基于Prophet算法的配电网线路峰值负荷预测Peak Load Forecasting of Distribution Network Lines Based on Prophet Algorithm
李衡,朱理,郑洁,刘海琼
LI Heng,ZHU Li,ZHENG Jie,LIU Haiqiong
摘要(Abstract):
对配电网线路进行负荷峰值预测,准确预测将出现重过载的线路,能为配电网制定供电计划提供重要参考。分析配电网线路历史负荷受节假日、季节影响的变化规律,提出基于Prophet的配电网线路峰值负荷预测方法,对每条线路单独建立Prophet模型,模型以历史日峰值负荷数据为输入数据,且通过自适调参方法对模型的变点增长率及变点个数参数进行调优,最后对实际数据进行算例分析,验证了该方法可准确实现配电网线路峰值负荷预测。
The peak load prediction of distribution network lines and the accurate prediction of impending overload lines can provide an important reference for the formulation of the power supply plan of distribution networks. This paper analyzes the variation law of historical data of distribution network lines being subject to holidays and seasons,puts forward the distribution network line peak load forecasting method based on Prophet,and establishes a Prophet model for each of the lines. The model takes the historical daily peak load data as the input data and optimizes its change point growth rate and change point number through the adaptive parameter adjustment method. Finally,an example analysis is carried out on the actual data to verify that the method can accurately fulfill peak load forecasting of distribution network lines.
关键词(KeyWords):
负荷预测;Prophet;电力峰值负荷;配电网
load forecasting;Prophet;electric peak load;distribution network
基金项目(Foundation): 国网浙江省电力有限公司科技项目(5211HZ19014P)
作者(Author):
李衡,朱理,郑洁,刘海琼
LI Heng,ZHU Li,ZHENG Jie,LIU Haiqiong
DOI: 10.19585/j.zjdl.202203003
参考文献(References):
- [1]张素香,赵丙镇,王风雨,等.海量数据下的电力负荷短期预测[J].中国电机工程学报,2015,35(1):37-42.
- [2]姜建,刘海琼,李衡,等.基于XGBoost的配电网线路峰值负荷预测方法[J].电力系统保护与控制,2021,49(16):119-127.
- [3]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.
- [4]RENDON-SANCHEZ J F,DE MENEZES L M.Structural combination of seasonal exponential smoothing forecasts applied to load forecasting[J].European Journal of Operational Research,2019,275(3):916-924.
- [5]ZHU X,SHEN M.Based on the ARIMA model with grey theory for short term load forecasting model[C]//International Conference on Systems and Informa-tics.Yan Tai:IEEE,2012:564-567.
- [6]李国庆,刘钊,金国彬,等.基于随机分布式嵌入框架及BP神经网络的超短期电力负荷预测[J].电网技术,2020,44(2):437-445.
- [7]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.
- [8]吴潇雨,和敬涵,张沛,等.基于灰色投影改进随机森林算法的电力系统短期负荷预测[J].电力系统自动化,2015,39(12):50-55.
- [9]陈振宇,刘金波,李晨,等.基于LSTM与XGBoost组合模型的超短期电力负荷预测[J].电网技术,2020,44(2):614-620.
- [10]杨修德,王金梅,张丽娜.XGBoost在超短期负荷预测中的应用[J].电气传动自动化,2017,39(4):21-25
- [11]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.
- [12]彭湃,刘敏.基于Prophet-LSTM组合模型的短期负荷预测方法[J/OL].电力系统及其自动化学报:1-9[2021-07-28].https://doi.org/10.19635/j.cnki.csuepsa.000705.
- [13]吴文培.基于Prophet模型优化及在区域用电量预测中的应用[D].河南:河南大学,2020.
- [14]刘升.基于时间序列的台区配电负荷峰值预测[J].电力科学与工程,2018,34(7):56-60.
- [15]李玉志,刘晓亮,邢方方,等.基于Bi-LSTM和特征关联性分析的日尖峰负荷预测[J].电网技术,2021,45(7):2719-2730.
- [16]刘翊枫,周辉,刘昕,等.基于气象成分分解的夏季短期负荷预测[J].电测与仪表,2019,56(21):129-135.
- [17]邢书豪,高广玲,张智晟.基于双层随机森林算法的短期负荷预测模型[J].广东电力,2019,32(9):160-166.
- [18]李富鹏,沈秋英,王森,等.基于大数据和多因素组合分析的单元制配电网精细化负荷预测[J].智慧电力,2020,48(1):55-62.
- [19]蒋敏,顾东健,孔军,等.基于在线序列极限支持向量回归的短期负荷预测模型[J].电网技术,2018,42(7):2240-2247.
- [20]罗凡,余向前,王林信,等.基于聚类与自适应划分的短期负荷预测[J].电力电容器与无功补偿,2021,42(6):184-189.
- [21]晏神,甘景福,田新成,等.基于方差比较的负荷曲线形态聚类研究[J].电器与能效管理技术,2021(8):24-30.