Open Access. Powered by Scholars. Published by Universities.®
- Discipline
Articles 1 - 4 of 4
Full-Text Articles in Engineering
Experience-Driven Control For Networking And Computing, Zhiyuan Xu
Experience-Driven Control For Networking And Computing, Zhiyuan Xu
Dissertations - ALL
Modern networking and computing systems have become very complicated and highly dynamic, which makes them hard to model, predict and control. In this thesis, we aim to study system control problems from a whole new perspective by leveraging emerging Deep Reinforcement Learning (DRL), to develop experience-driven model-free approaches, which enable a network or a device to learn the best way to control itself from its own experience (e.g., runtime statistics data) rather than from accurate mathematical models, just as a human learns a new skill (e.g., driving, swimming, etc). To demonstrate the feasibility and superiority of this experience-driven control design …
Experience-Driven Control For Networking And Computing, Zhiyuan Xu
Experience-Driven Control For Networking And Computing, Zhiyuan Xu
Dissertations - ALL
Modern networking and computing systems have become very complicated and highly dynamic, which makes them hard to model, predict and control. In this thesis, we aim to study system control problems from a whole new perspective by leveraging emerging Deep Reinforcement Learning (DRL), to develop experience-driven model-free approaches, which enable a network or a device to learn the best way to control itself from its own experience (e.g., runtime statistics data) rather than from accurate mathematical models, just as a human learns a new skill (e.g., driving, swimming, etc). To demonstrate the feasibility and superiority of this experience-driven control design …
Solving Process Planning And Scheduling Problems Using The Concept Of Maximum Weighted Independent Set, Kai Sun
Dissertations - ALL
Process planning and scheduling (PPS) is an essential and practical topic but a very intractable problem in manufacturing systems. Many research studies use iterative methods to solve such problems; however, they cannot achieve satisfactory results in both quality and computational speed. Other studies formulate scheduling problems as a graph coloring problem (GCP) or its extensions, but these formulations are limited to certain types of scheduling problems. In this dissertation, we propose a novel approach to formulate a general type of the PPS problem with resource allocation and process planning integrated towards a typical objective, minimizing the makespan. The PPS problem …
A Unified And Green Platform For Smartphone Sensing, Xiang Sheng
A Unified And Green Platform For Smartphone Sensing, Xiang Sheng
Dissertations - ALL
Smartphones have become key communication and entertainment devices in people's daily life. Sensors on (or attached to) smartphones can enable attractive sensing applications in different domains, including environmental monitoring, social networking, healthcare, transportation, etc. Most existing smartphone sensing systems are application-specific. How to leverage smartphones' sensing capability to make them become unified information providers for various applications has not yet been fully explored. This dissertation presents a unified and green platform for smartphone sensing, which has the following desirable features: 1) It can support various smartphone sensing applications; 2) It is personalizable; 2) It is energy-efficient; and 3) It can …