Page 273 - 《高原气象》2025年第3期
P. 273
3 期 苗 芮等:基于深度学习的多气象要素影响的供热负荷预测模型研究 831
热负荷预测模型的性能, 相较于仅输入气温, 相对 Building Technology Communication (2): 49.
误差减小约 1. 4 %。此外, 在相同的数据条件下, 李志新, 赖志琴, 2019. 基于 NARX 神经网络的电力负荷中期预测
[J]. 贵州农机化, 1: 26-31. Li Z X, Lai Z Q, 2019. Medium
NARX_8_4神经网络模型的预测误差较 LSTM 模型
term forecast of power load based on NARX neural network[J].
降低约3. 6 %。 Guizhou Agricultural Mechanization, 1: 26-31.
鹿宇, 2022. 热力站供热负荷预测的影响因素研究[D]. 北京: 北京
参考文献(References):
建筑大学 . Lu Y, 2022. Study on the influencing factors of heat‐
ing load forecast for thermal power station[D]. Beijing: Beijing
Chan A L S, 2011. Developing future hourly weather files for studying
University of Civil Engineering and Architecture.
the impact of climate change on building energy performance in
全德海, 2020. 室外温度变化与间歇供暖对值班供暖室温的影响
Hong Kong[J]. Energy and Buildings, 43(10): 2860-2868.
[J]. 建筑节能, 2(48): 163-168. Quan D H, 2020. Effect of
Ferbar T L, Strmcnik E, 2016. The comparision of Holt-winters meth‐
outdoor temperature change and intermittent heating on room tem‐
od and multiple regression method: a case study[J]. Energy and
perature of non-working time heating[J]. Building Energy Effi‐
Buildings, 109: 266-276.
ciency, 2(48): 163-168.
Hashmi M U, Arora V, Priolkar J G, 2015. Hourly electric load fore‐
孙玫玲, 李明财, 曹经福, 2018. 利用采暖/制冷度日分析不同气候
casting using Nonlinear AutoRegressive with eXogenous
区建筑能耗的适用性评估[J]. 气象与环境学报, 34(5): 135-
(NARX) based neural network for the state of Goa, India[C]. In‐
141.Sun M L, Li M C, Cao J F, 2018. Applicability of cooling/
ternational Conference on Industrial Instrumentation and Control,
heating degree days in evaluating building energy consumption of
1418-1423.
different climate zones[J]. Journal of Meteorology and Environ‐
Kelvin K K W, Danny W W L, Liu D L, et al, 2011. Future trends of
ment. Journal of Meteorology and Environment, 34 (5) :
building heating and cooling loads and energy consumption in dif‐
135-141.
ferent climates[J]. Building and Environment, 46(1): 223-234.
孙玫玲, 袁闪闪, 张宇峰, 等, 2019. 基于精细化气象预报的供热调
Li Z W, Huang G S, 2013. Re-evaluation of building cooling load pre‐
控技术研究进展[J]. 建筑科学, 35(10): 182-190. Sun M L,
diction models for use in humid subtropical area[J]. Energy and
Yuan S S, Zhang Y F, et al, 2019. A review of research process
Buildings, 62(3): 442-449.
in heating regulation technology based on fine meteorological
Liu R, Kuang J, Gong Q, et al, 2003. Principal component regres‐
forecast[J]. Building Science, 35(10): 182-190.
sion analysis with SPSS[J]. Computer Methods and Programs in
王凇, 2022. 基于机器学习的智慧供热负荷预测研究[D]. 吉林建筑
Biomedicine, 71(2): 141-147.
大学 . Wang S, 2022. Research on intelligent heating load fore‐
Powell K M, Akshay S, Wesley J C, et al, 2014. Heating, cooling,
casting based on machine learning[D]. Jilin Jianzhu University.
and electrical load forecasting for a large-scale district energy sys‐
王文标, 蔡麒, 汪思源, 2016. 基于气象因素的集中供热系统热负
tem[J]. Energy, 74: 877-885.
荷预测研究[J]. 计算机测量与控制, 24(2): 22-26. Wang W
Sansa I, Missaoui S, Boussada Z, et al, 2014. PV power forecasting B, Cai Q, Wang S Y, 2016. Research of district heating system
using different artificial neural networks strategies[C]. Interna‐
heat load prediction based on weather factors[J]. Computer Mea‐
tional Conference on Green Energy, Piscataway, NJ: IEEE, surement &Control, 24(2): 22-26.
2014: 54-59. 王雪菲, 李勇, 余国晓, 等, 2022. 基于 DMD-NARX 模型的短期电
Stephenson D G, Mitalas G P, 1967. Cooling load calculation by ther‐ 力负荷预测方法[J]. 黑龙江大学自然科学学报, 39(3): 307-
mal response factors[J]. ASHRAE Transaction, 73(1): 2. 316. Wang X F, Li Y, Yu G X, et al, 2022. Short-term power
Wang Y M, Li Z W, Liu J J, et al, 2023. Data-driven analysis and load forecasting method based on DMD-NARX model[J]. Jour‐
prediction of indoor characteristic temperature in district heating nal of Natural Science of Heilongjiang University, 39(3):
systems[J]. Energy, 282: 129023. 307-316.
Werner S, 1984. The heat load in district heating system[J]. Sweden: 夏雨, 2019. 基于西安实测的某集中供热系统动态分析及调控策略
Chalmers Unicersity of Technology. [D]. 西安: 西安工程大学 . Xia Y, 2019. Dynamic analysis and
Wojdyga K, 2008. An influence of weather conditions on heat demand control strategy of a central heating system based on field mea‐
in district heating systems[J]. Energy and Buildings, 40(11): surement in Xi'an[D]. Xi'an: Xi'an University of Engineering.
2009-2014. 谢吉洋, 闫冬, 谢垚, 等, 2018. 基于 NARX神经网络的热负荷预测
Zhao J, Liu X J, 2018. A hybrid method of dynamic cooling and heat‐ 中关键影响因素分析[J]. 计算机应用, 38(11): 3180-3187.
ing load forecasting for office buildings based on artificial intelli‐ Xie J Y, Yan D, Xie Y, et al, 2018. Analysis of key factors in
gence and regression analysis. Energy and Buildings, 174: heat demand prediction based on NARXneural network[J]. Jour‐
293-308. nal of Computer Applications, 38(11): 3180-3187.
江亿, 1981. 模拟房间热响应的新方法——状态空间法[J]. 建筑技 张德山, 王保民, 陈正洪, 等, 2008. 北京市城市集中供热节能气象
术通讯(暖通空调) (2): 49. Jiang Y, 1981. A new method to 预报系统的应用[J]. 煤气与热力, 28(11): 23-25. Zhang D S,
simulate room thermal response——State space method[J]. Wang B M, Chen Z H, et al, 2008. Application of weather fore‐