

浏览全部资源
扫码关注微信
1.阿里巴巴集团,浙江省杭州市 310099
2.中国南方电网电力调度控制中心,广东省广州市 510663
3.海南电网有限责任公司海南输变电检修分公司,海南省海口市 570100
Received:29 September 2022,
Revised:2023-04-11,
Published Online:16 June 2023,
Published:10 July 2023
移动端阅览
郑心仕,梁寿愚,苏晓等.基于贝叶斯方法与可解释机器学习的负荷特性分析与预测[J].电力系统自动化,2023,47(13):56-68.
ZHENG Xinshi,LIANG Shouyu,SU Xiao,et al.Characteristic Analysis and Load Forecasting Based on Bayesian Method and Interpretable Machine Learning[J].Automation of Electric Power Systems,2023,47(13):56-68.
郑心仕,梁寿愚,苏晓等.基于贝叶斯方法与可解释机器学习的负荷特性分析与预测[J].电力系统自动化,2023,47(13):56-68. DOI: 10.7500/AEPS20220929011.
ZHENG Xinshi,LIANG Shouyu,SU Xiao,et al.Characteristic Analysis and Load Forecasting Based on Bayesian Method and Interpretable Machine Learning[J].Automation of Electric Power Systems,2023,47(13):56-68. DOI: 10.7500/AEPS20220929011.
使用机器学习模型和方法进行短期负荷预测,虽能提升负荷预测的整体精度,但在极端天气、节假日等小样本预测场景中,对比基于专家经验的人工预测无明显优势。为充分结合预测业务人员的经验知识与机器学习的推理泛化能力,提出了一种基于贝叶斯时变系数(BTVC)与CatBoost模型的可解释负荷预测框架。首先,结合数据与专家知识,构建BTVC模型进行预测,获得各影响因子、趋势及周期因素的负荷分量。其次,将上述结果与常规特征进行组合,作为CatBoost回归模型的输入,进行最终预测。然后,使用事后模型解释框架(SHAP)进行归因分析,框架输出的定量关系可供负荷预测业务人员参考,使其开发出更有效的特征,进一步提高预测效果。最后,以某地区实际电网负荷数据为例,验证所提负荷预测与结果分析框架的有效性。
Using machine learning models and methods for short-term load forecasting can improve the overall accuracy of load forecasting
but in small sample forecasting scenarios
such as extreme weather conditions and holidays
there is no obvious advantage over manual forecasting based on expert experience. In order to fully combine the expert knowledge of forecasting operators with the reasoning generalization ability of machine learning
an interpretable load forecasting framework based on Bayesian time-varying coefficient (BTVC) and CatBoost model is proposed. First
combined with data and expert knowledge
BTVC model is built to forecast
and load components of various influencing factors
trends and seasonality factors are obtained. Secondly
combine the above results with conventional features as the input of CatBoost regression model for final forecasting. Then
Shapley additive explanation (SHAP) is used for attribution analysis. The quantitative relationship of the framework output can be used as a reference for load forecasting practitioners to create more effective features to further improve the forecasting results. Finally
the proposed load forecasting and result analysis framework are validated by using real load data in power grid of a region as an example.
康重庆 , 夏清 , 刘梅 . 电力系统负荷预测 [M]. 2版 . 北京 : 中国电力出版社 , 2017 .
KANG Chongqing , XIA Qing , LIU Mei . Power system load forecasting [M]. 2nd ed . Beijing : China Electric Power Press , 2017 .
于军琪 , 聂己开 , 赵安军 , 等 . 基于特征挖掘的ARIMA-GRU短期电力负荷预测 [J]. 电力系统及其自动化学报 , 2022 , 34 ( 3 ): 91 - 99 .
YU Junqi , NIE Jikai , ZHAO Anjun , et al . ARIMA-GRU short-term power load forecasting based on feature mining [J]. Proceedings of the CSU-EPSA , 2022 , 34 ( 3 ): 91 - 99 .
刘涅煊 , 杨学良 , 陶晓峰 , 等 . 基于改进Prophet算法的短期日负荷预测方法研究 [J]. 电力需求侧管理 , 2022 , 24 ( 5 ): 58 - 63 .
