一种基于XGBoost算法的月度负荷预测方法
|
摘要
为向大工业提供更为精确的月度负荷预测,提出将XGBoost(极端梯度上升)算法引入电网负荷预测,对负荷及相关影响因素指标进行异常识别填补、指标转换、独热编码等数据预处理工作;结合关联分析,对相关影响因素指标进行筛选;最后采用XGBoost算法进行月度负荷建模预测。结合实例,对比XGBoost与支持向量机、神经网络模型算法在大工业用户近几年历史月度负荷数据建模预测中的应用,发现XGBoost模型应用效果较佳,具有一定的实用性。
In order to provide more accurate monthly load forecasting for large industries, XGBoost(extreme gradient rise) algorithm is introduced into load forecasting of power grid, and the data preprocessing work such as anomaly identification, index conversion and unique heat coding is carried out; the related influencing factor indexes are screened by combining the correlation analysis; Finally, XGBoost algorithm is used for modelling and forecasting of monthly load. In an example, by comparing the application of XGBoost with that of support vector machine and neural network model algorithm in the past monthly load forecasting in the last years, it is found that XGBoost model has better application effect and practicability.
In order to provide more accurate monthly load forecasting for large industries, XGBoost(extreme gradient rise) algorithm is introduced into load forecasting of power grid, and the data preprocessing work such as anomaly identification, index conversion and unique heat coding is carried out; the related influencing factor indexes are screened by combining the correlation analysis; Finally, XGBoost algorithm is used for modelling and forecasting of monthly load. In an example, by comparing the application of XGBoost with that of support vector machine and neural network model algorithm in the past monthly load forecasting in the last years, it is found that XGBoost model has better application effect and practicability.
引文
[1]CHEN T,GUESTRAIN C.XGBoost:A Scalable Tree Boosting System[C]//ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,2016:785-794.
[2]李叶紫,王振友,周怡璐,等.基于贝叶斯最优化的Xg boost算法的改进及应用[J].广东工业大学学报,2018,35(1):23-28.
[3]基于Lasso和Xgboost的油价预测研究[J].工业技术经济,2018(7):31-37.
[4]WANG L,LI S Z.Tactical intention recognition of aerial target based on XGBoost decision tree[J].Journal of Measurement Science and Instrumentation,2018,9(2):148-152.
[5]张昊,纪宏超,张红宇.XGboost算法在电子商务商品推荐中的应用[J].智能处理与应用,2017(2):102-104.
[6]张昊,纪宏超,张红宇.XGboost在滚动轴承故障诊断中的应用[J].噪声与振动控制,2017,37(4):165-170.
[7]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(4):21-25.
[8]张宇航,邱才明,贺兴,等.一种基于LSTM神经网络的短期用电负荷预测方法[J].电力信息与通信技术,2017,15(9):19-25.
[9]王奔,冷北雪,张喜海,等.支持向量机在短期负荷预测中的应用概况[J].电力系统及其自动化学报,2011,23(4):115-121.
[10]杨镜非,谢宏,程浩忠.SVM与Fourier算法在电网短期负荷预测中的应用[J].继电器,2004,32(4):17-19.
[11]李广野,李伟,田小蕾,等.基于XGboost算法的短期电力负荷预报[J].智能电网,2017,7(4):274-285.
[12]叶淳铮,常鲜戎,顾为国.基于贝叶斯最优化的XGboost算法的改进及应用[J].广东工业大学学报,2018,35(1):41-45.
[13]机器学习方法在股指期货预测中的应用-研究基于BP神经网络、SVM和XGBoost的比较分析[J].数学的实践与认识,2018,48(8):297-307.
[14]叶淳铮,常鲜戎,顾为国.基于小波变换和支持向量机的电力系统短期负荷预测[J].电力系统保护与控制,2009,37(14):41-45.
[15]牛俊磊,程龙生.采用优化模型指标筛选的马田系统综合评价方法研究[J].数学的实践与认识,2015,45(17):1-12.
[2]李叶紫,王振友,周怡璐,等.基于贝叶斯最优化的Xg boost算法的改进及应用[J].广东工业大学学报,2018,35(1):23-28.
[3]基于Lasso和Xgboost的油价预测研究[J].工业技术经济,2018(7):31-37.
[4]WANG L,LI S Z.Tactical intention recognition of aerial target based on XGBoost decision tree[J].Journal of Measurement Science and Instrumentation,2018,9(2):148-152.
[5]张昊,纪宏超,张红宇.XGboost算法在电子商务商品推荐中的应用[J].智能处理与应用,2017(2):102-104.
[6]张昊,纪宏超,张红宇.XGboost在滚动轴承故障诊断中的应用[J].噪声与振动控制,2017,37(4):165-170.
[7]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(4):21-25.
[8]张宇航,邱才明,贺兴,等.一种基于LSTM神经网络的短期用电负荷预测方法[J].电力信息与通信技术,2017,15(9):19-25.
[9]王奔,冷北雪,张喜海,等.支持向量机在短期负荷预测中的应用概况[J].电力系统及其自动化学报,2011,23(4):115-121.
[10]杨镜非,谢宏,程浩忠.SVM与Fourier算法在电网短期负荷预测中的应用[J].继电器,2004,32(4):17-19.
[11]李广野,李伟,田小蕾,等.基于XGboost算法的短期电力负荷预报[J].智能电网,2017,7(4):274-285.
[12]叶淳铮,常鲜戎,顾为国.基于贝叶斯最优化的XGboost算法的改进及应用[J].广东工业大学学报,2018,35(1):41-45.
[13]机器学习方法在股指期货预测中的应用-研究基于BP神经网络、SVM和XGBoost的比较分析[J].数学的实践与认识,2018,48(8):297-307.
[14]叶淳铮,常鲜戎,顾为国.基于小波变换和支持向量机的电力系统短期负荷预测[J].电力系统保护与控制,2009,37(14):41-45.
[15]牛俊磊,程龙生.采用优化模型指标筛选的马田系统综合评价方法研究[J].数学的实践与认识,2015,45(17):1-12.