Vision-based detection and prediction of equipment heat gains in commercial office buildings using a deep learning method

Abstract Building energy consumption accounts for a large proportion of energy use globally. Previous works have shown that a large amount of energy is wasted in under- or over-utilized spaces since typical building management systems function based on fixed or static operation schedules. While the presence of occupants and how they use equipment contribute to the internal energy demand and affect the thermal environment. Office buildings are likely to have higher cooling demands in the future due to increasing use of equipment, emphasising the need to develop systems which can better understand (and reduce) the impact of internal gains from equipment and adapt to actual requirements. This project aims to develop a deep learning-based approach which enables the detection and recognition of equipment usage and the associated heat emissions in office spaces. Subsequently, the data can be fed into building energy management systems through the formation of equipment heat gain profile; therefore, building energy usage can be effectively managed. Experiments were conducted in typical offices to generate the corresponding heat gain profiles, and then these were used in building simulation software to assess building performance. It was found that the model can perform equipment detection with an accuracy of 89.3%. While maintaining thermal comfort levels, up to 19% annual cooling energy demand reduction can be achieved by the proposed strategy when compared to that for the building managed by a static scheduled heating, ventilation and air-conditioning system, where in the studies, we focus on three types of equipment - computer, printer and kettle that are widely used in the office buildings. The findings indicate that it is feasible to use the deep learning approach to predict equipment heat emission for achieving effective building energy management therefore to reduce building energy demand.

[1]  Michael Sheppy,et al.  Extracting Operating Modes from Building Electrical Load Data , 2011, 2011 IEEE Green Technologies Conference (IEEE-Green).

[2]  Ardeshir Mahdavi,et al.  Prediction of plug loads in office buildings: Simplified and probabilistic methods , 2016 .

[3]  J. L. Gomez Ortega,et al.  A machine-learning based approach to model user occupancy and activity patterns for energy saving in buildings , 2015, 2015 Science and Information Conference (SAI).

[4]  Sangmin Lee,et al.  Optimal power management for nanogrids based on technical information of electric appliances , 2019, Energy and Buildings.

[5]  Hao Jiang,et al.  Non-intrusive occupancy sensing in commercial buildings , 2017 .

[6]  R. Annie Uthra,et al.  Development and implementation of novel sensor fusion algorithm for occupancy detection and automation in energy efficient buildings , 2019 .

[7]  Miroslava Kavgic,et al.  Comparison of EnergyPlus and IES to model a complex university building using three scenarios: Free-floating, ideal air load system, and detailed , 2019, Journal of Building Engineering.

[8]  Gianpaolo Francesco Trotta,et al.  Computer vision and deep learning techniques for pedestrian detection and tracking: A survey , 2018, Neurocomputing.

[9]  Zoltán Nagy,et al.  Occupancy learning-based demand-driven cooling control for office spaces , 2017 .

[10]  Eduardo Álvarez-Miranda,et al.  A simulation and optimisation methodology for choosing energy efficiency measures in non-residential buildings , 2019, Applied Energy.

[11]  Alberto Mirandola,et al.  Components design and daily operation optimization of a hybrid system with energy storages , 2016 .

[12]  Jelena Srebric,et al.  Impact of occupancy rates on the building electricity consumption in commercial buildings , 2017 .

[13]  Ian Beausoleil-Morrison,et al.  Modeling plug-in equipment load patterns in private office spaces , 2016 .

[14]  Bart De Schutter,et al.  Forecasting spot electricity prices Deep learning approaches and empirical comparison of traditional algorithms , 2018 .

[15]  Neil Brown,et al.  Improved occupancy monitoring in non-domestic buildings , 2017 .

[16]  Peter E. D. Love,et al.  A deep learning-based approach for mitigating falls from height with computer vision: Convolutional neural network , 2019, Adv. Eng. Informatics.

[17]  Zhaoxia Wang,et al.  An occupant-based energy consumption prediction model for office equipment , 2015 .

[18]  José A. Candanedo,et al.  Model-based predictive control of an ice storage device in a building cooling system , 2013 .

