[J]. Journal of Frontiers of Computer Science & Technology, 2025, 19(1): 45-64. DOI:10.3778/j.issn.1673-9418.2403070.

王子乐, 王子谋, 蔡莹, 等. 基于长短期记忆神经网络组合算法的短期电力负荷预测[J]. 现代电力, 2023, 40(2): 201-209.

WANG Z Y, WANG Z M, CAI Y, et al. Short-term load forecasting based on long short-term memory network combination algorithm[J]. Modern Electric Power, 2023, 40(2): 201-209.

朱晓荣, 马英乔, 赵澄颢. 基于模型预测控制算法的多风储直流微电网分布式电压二次控制策略[J]. 电力自动化设备, 2021, 41(10): 184-191. DOI:10.16081/j.epae.202110038.

ZHU X R, MA Y Q, ZHAO C H. Distributed voltage secondary control strategy of multi wind-storage DC microgrid based on model predictive control algorithm[J]. Electric Power Automation Equipment, 2021, 41(10): 184-191. DOI:10.16081/j.epae.202110038.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

能源互联基础上分布式储能系统的应用及经济效益探讨

基于贪婪算法的分布式储能系统容量优化配置方法