Estimation method of actual heating heat index based on elastic network regression model

KANG Jingde; HUANG Jiasi; QIAO Lei; LI Jie; SUN Peng; HE Kai; LIU Shengguan; SHANG Haijun; WANG Yuze; SHI Yaohui; SONG Jiayi

doi:10.19666/j.rlfd.202307110

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

Estimation method of actual heating heat index based on elastic network regression model

更新时间：2025-09-28

- Estimation method of actual heating heat index based on elastic network regression model
- Thermal Power Generation Vol. 53, Issue 2, Pages: 114-123(2024)
- 作者机构：
  
  1. 西安热工研究院有限公司
  2. 华能山东发电有限公司
  3. 西安交通大学人居环境与建筑工程学院
- 作者简介：
- 基金信息：
- DOI：10.19666/j.rlfd.202307110
  CLC： TU995;TM621
- Published：2024
- 稿件说明：
移动端阅览
KANG Jingde, HUANG Jiasi, QIAO Lei, et al. Estimation method of actual heating heat index based on elastic network regression model[J]. Thermal power generation, 2024, 53(2): 114-123.
DOI：

KANG Jingde, HUANG Jiasi, QIAO Lei, et al. Estimation method of actual heating heat index based on elastic network regression model[J]. Thermal power generation, 2024, 53(2): 114-123. DOI： 10.19666/j.rlfd.202307110.

摘要

为满足热电联产企业估算区域热负荷的需求，提出一种使用弹性网络回归模型的估算方法。首先对实际采暖热指标的影响因素进行分析，确定模型的输入参数；然后以西安市123个小区2022—2023年采暖季的实际运行数据为基础建立估算模型，并证明该模型相较于Lasso回归和岭回归模型的拟合优度分别提高了3.88%和4.22%；最后从多角度选取西安市部分小区相关数据构成验证集对弹性网络回归模型进行验证。验证结果表明：弹性网络回归模型综合了Lasso回归和岭回归的优点，模型的均方根误差和拟合优度分别为1.150和0.953，相较于传统模型能在符合热负荷需求的同时降低4%的能源消耗。说明该方法能准确估算不同参数条件下的实际采暖热指标，可以满足热电联产企业的实际需求。

Abstract

In order to meet the demand of estimating regional heat load for cogeneration enterprises

an estimation method using elastic network regression model is proposed. Firstly

the influencing factors of the actual heating heat index are analyzed to determine the input parameters of the model. Then

based on the actual operation data of 123residential areas in Xi'an in the heating season from 2022 to 2023

the estimation model is established

and it is proved that the accuracy of the model is higher than that of Lasso regression and ridge regression models. Finally

part of the communities in Xi'an are selected to form a verification set to verify the elastic network regression model. The verification results show that

the elastic network regression model combines the advantages of Lasso regression and ridge regression

and has higher prediction accuracy than the conventional machine learning model.The MAE and goodness of fit of the model are 1.150 and 0.953

respectively

indicating that the method can accurately estimate the actual heating heat index with different parameters

and can meet the actual engineering needs of cogeneration enterprises.

关键词

Keywords

references

Views

143

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

STUDY ON ON-LINE MONITORING SYSTEM FOR COGENERATION UNITS IN SHANDONG PROVINCE

Effect of environmental temperature on cogeneration units and the countermeasures

Peaking capability and economic analysis for a 330MW cogeneration unit

Dynamic environmental assessment for natural gas cogeneration systems based on supply-demand coupling analysis

Application of low-grade energy heating technology in central heating by cogeneration

Related Author

ZHU Wei-yi21.Shandong Electric Power Research Institute

LIU Ji-dong2

SHANG Li2

SUN Wei1

PENG Xinfei School of Energy

LI Meibao

FU Li

FAN Xue

Related Institution

Shandong Electric Power Corporation

Shandong Electric Power Research Institute

College of Energy, Power and Mechanical Engineering, North China Electric Power University

School of Electric Power, South China University of Technology

Guangdong Power Grid Corporation Electric Power Science Research Institute

AI问答

⁰