Hidden Markov Models for indirect classification of occupant behaviour

Abstract

Even for similar residential buildings, a huge variability in the energy consumption can be observed. This variability is mainly due to the different behaviours of the occupants and this impacts the thermal (temperature setting, window opening, etc.) as well as the electrical (appliances, TV, computer, etc.) consumption.It is very seldom to find direct observations of occupant presence and behaviour in residential buildings. However, given the increasing use of smart metering, the opportunity and potential for indirect observation and classification of occupants' behaviour is possible. This paper focuses on the use of Hidden Markov Models (HMMs) to create methods for indirect observations and characterisation of occupant behaviour.By applying homogeneous HMMs on the electricity consumption of fourteen apartments, three states describing the data were found suitable. The most likely sequence of states was determined (global decoding). From reconstruction of the states, dependencies like ambient air temperature were investigated. Combined with an occupant survey, this was used to classify/interpret the states as 1) Absent or asleep, 2) Home, medium consumption and 3) Home, high consumption. From the global decoding, the average probability profiles with respect to time of day were investigated, and four distinct patterns of occupant behaviour were observed. Based on the initial results of the homogeneous HMMs and with the observed dependencies, time dependent HMMs (inhomogeneous HMMs) were developed, which improved forecasting. For both the homogeneous and inhomogeneous HMMs, indications of common parameters were observed, which suggests further development of the HMMs as population models.

Study on Transition of Primary Energy Structure and Carbon Emission Reduction Targets in China Based on Markov Chain Model and GM (1, 1)

“…And the modeling process of the simple linear regression model can refer to the relevant literature [24]. [25][26][27][28]. A Markov chain can be expressed as X = X( ), = 0, 1, 2, .…”

Semantic trajectory insights for worker safety in dynamic environments

“…The pseudo-residuals should follow a standard normal distribution if the trained model is a true datagenerating process [89]. It means that, if the model fits the data well, the points in the qq-plot will be closer to the straight line and a deviation from normality will indicate a lack of fit [90,91]. Moreover, an absolute value of residual increases with increased deviation from the straight line and specific observations can be known in less time.…”

CO2-based grey-box model to estimate airflow rate and room occupancy

“…These are statistical models that allow to draw inference about the unobserved occupancy state from of one or more observed variables. The authors in [9] use of HMM for occupancy modelling based on observations from smart electricity meters. However, in most cases, the observations contain environmental variables such as the CO2 concentration ( [10][11][12]).…”