Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

IoT-driven scheduling of residential HVAC and virtual bus lanes for energy savings

Petrov, Daniel (2021) IoT-driven scheduling of residential HVAC and virtual bus lanes for energy savings. Doctoral Dissertation, University of Pittsburgh. (Unpublished)

[img]
Preview
PDF
Submitted Version

Download (21MB) | Preview

Abstract

The availability of commodity Internet connection and the decrease in price and form factor of consumer electronics led to the emergence of Internet of Things (IoT), with which our world becomes more connected and instrumented. IoT is a great vehicle for enabling solutions to problems in the connected environment that surrounds us (i.e., smart homes and smart cities). An example is the use of sensors and IoT to address issues related to energy efficiency, the broad area of this dissertation.
Our hypothesis is that data processing and decision making need to be carried out at the network edge, specifically as close to the physical system as possible, where data are generated and used, to produce results in real-time and make sure the data is not exposed to privacy and security risks. To this end, we propose to leverage scheduling principles and statistical techniques in the context of two applications, namely aiming to reduce duty cycle of HVAC (Heating, Ventilation, and Air Conditioning) systems in smart homes and to mitigate road congestion in smart cities. The common goal in these two aims is the reduction of energy consumption and the reduction of atmospheric pollution.
To achieve our first aim we propose intelligent scheduling of the duty cycles of HVAC systems in residential buildings. Our solution combines linear and polynomial regression enabled estimator that drives the calculations about the amounts of time thermally conditioned air should be supplied to each room. The output from our estimator is fed into our scheduler based on integer linear programming to decrease the duty cycle of the home's HVAC systems. We evaluate the effectiveness and efficiency of our HVAC solution with a
dataset collected from several residential houses in the state of Pennsylvania.
To achieve the second aim, we propose the concept of virtual bus lanes, that combines on-demand creation of bus lanes with dynamic control of traffic lights. Moreover, we propose to guide drivers through less congested routes using light boards that provide to drivers information in real-time for such routes. Our methods are anchored to priority scheduling, incremental windowed-based aggregation, and shortest path first Dijkstra's algorithm. We evaluate the effectiveness and efficiency of our virtual bus lanes solution with a real dataset from the city of Beijing, China, and a synthetic traffic scenario from the city of Luxembourg.


Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: University of Pittsburgh ETD
Status: Unpublished
Creators/Authors:
CreatorsEmailPitt UsernameORCID
Petrov, Danieldpp14@Pitt.edudpp14
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Committee ChairChrysanthis, Panospanos@pitt.edupanos0000-0001-7189-9816
Committee CoChairMosse, Danielmosse@pitt.edumosse0000-0002-9508-9815
Committee MemberLabrinidis, Alexandroslabrinid@pitt.edulabrinid
Committee MemberZadorozny, Vladimirviz@pitt.eduviz0000-0001-6420-1926
Date: 8 September 2021
Date Type: Publication
Defense Date: 29 April 2021
Approval Date: 8 September 2021
Submission Date: 2 August 2021
Access Restriction: No restriction; Release the ETD for access worldwide immediately.
Number of Pages: 158
Institution: University of Pittsburgh
Schools and Programs: School of Computing and Information > Computer Science
Degree: PhD - Doctor of Philosophy
Thesis Type: Doctoral Dissertation
Refereed: Yes
Uncontrolled Keywords: IoT, scheduling, HVAC, transportation, energy, savings
Date Deposited: 08 Sep 2021 13:22
Last Modified: 08 Sep 2021 13:22
URI: http://d-scholarship.pitt.edu/id/eprint/41528

Metrics

Monthly Views for the past 3 years

Plum Analytics


Actions (login required)

View Item View Item