针对电力系统短期负荷预测的问题,提出计及区域时空负荷联合影响的集成学习负荷预测模型。首先,提出一种负荷区时空联合的采样方案,使用其他负荷区近期负荷预测当前负荷区负荷,从而更多地利用强时效数据;其次,构建基于极限梯度提升等机器学习和神经网络模型的基学习器,并结合交叉验证用改进贝叶斯算法分散优化模型超参数,尽量提高各自的预测性能;再次,基于深度学习构建元学习器,实现Stacking集成学习,使之结合各基学习器的学习结果给出最终预测值;最后,在南方某负荷数据集上进行算例验证,并与常用的采样方法进行对比,验证了所提集成学习模型及采样特征方案的可行性和优越性。
Abstract
Addressing the problem of short-term load forecasting difficulty in power systems, this paper proposes an integrated learning load forecasting model that considers the spatio-temporal joint influence of load areas. Firstly, a spatiotemporally joint sampling scheme for load areas is proposed, using recent load data from other load areas to predict the load in the current load area, thereby making more use of highly time-sensitive data. Secondly, base learners are constructed based on machine learning and neural network models such as Extreme Gradient Boosting （XGBoost）. Combined with cross-validation, an improved Bayesian algorithm is used to distributedly optimize model hyperparameters, aiming to maximize their respective prediction performance. Thirdly, a meta-learner is built based on deep learning to implement Stacking ensemble learning, enabling it to combine the learning results of each base learner to output the final predicted value. Finally, case study validation is performed using a load dataset from southern China, and comparisons are made with commonly used sampling methods, verifying the feasibility and superiority of the proposed integrated learning model and sampling feature scheme.
关键词
电力负荷 /
预测 /
采样方法 /
贝叶斯优化 /
Stacking集成学习 /
神经网络
Key words
electrical loads /
forecasting /
sampling method /
Bayesian optimization /
Stacking ensemble learning /
neural networks
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 马恒瑞, 袁傲添, 王波, 等. 基于深度学习的负荷预测研究综述与展望[J]. 高电压技术, 2025, 51(3): 1233-1250.
Ma H R, Yuan A T, Wang B, et al.Review and prospect of load forecasting based on deep learning[J]. High Voltage Engineering, 2025, 51(3): 1233-1250.
[2] 曾鸣, 张徐东, 田廓, 等. 低碳电力市场设计与政策分析[J]. 电力系统自动化, 2011, 35(24): 7-11.
Zeng M, Zhang X D, Tian K, et al.Low carbon electricity market design and policy analysis[J]. Automation of Electric Power Systems, 2011, 35(24): 7-11.
[3] Yazici I, Beyca O F, Delen D.Deep-learning-based short-term electricity load forecasting: a real case application[J]. Engineering Applications of Artificial Intelligence, 2022, 109: 104645.
[4] 赵紫昱, 陈渊睿, 陈霆威, 等. 基于时空图注意力网络的超短期区域负荷预测[J]. 电力系统自动化, 2024, 48(12): 147-155.
Zhao Z Y, Chen Y R, Chen T W, et al.Ultra-short-term regional load forecasting based on spatio-temporal graph attention network[J]. Automation of Electric Power Systems, 2024, 48(12): 147-155.
[5] Huy P C, Minh N Q, Tien N D, et al.Short-term electricity load forecasting based on temporal fusion transformer model[J]. IEEE Access, 2022, 10: 106296-106304.
[6] 罗琦, 杨俊华, 黄逸, 等. 基于变分模式分解和向量自回归模型的波浪发电系统输出功率预测[J]. 太阳能学报, 2023, 44(3): 291-297.
Luo Q, Yang J H, Huang Y, et al.Output power prediction of wave power system based on variational model decomposition and vector autoregressive model[J]. Acta Energiae Solaris Sinica, 2023, 44(3): 291-297.
[7] Haque A, Rahman S.Short-term electrical load forecasting through heuristic configuration of regularized deep neural network[J]. Applied Soft Computing, 2022, 122: 108877.
[8] 薛东, 段立强, 高统彤, 等. 考虑多重特征与不确定性度量的综合能源系统负荷预测研究[J]. 太阳能学报, 2024, 45(7): 379-388.
