Multi-Step Forecasting for Lighting and Equipment Energy Consumption in Office Building Based on Deep Learning

被引：1
|
作者：
Zhou X. [1 ]
Lei S. [1 ]
Yan J. [1 ]
机构：
[1] School of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou
来源：
Huanan Ligong Daxue Xuebao/Journal of South China University of Technology (Natural Science) | 2020年 / 48卷 / 10期
关键词：
Deep learning; Large-scale office building; Lighting and equipment energy consumption; Long-short term memory model; Multi-step forecasting;
D O I：
10.12141/j.issn.1000-565X.190546
中图分类号：
学科分类号：
摘要：
Multi-step forecasting for lighting and equipment energy consumption is important for fine management of building energy, regulation of power load and other areas related to building energy saving. However, due to the uncertainty, randomness and nonlinearity caused by multiple factors, such as indoor human behavior, external environment and relative humidity, it is difficult to make accurate prediction of lighting and equipment energy consumption. In this paper, the distribution tendency of time series of sub-item energy consumption in large-scale office building was analyzed, and a multi-step forecasting method for lighting and equipment energy consumption was put forward based on long-short term model. Moreover, parameter selection issues concerning the deep learning model, such as the number of hidden layer, the number of hidden layer neurons and the times of iterations depth were discussed, and the influence of sample size on the model accuracy was investigated. Simulation results show that the average accuracy of the 24h multi-step forecasting model based on deep learning is improved by 13.25% and 4.23% respectively compared with that of the BP neural network and least squares support vector machine. © 2020, Editorial Department, Journal of South China University of Technology. All right reserved.
引用
收藏
页码：19 / 29
页数：10
相关论文
共 25 条
  • [1] pp. 26-45, (2018)
  • [2] XIAO He, WEI Qing-peng, Dual structure in energy consumption of public building, Construction Science and Technology, 8, pp. 31-34, (2010)
  • [3] BENNET E Isis, O'BRIEN William, Office building plug and light loads:comparison of a multi-tenant office tower to conventional assumptions, Energy and Buildings, 153, pp. 461-475, (2017)
  • [4] PISELLI Cristina, PISELLO Laura Ann, Occupant behavior long-term continuous monitoring integrated to prediction models:impact on office building energy performance, Energy, 176, pp. 667-681, (2019)
  • [5] Burak GUNAY H, O'BRIEN William, -MORRISON Ian BEAUSOLEIL, Et al., Modeling plug-in equipment load patterns in private office spaces, Energy and Buildings, 121, pp. 234-249, (2016)
  • [6] WANG Chuang, YAN Da, REN Xiaoxin, Modeling individual's light switching behavior to understand lighting energy use of office building, Energy Procedia, 88, pp. 781-787, (2016)
  • [7] ANAND Prashant, CHEONG David, SEKHAR Chandra, Et al., Energy saving estimation for plug and lighting load using occupancy analysis[J], Renewable Energy, 143, pp. 1143-1161, (2019)
  • [8] WANG Zhe, HONG Tianzhen, PIETTE Ann Mary, Predicting plug loads with occupant count data through a deep learning approach, Energy, 181, pp. 29-42, (2019)
  • [9] MAHDAVI Ardeshir, TAHMASEBI Farhang, Mine KAYALAR, Prediction of plug loads in office buildings:simplified and probabilistic methods, Energy and Buildings, 129, pp. 322-329, (2016)
  • [10] CHAMMAS Michel, MAKHOUL Abdallah, DEMERJIAN Jacques, An efficient data model for energy prediction using wireless sensors, Computers & Electrical Engineering, 76, pp. 249-257, (2019)
123