Authors

Tao GongFollow

Date of Completion

3-9-2020

Embargo Period

3-9-2020

Keywords

Real-time wireless networks, Internet-of-Things, disturbances, lossy links, dynamic packet scheduling, reliability, distributed and reliable packet scheduling

Major Advisor

Song Han

Associate Advisor

Bing Wang

Associate Advisor

Shengli Zhou

Field of Study

Computer Science and Engineering

Degree

Doctor of Philosophy

Open Access

Open Access

Abstract

Along with the rapid development of real-time wireless network (RTWN) technologies in a wide range of time- and safety-critical industrial applications, packet scheduling algorithms have been playing a critical role in RTWNs to achieve desired Quality of Service (QoS) for real-time sensing and control, especially in the presence of unexpected disturbances. Most existing solutions focus on communication schedule construction to meet the desired QoS but have common assumptions that all wireless links are reliable, and the network topologies are prior known. Although these assumptions simplify the algorithm design and analysis, they are not realistic in real world.

To relax the assumption on the perfect network links, we propose RD-PaS, a reliable dynamic packet scheduling framework for RTWNs, to guarantee the QoS in lossy wireless environments. RD-PaS can not only construct static schedules to meet the timing and reliability requirements of packet transmissions for a given periodic network traffic pattern, but also construct new schedules to handle increased traffic induced by unexpected disturbances while minimizing the impact on existing traffic. Given that RD-PaS relies on a central controller to make schedule change decisions, we further propose FD-PaS to support distributed schedule change which leads to a faster response time and does not require a central controller. FD-PaS allows the involved nodes to make schedule change decisions immediately upon the detection of the disturbances.

We continue to improve the QoS in large-scale RTWNs where the network topologies could be dynamic in the runtime. RD-PaS and FD-PaS cannot be applied as they require static network topology. A randomized scheduler has been implemented to construct baseline communication schedules. However, such scheduler suffers from high latency for packet transmissions. To reduce the latency, the network schedule needs to be adjusted according to the formed topology, which leads to numerous schedule update messages. To reduce such overhead, we propose a partition-based scheduler by reserving network bandwidth for topology changes and making efficient schedule adjustment.

RD-PaS, FD-PaS and the partition-based schedulers are all implemented on RTWN testbeds for evaluation. Our results show that these algorithms improve the latency, schedulability, and scalability in their RTWN applications.

Download
COinS