Xue D, Duan L Q, Gao T T, et al.Study of integrated energy system load forecasting considering multiple characteristics and uncertainty measures[J]. Acta Energiae Solaris Sinica, 2024, 45(7): 379-388.
[9] Mounir N, Ouadi H, Jrhilifa I.Short-term electric load forecasting using an EMD-BI-LSTM approach for smart grid energy management system[J]. Energy and Buildings, 2023, 288: 113022.
[10] 杨宜龙, 范帅, 蔡思烨, 等. 内嵌调节目标的分布式能源调节能力分层分类聚合方法[J]. 电力系统自动化, 2025, 49(9): 84-95.
Yang Y L, Fan S, Cai S Y, et al.Hierarchical and classified aggregation method with embedded regulation targets for regulation capability of distributed energy resources[J]. Automation of Electric Power Systems, 2025, 49(9): 84-95.
[11] 杨海柱, 田馥铭, 张鹏, 等. 基于CEEMD-FE和AOA-LSSVM的短期电力负荷预测[J]. 电力系统保护与控制, 2022, 50(13): 126-133.
Yang H Z, Tian F M, Zhang P, et al.Short-term load forecasting based on CEEMD-FE-AOA-LSSVM[J]. Power System Protection and Control, 2022, 50(13): 126-133.
[12] 叶林, 路朋, 赵永宁, 等. 含风电电力系统有功功率模型预测控制方法综述[J]. 中国电机工程学报, 2021, 41(18): 6181-6197.
Ye L, Lu P, Zhao Y N, et al.Review of model predictive control for power system with large-scale wind power grid-connected[J]. Proceedings of the CSEE, 2021, 41(18): 6181-6197.
[13] 孙超, 吕奇, 朱思曈, 等. 基于双层XGBoost算法考虑多特征影响的超短期电力负荷预测[J]. 高电压技术, 2021, 47(8): 2885-2895.
Sun C, Lü Q, Zhu S T, et al.Ultra-short-term power load forecasting based on two-layer XGBoost algorithm considering the influence of multiple features[J]. High Voltage Engineering, 2021, 47(8): 2885-2895.
[14] Yang Y, Tao Z H, Qian C, et al.A hybrid robust system considering outliers for electric load series forecasting[J]. Applied Intelligence, 2022, 52(2): 1630-1652.
[15] Nikodinoska D, Käso M, Müsgens F.Solar and wind power generation forecasts using elastic net in time-varying forecast combinations[J]. Applied Energy, 2022, 306: 117983.
[16] Yang W W, Shi J, Li S J, et al.A combined deep learning load forecasting model of single household resident user considering multi-time scale electricity consumption behavior[J]. Applied Energy, 2022, 307: 118197.
[17] 刘荣, 方鸽飞. 改进Elman神经网络的综合气象短期负荷预测[J]. 电力系统保护与控制, 2012, 40(22): 113-117.
Liu R, Fang G F.Short-term load forecasting with comprehensive weather factors based on improved Elman neural network[J]. Power System Protection and Control, 2012, 40(22): 113-117.
[18] Niu D X, Yu M, Sun L J, et al.Short-term multi-energy load forecasting for integrated energy systems based on CNN-BiGRU optimized by attention mechanism[J]. Applied Energy, 2022, 313: 118801.
[19] Javed U, Ijaz K, Jawad M, et al.A novel short receptive field based dilated causal convolutional network integrated with Bidirectional LSTM for short-term load forecasting[J]. Expert Systems with Applications, 2022, 205: 117689.
[20] Lin J, Ma J, Zhu J G, et al.Short-term load forecasting based on LSTM networks considering attention mechanism[J]. International Journal of Electrical Power & Energy Systems, 2022, 137: 107818.
[21] Haris M, Hasan M N, Qin S Y.Early and robust remaining useful life prediction of supercapacitors using BOHB optimized Deep Belief Network[J]. Applied Energy, 2021, 286: 116541.
[22] 周泽楷, 侯宏娟, 孙莉, 等. 基于CNN和BiLSTM神经网络模型的太阳能供暖负荷预测研究[J]. 太阳能学报, 2024, 45(10): 415-422.
Zhou Z K, Hou H J, Sun L, et al.Research on solar heating load forecasting based on CNN and BiLSTM neural network model[J]. Acta Energiae Solaris Sinica, 2024, 45(10): 415-422.
PDF(2090 KB)
