南京师大学报（自然科学版）2023，Vol.46Issue(4)：114-124,11.DOI:10.3969/j.issn.1001-4616.2023.04.015
基于特征选择和组合预测模型的负荷短期预测方法
Short-term Load Forecasting Method Based on Feature Selection and Combination Forecasting Model
摘要
Abstract
Improving the accuracy of short-term forecasting of bus load in a distribution network is crucial to its dispatch and operation.With the increasing number of weather-sensitive loads in the distribution network,the influence of load fluctuation caused by meteorological factors on forecasting accuracy also increases.Aiming at the problem of meteorological feature selection in traditional load forecasting modeling,an optimal meteorological feature selection process was proposed based on the maximum correlation,minimum redundancy,and maximum synergy of features.On this basis,based on different time dimensions of different characteristics,a short-term load combination forecasting model combining regression model and time series model is proposed.The model uses the regression model to fit the future date-time characteristics and meteorological characteristics and uses the convolutional neural network and bidirectional gated recurrent unit to construct a time series model to describe the time series characteristics of the historical load and meteorological time series and the cumulative effect of meteorological factors.Example analysis proves that the feature selection method has a lower forecast error than the traditional feature selection methods.Compared with the traditional regression and time-series model,the forecasting accuracy of combination forecasting model is improved significantly.关键词
特征选择/回归模型/时间序列模型/组合预测模型Key words
feature selection/regression model/time series model/combination forecasting model分类
信息技术与安全科学引用本文复制引用
陆嘉华,梅飞,杨赛,唐瑜,华昊辰..基于特征选择和组合预测模型的负荷短期预测方法[J].南京师大学报（自然科学版）,2023,46(4):114-124,11.基金项目
国家重点研发计划项目(2022YFE0140600)、江苏省重点研发计划项目(BE2020027). （2022YFE0140600）
