Learning short-term past as predictor of human behavior in commercial buildings

This paper addresses the question of identifying the time-window in short-term past from which the information regarding the future occupant's window opening actions and resulting window states in buildings can be predicted. The addressed sequence duration was in the range between 30 and 240 time-steps of indoor climate data, where the applied temporal discretization was one minute. For that purpose, a deep neural network is trained to predict the window states, where the input sequence duration is handled as an additional hyperparameter. Eventually, the relationship between the prediction accuracy and the time-lag of the predicted window state in future is analyzed. The results pointed out, that the optimal predictive performance was achieved for the case where 60 time-steps of the indoor climate data were used as input. Additionally, the results showed that very long sequences (120-240 time-steps) could be addressed efficiently, given the right hyperprameters. Hence, the use of the memory over previous hours of high-resolution indoor climate data did not improve the predictive performance, when compared to the case where 30/60 minutes indoor sequences were used. The analysis of the prediction accuracy in the form of F1 score for the different time-lag of future window states dropped from 0.51 to 0.27, when shifting the prediction target from 10 to 60 minutes in future.

[1]  R. Fritsch,et al.  A stochastic model of user behaviour regarding ventilation , 1990 .

[2]  Elie Azar,et al.  A comprehensive framework to quantify energy savings potential from improved operations of commercial building stocks , 2014 .

[3]  Bing Dong,et al.  Sensor-based occupancy behavioral pattern recognition for energy and comfort management in intelligent buildings , 2009 .

[4]  Na Zhu,et al.  Occupancy prediction through Markov based feedback recurrent neural network (M-FRNN) algorithm with WiFi probe technology , 2018, Building and Environment.

[5]  Lingfeng Wang,et al.  Development of multi-agent system for building energy and comfort management based on occupant behaviors , 2013 .

[6]  Jesús Martínez del Rincón,et al.  Recurrent Convolutional Network for Video-Based Person Re-identification , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Michael C. Mozer,et al.  A Focused Backpropagation Algorithm for Temporal Pattern Recognition , 1989, Complex Syst..

[8]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[9]  Frederico G. Guimarães,et al.  A GPU deep learning metaheuristic based model for time series forecasting , 2017 .

[10]  Bing Dong,et al.  A real-time model predictive control for building heating and cooling systems based on the occupancy behavior pattern detection and local weather forecasting , 2013, Building Simulation.

[11]  Ernest Orlando Lawrence,et al.  An Ontology to Represent Energy- related Occupant Behavior in Buildings Part I: Introduction to the DNAs Framework , 2015 .

[12]  Andreas Wagner,et al.  Exploring occupant behavior in buildings: Methods and challenges , 2018 .

[13]  Simon King,et al.  Deep neural networks employing Multi-Task Learning and stacked bottleneck features for speech synthesis , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[14]  Bing Dong,et al.  Occupancy behavior based model predictive control for building indoor climate—A critical review , 2016 .

[15]  B R Baker,et al.  Using images to generate speech , 1986 .

[16]  Biao Huang,et al.  A Long-Short Term Memory Recurrent Neural Network Based Reinforcement Learning Controller for Office Heating Ventilation and Air Conditioning Systems , 2017 .

[17]  A. Ng.  Feature selection, L1 vs. L2 regularization, and rotational invariance , 2004, Twenty-first international conference on Machine learning - ICML '04.

[18]  David H. Albonesi,et al.  Energy-comfort optimization using discomfort history and probabilistic occupancy prediction , 2014, International Green Computing Conference.

[19]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups , 2012, IEEE Signal Processing Magazine.

[20]  Ardeshir Mahdavi,et al.  On the quality evaluation of behavioural models for building performance applications , 2017 .

[21]  Prabir Barooah,et al.  Agent-based and graphical modelling of building occupancy , 2012 .

[22]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[23]  Siliang Lu,et al.  A DEEP REINFORCEMENT LEARNING APPROACH TO USINGWHOLE BUILDING ENERGYMODEL FOR HVAC OPTIMAL CONTROL , 2018 .

[24]  Gerald Penn,et al.  Convolutional Neural Networks for Speech Recognition , 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[25]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[26]  Darren Robinson,et al.  A bottom-up stochastic model to predict building occupants' time-dependent activities , 2013 .

[27]  Brandon Hencey,et al.  Model Predictive HVAC Control with Online Occupancy Model , 2014, ArXiv.

[28]  Christoph van Treeck,et al.  Window Opening Model using Deep Learning Methods , 2018, Building and Environment.

[29]  Dirk Müller,et al.  WinProGen: A Markov-Chain-based stochastic window status profile generator for the simulation of realistic energy performance in buildings , 2018 .

[30]  Pawalai Kraipeerapun,et al.  Room Occupancy Detection using Modified Stacking , 2017, ICMLC.

[31]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[32]  Razvan Pascanu,et al.  On the difficulty of training recurrent neural networks , 2012, ICML.

[33]  Diane J. Cook,et al.  Data Mining for Hierarchical Model Creation , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[34]  Zhongdong Qi,et al.  Learning-based occupancy behavior detection for smart buildings , 2016, 2016 IEEE International Symposium on Circuits and Systems (ISCAS).

[35]  Bing Dong,et al.  A new modeling approach for short-term prediction of occupancy in residential buildings , 2017 .

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

[37]  Bing Dong,et al.  Investigation of A Short-term Prediction Method of Occupancy Presence in Residential Buildings , 2017 .