On-line learning of indoor temperature forecasting models towards energy efficiency

被引:100
|
作者
Zamora-Martinez, F. [1 ]
Romeu, P. [1 ]
Botella-Rocamora, P. [1 ]
Pardo, J. [1 ]
机构
[1] Univ CEU Cardenal Herrera, Escuela Super Ensenanzas Tecn, Embedded Syst & Artificial Intelligence Grp, Valencia 46115, Spain
关键词
Energy efficiency; Time series forecasting; Bayesian models; Gradient descent; Artificial neural networks; ARTIFICIAL NEURAL-NETWORK; PREDICTIVE CONTROL; SIMULATION;
D O I
10.1016/j.enbuild.2014.04.034
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
The SMLsystem is a house built at the Universidad CEU Cardenal Herrera (CEU-UCH) to participate in the Solar Decathlon 2012 competition. Several technologies have been integrated to reduce power consumption. A predictive module, based on artificial neural networks (ANNs), has been developed using data acquired in Valencia. The module produces short-term forecast of indoor temperature, using as input data captured by a complex monitoring system. The system expects to reduce the power consumption related to Heating, Ventilation and Air Conditioning (HVAC) system, due to the following assumptions: the high power consumption for which HVAC is responsible (53.9% of the overall consumption); and the energy needed to maintain temperature is less than the energy required to lower/increase it. This paper studies the development viability of predictive systems for a totally unknown environment applying online learning techniques. The model parameters are estimated starting from a totally random model or from an unbiased a priori knowledge. These forecasting measures could allow the house to adapt itself to future temperature conditions by using home automation in an energy-efficient manner. Experimental results show reasonable forecasting accuracy with simple models, and in relatively short training time (4-5 days). (C) 2014 Elsevier B.V. All rights reserved.
引用
收藏
页码:162 / 172
页数:11
相关论文
共 50 条
  • [1] Towards Energy Efficiency: Forecasting Indoor Temperature via Multivariate Analysis
    Zamora-Martinez, Francisco
    Romeu, Pablo
    Botella-Rocamora, Paloma
    Pardo, Juan
    ENERGIES, 2013, 6 (09): : 4639 - 4659
  • [2] Deep Learning Models for Time Series Forecasting of Indoor Temperature and Energy Consumption in a Cold Room
    Mellouli, Nedra
    Akerma, Mahdjouba
    Hoang, Minh
    Leducq, Denis
    Delahaye, Anthony
    COMPUTATIONAL COLLECTIVE INTELLIGENCE, PT II, 2019, 11684 : 133 - 144
  • [3] Toward on-line predictive models for forecasting workload in Clouds
    Dong Nguyen Doan
    2018 20TH INTERNATIONAL SYMPOSIUM ON SYMBOLIC AND NUMERIC ALGORITHMS FOR SCIENTIFIC COMPUTING (SYNASC 2018), 2019, : 260 - 265
  • [4] Towards on-line learning agents for autonomous navigation
    Li, Guang
    Doktorsavhandlingar vid Chalmers Tekniska Hogskola, 1999, (1523): : 1 - 68
  • [5] Use of Machine Learning Methods for Indoor Temperature Forecasting
    Ramadan, Lara
    Shahrour, Isam
    Mroueh, Hussein
    Chehade, Fadi Hage
    FUTURE INTERNET, 2021, 13 (10):
  • [6] Fast on-line learning of point distribution models
    Al-Shaher, AA
    Hancock, ER
    16TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL II, PROCEEDINGS, 2002, : 208 - 211
  • [7] Embedded On-line System for Electrical Energy Measurement and Forecasting in Buildings
    Nichiforov, Cristina
    Stamatescu, Grigore
    Stamatescu, Iulia
    Arghira, Nicoleta
    Fagarasan, Ioana
    Iliescu, Sergiu Stelian
    PROCEEDINGS OF THE 2019 10TH IEEE INTERNATIONAL CONFERENCE ON INTELLIGENT DATA ACQUISITION AND ADVANCED COMPUTING SYSTEMS - TECHNOLOGY AND APPLICATIONS (IDAACS), VOL. 2, 2019, : 586 - 591
  • [8] Students' attitudes towards an on-line orthodontic learning resource
    Linjawi, A. L.
    Hamdan, A. M.
    Perryer, D. G.
    Walmsley, A. D.
    Hill, K. B.
    EUROPEAN JOURNAL OF DENTAL EDUCATION, 2009, 13 (02) : 87 - 92
  • [9] On-line energy education: Learning anywhere, anytime
    Amundsen, Robert N.
    Strategic Planning for Energy and the Environment, 2000, 19 (04) : 69 - 76
  • [10] An on-line approach for energy efficiency monitoring of machine tools
    Hu, Shaohua
    Liu, Fei
    He, Yan
    Hu, Tong
    JOURNAL OF CLEANER PRODUCTION, 2012, 27 : 133 - 140