Understanding occupancy pattern and improving building energy efficiency through Wi-Fi based indoor positioning

Building and Environment

Hong

et al. 2019

Fusing various sensing data sources is able to improve the accuracy and reliability of building occupancy detection. Efficiently fusing environmental sensors and wireless network signals is seldom studied for its computational and technical challenges. This study aims to propose an integrated model that is able to extract critical data features for environmental and Wi-Fi probe dual sensing sources to promote computational efficiency. The adaptive lasso model was introduced for the feature extraction and reduction process. To validate the proposed model, an onsite experiment was conducted and two occupancy resolutions, real-time and four-level occupancy resolutions, were compared. The results suggested that eight features among all twelve features are most relevant. The mean absolute error of the selected data features is about 2.18 for real-time occupancy and F1_accuracy is about 84.36% for four-level occupancy.

Section: Occupancy Studies With Single Data Typementioning

confidence: 99%

Cross-source sensing data fusion for building occupancy prediction with adaptive lasso feature filtering

Building and Environment

Hong

et al. 2019

“…Researchers have proposed multiple methods to detect occupant count, such as CO 2 concentration based models [38], [39], Radio-Frequency Identification detection (RFID) systems [40], Wi-Fi connection based detection [41], [42], and camera-based sensors [43], [44]. Yang et al (2016) summarized the advantages and disadvantages of the currently available occupancy detection approaches [45].…”

Section: Occupancy Detectionmentioning

confidence: 99%

Predicting plug loads with occupant count data through a deep learning approach

Hong

Piette

2019

Energy

Predictive control has gained increasing attention for its ability to reduce energy consumption and improve occupant comfort in buildings. The plug loads prediction is a key component for the predictive building controls, as plug loads is a major source of internal heat gains in buildings. This study proposed a novel method to apply the Long-Short-Term-Memory (LSTM) Network, a special form of Recurrent Neural Network, to predict plug loads. The occupant count and the time have been confirmed to drive the plug load profile and thus selected as the features for the plug load prediction. The LSTM network was trained and tested with ground truth occupant count data collected from a real office building in Berkeley, California. Results from the LSTM network markedly improve the prediction accuracy compared with traditional linear regression methods and the classical Artificial Neural Network. 95% of 1-hour predictions from LSTM network are within ±1 kW of the actual plug loads, given the average plug loads during the office hour is 8.6 kW. The CV(RMSE) of the predicted plug load is 11% for the next hour, and 20% for the next eight hours. Lastly, we compared four prediction approaches with the office building we monitored: LSTM vs. ARIMA, with occupant counts vs. without occupant counts. It was found, the prediction error of the LSTM approach is around 4% less than the ARIMA approach. Using occupant counts as an exogenous input could further reduce the prediction error by 5%-6%. The findings of this paper could shed light on the plug load prediction for building control optimizations such as model-predictive control.

“…Secondly, it is necessary to determine the duration when a detected device is inside the studied space. A Visual Basic programme was developed by the authors for this purpose (Wang, 2016). A more detailed occupancypattern analysis was carried out using open source software R.…”

Section: Calculationmentioning

confidence: 99%

“…Occupancy information is also important for building simulation tools for IEQ and IAQ assessment (Duarte, Wymelenberg & Rieger, 2013), and significant deviation of prediction to ground truth can occur when fixed occupancy profile assumptions are used during simulation to represent highly variable or stochastic occupancy scenarios (Chang & Hong, 2013). In addition, the impact of occupancy on energy demand reduction has been widely recognised (Wang & Shao, 2017) and detailed occupancy monitoring has brought significant advancement to the quantitative study of building space usage (Spataru, Gillott, & Hall, 2010).…”

Section: Introductionmentioning

confidence: 99%

Understanding occupancy and user behaviour through Wi-Fi-based indoor positioning

Building Research & Information

Shao

2017

A 30-day monitoring campaign was conducted in a university library building to investigate the usefulness of a novel Wi-Fi based indoor location system for revealing indoor occupancy patterns and related user behaviour. The system has demonstrated its effectiveness in providing occupancy information with a relatively high degree of granularity and accuracy in this study. The occupancy results revealed that the 24-hour opening policy for the library during the term time was not necessary. On the other hand, the 8-hour library-opening duration during the summer vacation could be extended to include the early evening hours to benefit user productivity. Four occupancy patterns were identified based on cluster analysis. Most users were found to belong to the short-occupancy one-time visitor type, while a minority were the long-occupancy users. The cross-correlations between various occupancy parameters were investigated. For example, the pattern of user arrival times at the library was found to be significantly correlated with their study durations. Further data analysis showed that the majority of long-occupancy users tended not to have frequent breaks with some taking no break for 4 hours. This could have implications for their health and wellbeing as well as their productivity.