面向城市用电负荷预测的混合机器学习模型  

Urban Electricity Load Forecasting Based on Hybrid Deep Learning Model

作　　者：胡乙丹 张俊芳[1] HU Yidan;ZHANG Junfang(School of Automation,Nanjing University of Science&Technology,Nanjing Jiangsu 210018,China)

机构地区：[1]南京理工大学自动化学院,江苏南京210018

出　　处：《软件导刊》2023年第9期65-72,共8页Software Guide

摘　　要：城市用电负荷的精准预测对电力系统的运行和规划至关重要,可产生巨大的经济价值和社会效益。城市中长期用电需求预测不仅需要考虑长期经济趋势和季节周期因素,而且需要考虑诸多不确定性和非线性问题,而现有预测方法仅考虑了其中部分因素,因而无法实现精准预测。针对上述问题,提出一种面向城市用电负荷预测的混合机器学习(HML)模型。该模型首先对影响城市用电负荷的各因素进行特征选择,筛选出重要特征;其次利用指数平滑(ETS)捕捉用电负荷时间序列的季节分量和水平分量;然后利用长短期记忆(LSTM)网络发掘用电负荷时间序列的非线性趋势;最后利用集成学习实现各学习模块性能的有效聚合。实验选择中国两个城市的月度用电量作为标准数据集,实验结果表明,该HML模型在月度用电量预测精度方面优于其他同类模型。The accurate forecasting of urban electricity load is extremely important to the operation and planning of power system,which can produce great economic value and social benefits.The medium-and long-term urban electricity demand forecasting needs to consider not only the long-term economic trend and seasonal cycle factors,but also many uncertainties and non-linear issues.However,the existing forecasting methods only consider part of these factors,making they can not achieve accurate forecasting.To fill this gap,this paper proposes a hybrid ma-chine learning(HML)model for urban electricity load forecasting.Firstly,HML selects the important features that significantly affect the ur-ban electricity load demands;Secondly,exponential smoothing(ETS)is employed to capture the seasonal and horizontal components of elec-tricity load time series;Then,the long short term memory(LSTM)is used to discover the nonlinear trend of the time series of electricity load;Finally,ensemble learning is adopted to realize the effective aggregation of the performance of each learning module.In the experiments,the monthly electricity consumptions of two cities in China are adopted as the benchmark datasets.The results show that our HML model is superi-or to the latest existing models in terms of the forecasting accuracy of monthly electricity consumption.

关 键 词：深度学习 指数平滑 长短期记忆 用电负荷预测 递归神经网络 时间序列预测 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]