Electrical and Computer Engineering ETDs

Publication Date

Fall 11-5-2021

Abstract

The emerging Smart City ecosystem consists of a vast edge network of Internet of Things (IoT) devices that continuously interact with mobile devices carried by its citizens. In this setting, the IoT infrastructure, apart from the main communications facilitator, acts as a crowdsourcing mechanism that collects massive amounts of user data, and can support public safety applications for the Smart City. In this thesis, we design and analyze learning mechanisms that extract intelligence from crowd interactions with the wireless IoT infrastructure, and optimize its energy efficiency while operating as a public safety network. First, we deploy a multi-story facility testbed and perform an extensive real-subject trial to gather user interactions with a realistic IoT infrastructure. The resulted BLEBeacon dataset is a collection of Bluetooth Low Energy (BLE) advertisement packets generated from BLE beacons carried by people following their daily routine. To aid fingerprinting localization services, instead of extensive offline measurements, we use the gathered unlabeled Received Signal Strength Indication (RSSI) samples to design a user localization and mobility tracking framework that relies on unsupervised learning.

Following that, we study the transformation of the Smart City's underlying IoT network (edge devices and user equipment) into a Public Safety Networks (PSN) able to provide resilient communications under disaster recovery scenarios. We first propose a heterogeneous device-to-device PSN framework that utilizes reinforcement learning to select the most appropriate wireless protocol, in terms of topology, protocol specifications, and battery-life extension. The framework also utilizes a coalition formation approach that considers social relations among devices, physical distance,and energy availability. Each device’s optimal transmission power is obtained through the formulation of a utility-based power control problem as a non-cooperative, distributed game among IoT devices, that converges to a unique Nash equilibrium. The second PSN framework we propose builds on this power management and combines Unmanned Areal Vehicle (UAV)-support with wireless powered communication (WPC) techniques to further improve energy efficiency. The IoT devices use reinforcement learning to form clusters and actively associate with a cluster-head. Towards extending the PSN’s lifetime, we utilize a harvest-transmit-store WPC mechanism, the UAV optimal positioning in the Euclidean 3D space is determined through an optimization problem of maximizing the coalition head’s total energy availability.

Finally, we propose an extensive form perfect information game to model interactions and optimal city resource allocations when a Terrorist Organization (TO) performs attacks on multiple targets across two conceptual Smart City (SC) levels, a physical, and a cyber-social. The Smart City Defense Game (SCDG) considers two SC agencies that have to defend their physical or social territories respectively, and fight against a common enemy, the TO. Each layer consists of multiple targets and the attack outcome depends on whether the resources allocated there by the associated agency, exceed or not the TO's. Each player's utility is equal to the number of successfully defended targets. The two agencies are allowed to make budget transfers provided that it is beneficial for both. We completely characterize the Sub-game Perfect Nash Equilibrium (SPNE) of the SCDG that consists of strategies for optimal resource exchanges between SC agencies and accounts for the TO's budget allocation across physical and cyber targets.

Keywords

Internet of Things, Public Safety, Smart City, Bluetooth, BLEBeacon Dataset

Document Type

Dissertation

Language

English

Degree Name

Computer Engineering

Level of Degree

Doctoral

Department Name

Electrical and Computer Engineering

First Committee Member (Chair)

Michael Devetsikiotis

Second Committee Member

Manel Martinez-Ramon

Third Committee Member

I. Safak Bayram

Fourth Committee Member

Ali Bidram

Fifth Committee Member

Ioannis Papapanagiotou

Download

Share

COinS