Hourly Energy Consumption Forecasting for Office Buildings Based on Support Vector Machine

doi:10.16183/j.cnki.jsjtu.2019.310

Abstract

Abstract:

Aimed at the nonlinearity and uncertainty of building energy consumption, a forecasting approach based on the support vector machine is proposed in this paper for the prediction of hourly energy consumption of an office building. The univariate model test is used to determine the input parameters. Superior model hyper-parameters are found by grid search optimization. The confidence interval of the model fitting error is applied to describe the uncertainty of building energy consumption. A case study is conducted using the data collected from an actual office building to verify the proposed approach. The results show that the overall mean absolute percentage error (MAPE) of the model after grid search optimization is reduced by 31.3%, and a higher model precision is achieved. After combining the prediction with the confidence interval, MAPE is found to be lower than 1.5% in different seasons and the building operation fluctuations are embodied. This approach can be used in the diagnosis and optimization of building operation.

Key words: energy consumption, forecasting approach, support vector machine, grid search, confidence interval

CLC Number:

TU855

XIAO Ran, WEI Ziqing, ZHAI Xiaoqiang. Hourly Energy Consumption Forecasting for Office Buildings Based on Support Vector Machine[J]. Journal of Shanghai Jiao Tong University, 2021, 55(3): 331-336.

Figures/Tables 7

Fig.1

Fig.2

Fig.3

Tab.1

Tab.2

Fig.4

Tab.3

References 15

[1]	中国建筑节能协会能耗统计专委会. 2018中国建筑能耗研究报告[J]. 建筑，2019(2): 26-31.
	China Association of Building Energy Efficiency. 2018 China building energy research report[J]. Construction and Architecture, 2019(2): 26-31.
[2]	刘海静，潘毅群. 区域建筑群负荷预测及其平准化分析[J]. 暖通空调，2017, 47(4): 14-18.
	LIU Haijing, PAN Yiqun. Load prediction and leveling analysis for community buildings[J]. Heating Ventilating & Air Conditioning, 2017, 47(4): 14-18.
[3]	AFRAM A, JANABI S F, FUNG A S, et al. Artificial neural network (ANN) based model predictive control (MPC)and optimization of HVAC systems: A state of the art review and case study of a residential HVAC system[J]. Energy and Buildings, 2017(141): 96-113.
[4]	FOUCQUIER A, ROBERT S, SUARD F, et al. State of the art in building modelling and energy performances prediction: A review[J]. Renewable and Sustainable Energy Reviews, 2013(23): 272-288.
[5]	李紫微，林波荣，陈洪钟. 建筑方案能耗快速预测方法研究综述[J]. 暖通空调，2018, 48(5): 1-8.
	LI Ziwei, LIN Borong, CHEN Hongzhong. Review of rapid prediction method of building energy consumption[J]. Heating Ventilating & Air Conditioning, 2018, 48(5): 1-8.
[6]	LI X W, WEN J. Review of building energy modeling for control and operation[J]. Renewable and Sustainable Energy Reviews, 2014, 37: 517-537.
[7]	BOURDEAU M, ZHAI X Q, NEFZAOUI E, et al. Modeling and forecasting building energy consumption: A review of data-driven techniques[J]. Sustainable Cities and Society, 2019, 48: 101533.
[8]	侯博文，谭泽汉，陈焕新，等. 基于支持向量机的建筑能耗预测研究[J]. 制冷技术，2019, 39(2): 1-6.
	HOU Bowen, TAN Zehan, CHEN Huanxin, et al. Research on building energy consumption prediction based on support vector machine[J]. Chinese Journal of Refrigeration Technology, 2019, 39(2): 1-6.
[9]	AHMAD T, CHEN H X, GUO Y B, et al. A comprehensive overview on the data driven and large scale based approaches for forecasting of building energy demand: A review[J]. Energy and Buildings, 2018, 165: 301-320.
[10]	QUAN H, SRINIVASAN D, KHOSRAVI A. Uncertainty handling using neural network-based prediction intervals for electrical load forecasting[J]. Energy, 2014, 73(7): 916-925.
[11]	PRODREGOSA F, et al. Scikit-learn: Machine learning in Python[J]. Journal of Machine Learning Research, 2011(12): 2825-2830.
[12]	CORTES C, VAPNIK V. Support-vector networks[J]. Machine Learning, 1995, 20(3): 273-297.
[13]	SMOLA A J, SCHÖLKOPF B. A tutorial on support vector regression[J]. Statistics and Computing, 2004, 14(3): 199-222.
[14]	IOWA STATE UNIVERSITY. Iowa environmental mesonet [DB/OL]. (2019-10-15) [2019-10-22]. .
[15]	SEABOLD S, PERKTOLD J. Statsmodels: Econometric and statistical modeling with Python [EB/OL]. (2010)[2019-10-22]. .

变量	R²
当前时刻	0.748 4
工作日与否	0.087 4
室外气温	0.499 4
室外相对湿度	0.441 4
风速	－0.027 2
1 h前能耗值	0.892 7
24 h前能耗值	0.690 6

模型	季节	拟合性能		预测性能		模型超参数
模型	季节	MAPE	R²	MAPE	R²	C	γ	ε
SVM	供暖季	11.03%	0.952 6	8.635%	0.938 3	1	0.036	0.1
	过渡季	11.73%	0.934 1	14.26%	0.866 4	1	0.036	0.1
	供冷季	11.41%	0.965 9	10.04%	0.970 3	1	0.036	0.1
GS-SVM	供暖季	6.012%	0.974 2	6.482%	0.943 8	10	0.1	0.001
	过渡季	5.690%	0.971 1	8.710%	0.939 4	100	0.1	0.001
	供冷季	5.326%	0.984 0	7.133%	0.974 8	10	0.1	0.01

季节	MAPE	P_in
供热季	1.333%	77.4%
过渡季	1.028%	75.6%
供冷季	1.046%	76.2%