LIU Niexuan , YANG Xueliang , TAO Xiaofeng , et al . Research on short-term daily load forecasting method based on improved Prophet algorithm [J]. Power Demand Side Management , 2022 , 24 ( 5 ): 58 - 63 .
TRIEBE O , HEWAMALAGE H , PILYUGINA P , et al . NeuralProphet: explainable forecasting at scale [EB/OL]. [ 2021-11-29 ]. https://arxiv.org/abs/2111.15397 https://arxiv.org/abs/2111.15397 .
李焱 , 贾雅君 , 李磊 , 等 . 基于随机森林算法的短期电力负荷预测 [J]. 电力系统保护与控制 , 2020 , 48 ( 21 ): 117 - 124 .
LI Yan , JIA Yajun , LI Lei , et al . Short term power load forecasting based on a stochastic forest algorithm [J]. Power System Protection and Control , 2020 , 48 ( 21 ): 117 - 124 .
陈纬楠 , 胡志坚 , 岳菁鹏 , 等 . 基于长短期记忆网络和LightGBM组合模型的短期负荷预测 [J]. 电力系统自动化 , 2021 , 45 ( 4 ): 91 - 97 .
CHEN Weinan , HU Zhijian , YUE Jingpeng , et al . Short-term load prediction based on combined model of long short-term memory network and light gradient boosting machine [J]. Automation of Electric Power Systems , 2021 , 45 ( 4 ): 91 - 97 .
庄家懿 , 杨国华 , 郑豪丰 , 等 . 基于多模型融合的CNN-LSTM-XGBoost短期电力负荷预测方法 [J]. 中国电力 , 2021 , 54 ( 5 ): 46 - 55 .
ZHUANG Jiayi , YANG Guohua , ZHENG Haofeng , et al . Short-term load forecasting method based on multi-model fusion using CNN-LSTM-XGBoost framework [J]. Electric Power , 2021 , 54 ( 5 ): 46 - 55 .
陆继翔 , 张琪培 , 杨志宏 , 等 . 基于CNN-LSTM混合神经网络模型的短期负荷预测方法 [J]. 电力系统自动化 , 2019 , 43 ( 8 ): 131 - 137 .
LU Jixiang , ZHANG Qipei , YANG Zhihong , et al . Short-term load forecasting method based on CNN-LSTM hybrid neural network model [J]. Automation of Electric Power Systems , 2019 , 43 ( 8 ): 131 - 137 .
赵兵 , 王增平 , 纪维佳 , 等 . 基于注意力机制的CNN-GRU短期电力负荷预测方法 [J]. 电网技术 , 2019 , 43 ( 12 ): 4370 - 4376 .
ZHAO Bing , WANG Zengping , JI Weijia , et al . A short-term power load forecasting method based on attention mechanism of CNN-GRU [J]. Power System Technology , 2019 , 43 ( 12 ): 4370 - 4376 .
杨国华 , 郑豪丰 , 张鸿皓 , 等 . 基于Holt-Winters指数平滑和时间卷积网络的短期负荷预测 [J]. 电力系统自动化 , 2022 , 46 ( 6 ): 73 - 82 .
YANG Guohua , ZHENG Haofeng , ZHANG Honghao , et al . Short-term load forecasting based on Holt-Winters exponential smoothing and temporal convolutional network [J]. Automation of Electric Power Systems , 2022 , 46 ( 6 ): 73 - 82 .
ELSAYED S , THYSSENS D , RASHED A , et al . Do we really need deep learning models for time series forecasting? [EB/OL]. [ 2021-01-06 ]. https://arxiv.org/abs/2101.02118 https://arxiv.org/abs/2101.02118 .
GRINSZTAJN L , OYALLON E , VAROQUAUX G . Why do tree-based models still outperform deep learning on tabular data? [EB/OL]. [ 2022-07-18 ]. https://arxiv.org/abs/2207.08815 https://arxiv.org/abs/2207.08815 .
NG E , WANG Z S , DAI A . Bayesian time varying coefficient model with applications to marketing mix modeling [EB/OL]. [ 2021-06-07 ]. https://arxiv.org/abs/2106.03322 https://arxiv.org/abs/2106.03322 .
GELMAN A , CARLIN J B , STERN H S , et al . Bayesian data analysis [M]. Boca Raton, USA : CRC Press , 2013 .