[19]  Mary Ann Piette,et al.  Data fusion in predicting internal heat gains for office buildings through a deep learning approach , 2019, Applied Energy.

[20]  John Kaiser Calautit,et al.  Analysis of the Thermal Comfort and Energy Performance of a Thermal Chair for Open Plan Office , 2020 .

[21]  Ruey Lung Hwang,et al.  Future trends of residential building cooling energy and passive adaptation measures to counteract climate change: The case of Taiwan , 2016 .

[22]  Farrokh Jazizadeh,et al.  Human-in-the-loop HVAC operations: A quantitative review on occupancy, comfort, and energy-efficiency dimensions , 2019, Applied Energy.

[23]  Zoltán Nagy,et al.  Using machine learning techniques for occupancy-prediction-based cooling control in office buildings , 2018 .

[24]  Peter E.D. Love,et al.  Falls from heights: A computer vision-based approach for safety harness detection , 2018, Automation in Construction.

[25]  Lihua Xie,et al.  Building occupancy estimation and detection: A review , 2018, Energy and Buildings.

[26]  Darren Robinson,et al.  A generalised stochastic model for the simulation of occupant presence , 2008 .

[27]  Han Zou,et al.  Towards occupant activity driven smart buildings via WiFi-enabled IoT devices and deep learning , 2018, Energy and Buildings.

[28]  Jie Zhao,et al.  Occupant behavior and schedule modeling for building energy simulation through office appliance power consumption data mining , 2014 .

[29]  Oliver Amft,et al.  Recognizing Energy-related Activities Using Sensors Commonly Installed in Office Buildings , 2013, ANT/SEIT.

[30]  Yixing Chen,et al.  Occupant behavior models: A critical review of implementation and representation approaches in building performance simulation programs , 2018 .

[31]  Shawn H. Sun,et al.  Understanding artificial intelligence based radiology studies: What is overfitting? , 2020, Clinical imaging.

[32]  Mark Gillott,et al.  The development of occupancy monitoring for removing uncertainty within building energy management systems , 2017, 2017 International Conference on Localization and GNSS (ICL-GNSS).

[33]  Han Zou,et al.  Device-free occupancy detection and crowd counting in smart buildings with WiFi-enabled IoT , 2018, Energy and Buildings.

[34]  Nan Li,et al.  Measuring and monitoring occupancy with an RFID based system for demand-driven HVAC operations , 2012 .

[35]  Ahmad Lotfi,et al.  Behavioural pattern identification and prediction in intelligent environments , 2013, Appl. Soft Comput..

[36]  John Kaiser Calautit,et al.  Advanced personal comfort system (APCS) for the workplace: A review and case study , 2018 .

[37]  Chandra Sekhar,et al.  Energy saving estimation for plug and lighting load using occupancy analysis , 2019, Renewable Energy.

[38]  Yixuan Wei,et al.  Prediction of occupancy level and energy consumption in office building using blind system identification and neural networks , 2019, Applied Energy.

[39]  Hélène Laurent,et al.  Towards a sensor for detecting human presence and characterizing activity , 2011 .

[40]  Gongsheng Huang,et al.  Multiplexed real-time optimization of HVAC systems with enhanced control stability , 2017 .

[41]  Wei Wang,et al.  Energy efficient HVAC control for an IPS-enabled large space in commercial buildings through dynamic spatial occupancy distribution , 2017 .

[42]  Panagiota Karava,et al.  A model predictive control strategy to optimize the performance of radiant floor heating and cooling systems in office buildings , 2019, Applied Energy.

[43]  Ian Walker,et al.  The building performance gap: Are modellers literate? , 2017 .

[44]  Dino Bouchlaghem,et al.  Estimating the energy consumption and power demand of small power equipment in office buildings , 2014 .

[45]  Sheldon X.-D. Tan,et al.  Thermal-Sensor-Based Occupancy Detection for Smart Buildings Using Machine-Learning Methods , 2018, ACM Trans. Design Autom. Electr. Syst..

[46]  Nilay Shah,et al.  Smart energy systems for sustainable smart cities: Current developments, trends and future directions , 2019, Applied Energy.