Temporal Mining Approaches for Smart Buildings Research
| dc.contributor.author | Shao, Huijuan | en |
| dc.contributor.committeechair | Ramakrishnan, Naren | en |
| dc.contributor.committeemember | Lu, Chang-Tien | en |
| dc.contributor.committeemember | Vullikanti, Anil Kumar S. | en |
| dc.contributor.committeemember | Marwah, Manish | en |
| dc.contributor.committeemember | Prakash, B. Aditya | en |
| dc.contributor.department | Computer Science | en |
| dc.date.accessioned | 2018-07-25T06:00:21Z | en |
| dc.date.available | 2018-07-25T06:00:21Z | en |
| dc.date.issued | 2017-01-30 | en |
| dc.description.abstract | With the advent of modern sensor technologies, significant opportunities have opened up to help conserve energy in residential and commercial buildings. Moreover, the rapid urbanization we are witnessing requires optimized energy distribution. This dissertation focuses on two sub-problems in improving energy conservation; energy disaggregation and occupancy prediction. Energy disaggregation attempts to separate the energy usage of each circuit or each electric device in a building using only aggregate electricity usage information from the meter for the whole house. The second problem of occupancy prediction can be accomplished using non-invasive indoor activity tracking to predict the locations of people inside a building. We cast both problems as temporal mining problems. We exploit motif mining with constraints to distinguish devices with multiple states, which helps tackle the energy disaggregation problem. Our results reveal that motif mining is adept at distinguishing devices with multiple power levels and at disentangling the combinatorial operation of devices. For the second problem we propose time-gap constrained episode mining to detect activity patterns followed by the use of a mixture of episode generating HMM (EGH) models to predict home occupancy. Finally, we demonstrate that the mixture EGH model can also help predict the location of a person to address non-invasive indoor activities tracking. | en |
| dc.description.abstractgeneral | This dissertation uses data analytics techniques to address energy problems in commercial and residential buildings. One topic is energy disaggregation, which is to discover energy consumption patterns without instrumenting each device inside a building. This research gains insight into the following electricity usages inside a building: what devices use majority of power; how much electricity is consumed by each device; when a device is turned on or off. Since we only analyzing data from a few installed power meters, the installation cost is pretty low. As a result, it is applicable to millions of buildings. This work benefits both electricity companies and electricity customers. Another research topic occupancy prediction is to forecast when a house will be occupied. Since heating, venting, and air conditioner (HVAC) consumes the largest power usage at home, automatic operations of HVAC according to house occupancy are crucial for saving electricity without sacrificing the comfort of people in a building. By analysis, we can accurately predict whether a house will be occupied. The HVAC can be turned on and off based on the occupancy status of the building. By integrating this technique with an automatic HVAC device, any house installed with it can provide a more energy-efficient and comfortable environment. In conclusion, this research contributes to saving energy and protecting environment. | en |
| dc.description.degree | Ph. D. | en |
| dc.format.medium | ETD | en |
| dc.identifier.other | vt_gsexam:8974 | en |
| dc.identifier.uri | http://hdl.handle.net/10919/84349 | en |
| dc.publisher | Virginia Tech | en |
| dc.rights | In Copyright | en |
| dc.rights.uri | http://rightsstatements.org/vocab/InC/1.0/ | en |
| dc.subject | Data mining | en |
| dc.subject | Sustainability | en |
| dc.subject | Energy disaggregation | en |
| dc.subject | Occupancy prediction | en |
| dc.title | Temporal Mining Approaches for Smart Buildings Research | en |
| dc.type | Dissertation | en |
| thesis.degree.discipline | Computer Science and Applications | en |
| thesis.degree.grantor | Virginia Polytechnic Institute and State University | en |
| thesis.degree.level | doctoral | en |
| thesis.degree.name | Ph. D. | en |
Files
Original bundle
1 - 1 of 1