Load forecasting of district heating system based on Informer

计算机科学 采暖系统 环境科学 工程类 机械工程
作者
Mingju Gong,Yin Zhao,Jiawang Sun,Cuitian Han,Guannan Sun,Bo Yan
出处
期刊:Energy [Elsevier BV]
卷期号:253: 124179-124179 被引量:118
标识
DOI:10.1016/j.energy.2022.124179
摘要

Accurate load forecasting of district heating systems (DHSs) is an essential guide to guaranteeing effective energy production, distribution, and rational utilization. Artificial neural networks have been extensively applied to heating energy prediction in DHS. Recently, a new time series prediction model namely Informer was proposed. This study proposes an Informer-based framework for DHS heating load forecasting. To explore the performance of Informer in heating load forecasting tasks, four forecasting models namely Autoregressive Integrated Moving Average model, Multilayer Perceptron, Recurrent Neural Network and Long Short-Term Memory network are established for comparison. The historical heating load, outdoor temperature, relative humidity, wind speed and air quality index of a DHS in Tianjin are used as the input characteristics to comprehensively assess the performance of these five forecasting strategies. The prediction results of the models are evaluated and visualized. The experimental results show that the Informer-based forecasting model can achieve the most accurate and stable predictions. Furthermore, a relative position encoding algorithm is introduced to enhance its generalization and robustness. Overall, the Informer-based framework can report satisfactory testing results. The prediction curve is fitted to the trend of temperature change which can play an excellent guiding role in heating dispatching. • A new framework based on Informer is proposed for heating load forecasting of a DHS in Tianjin, China. • Informer is compared with other four popular prediction models namely ARIMA, MLP, RNN and LSTM. • The performance of Informer in heating load forecasting has been verified. • A relative position coding is introduced to improve the prediction ability of Informer.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
每天读顶刊完成签到,获得积分10
刚刚
冬去春来发布了新的文献求助10
刚刚
1秒前
大模型应助danmoyjj采纳,获得30
1秒前
Yelicious发布了新的文献求助10
1秒前
小雒雒发布了新的文献求助10
2秒前
NINI发布了新的文献求助10
2秒前
wjx发布了新的文献求助10
3秒前
amberzyc完成签到,获得积分10
3秒前
疚祠发布了新的文献求助10
3秒前
3秒前
orixero应助欣慰的乌冬面采纳,获得10
4秒前
meng发布了新的文献求助10
4秒前
端庄的月光完成签到 ,获得积分10
5秒前
5秒前
领导范儿应助hh采纳,获得10
5秒前
星辰大海应助Fin2046采纳,获得10
6秒前
量子星尘发布了新的文献求助10
6秒前
6秒前
zwenng发布了新的文献求助10
6秒前
7秒前
8秒前
小饼干完成签到,获得积分10
8秒前
白白SAMA123完成签到,获得积分10
9秒前
蒲公英发布了新的文献求助10
9秒前
梦想里发布了新的文献求助10
11秒前
执剑燃此生完成签到,获得积分10
12秒前
12秒前
shinn发布了新的文献求助10
13秒前
13秒前
14秒前
14秒前
楚舜华发布了新的文献求助10
14秒前
14秒前
15秒前
练习时长两年半应助variant采纳,获得10
16秒前
打打应助刘潮汕采纳,获得10
17秒前
17秒前
wjx发布了新的文献求助30
17秒前
二零发布了新的文献求助10
17秒前
高分求助中
Picture Books with Same-sex Parented Families: Unintentional Censorship 700
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
Effective Learning and Mental Wellbeing 300
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3975165
求助须知:如何正确求助?哪些是违规求助? 3519595
关于积分的说明 11198781
捐赠科研通 3255912
什么是DOI,文献DOI怎么找? 1798001
邀请新用户注册赠送积分活动 877343
科研通“疑难数据库(出版商)”最低求助积分说明 806298