HASTIE T , TIBSHIRANI R . Generalized additive models: Vol . 43 [M]. Boca Raton, USA : CRC Press , 1990 .
WU C , CHIANG C . Kernel smoothing on varying coefficient models with longitudinal dependent variable [J]. Statistica Sinica , 2000 , 10 ( 2 ): 433 - 456 .
王雁凌 , 吴梦凯 , 周子青 , 等 . 基于改进灰色关联度的电力负荷影响因素量化分析模型 [J]. 电网技术 , 2017 , 41 ( 6 ): 1772 - 1778 .
WANG Yanling , WU Mengkai , ZHOU Ziqing , et al . Quantitative analysis model of power load influencing factors based on improved grey relational degree [J]. Power System Technology , 2017 , 41 ( 6 ): 1772 - 1778 .
康田园 , 尹淑萍 , 王现法 , 等 . 大型城市电网负荷特性及其影响因素分析 [J]. 电测与仪表 , 2016 , 53 ( 6 ): 51 - 56 .
KANG Tianyuan , YIN Shuping , WANG Xianfa , et al . Load characteristics of large city power gridand analysis on its influencing factors [J]. Electrical Measurement & Instrumentation , 2016 , 53 ( 6 ): 51 - 56 .
马瑞 , 周谢 , 彭舟 , 等 . 考虑气温因素的负荷特性统计指标关联特征数据挖掘 [J]. 中国电机工程学报 , 2015 , 35 ( 1 ): 43 - 51 .
MA Rui , ZHOU Xie , PENG Zhou , et al . Data mining on correlation feature of load characteristics statistical indexes considering temperature [J]. Proceedings of the CSEE , 2015 , 35 ( 1 ): 43 - 51 .
RIBEIRO M T , SINGH S , GUESTRIN C . “why should I trust You?”: explaining the predictions of any classifier [C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining , August 13-17 , 2016 , San Francisco, USA : 1135 - 1144 .
LUNDBERG S , LEE S I . A unified approach to interpreting model predictions [EB/OL]. [ 2017-05-22 ]. https://arxiv.org/abs/1705.07874 https://arxiv.org/abs/1705.07874 .
YOUNG H P . Monotonic solutions of cooperative games [J]. International Journal of Game Theory , 1985 , 14 ( 2 ): 65 - 72 .
PROKHORENKOVA L , GUSEV G , VOROBEV A , et al . CatBoost: unbiased boosting with categorical features [EB/OL]. [ 2017-06-28 ]. https://arxiv.org/abs/1706.09516 https://arxiv.org/abs/1706.09516 .
HOFFMAN M , BLEI D M , WANG C , et al . Stochastic variational inference [EB/OL]. [ 2012-06-29 ]. https://arxiv.org/abs/1206.7051 https://arxiv.org/abs/1206.7051 .
Wolpert D H . Stacked generalization [M]. Boston, USA : Springer , 2017 : 6 - 10 .
朱江行 , 邹晓松 , 熊炜 , 等 . 基于Prophet与XGBoost混合模型的短期负荷预测 [J]. 现代电力 , 2021 , 38 ( 3 ): 325 - 331 .
ZHU Jianghang , ZOU Xiaosong , XIONG Wei , et al . Short-term power load forecasting based on Prophet and XGBoost mixed model [J]. Modern Electric Power , 2021 , 38 ( 3 ): 325 - 331 .
SHAPLEY L. A value for n-person games . Contributions to the theory of games II ( 1953) 307 - 317 [M]// HAROLD W K. Classics in Game Theory. Princeton, USA : Princeton University Press , 1997 : 69 - 79 .
陈星莺 , 郁清云 , 谢俊 , 等 . 基于合作博弈论的电能替代效益分摊方法 [J]. 电力自动化设备 , 2019 , 39 ( 3 ): 30 - 35 .
CHEN Xingying , YU Qingyun , XIE Jun , et al . Benefit allocation method for electric energy substitution based on cooperative game theory [J]. Electric Power Automation Equipment , 2019 , 39 ( 3 ): 30 - 35 .
JIANG Y Q , GAO T L , DAI Y X , et al . Very short-term residential load forecasting based on deep-autoformer [J]. Applied Energy , 2022 , 328 : 120120 .
0
Views
0
下载量
6
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621