Mobile Edge Computing for Future Internet-of-Things
- Publication Type:
- Thesis
- Issue Date:
- 2020
Open Access
Copyright Clearance Process
- Recently Added
- In Progress
- Open Access
This item is open access.
Integrating sensors, the Internet, and wireless systems, Internet-of-Things (IoT) provides a new paradigm of ubiquitous connectivity and pervasive intelligence. The key enabling technology underlying IoT is mobile edge computing (MEC), which is anticipated to realize and reap the promising benefits of IoT applications by placing various cloud resources, such as computing and storage resources closer to smart devices and objects. Challenges of designing efficient and scalable MEC platforms for future IoT arise from the physical limitations of computing and battery resources of IoT devices, heterogeneity of computing and wireless communication capabilities of IoT networks, large volume of data arrivals and massive number connections, and large-scale data storage and delivery across the edge network. To address these challenges, this thesis proposes four efficient and scalable task offloading and cooperative caching approaches are proposed.
Firstly, for the multi-user single-cell MEC scenario, the base station (BS) can only have outdated knowledge of IoT device channel conditions due to the time-varying nature of practical wireless channels. To this end, a hybrid learning approach is proposed to optimize the real-time local processing and predictive computation offloading decisions in a distributed manner.
Secondly, for the multi-user multi-cell MEC scenario, an energy-efficient resource management approach is developed based on distributed online learning to tackle the heterogeneity of computing and wireless transmission capabilities of edge servers and IoT devices. The proposed approach optimizes the decisions on task offloading, processing, and result delivery between edge servers and IoT devices to minimize the time-average energy consumption of MEC.
Thirdly, for the computing resource allocation under large-scale network, a distributed online collaborative computing approach is proposed based on Lyapunov optimization for data analysis in IoT application to minimize the time-average energy consumption of network.
Finally, for the storage resource allocation under large-scale network, a distributed IoT data delivery approach based on online learning is proposed for caching application in mobile applications. A new profitable cooperative region is established for every IoT data request admitted at an edge server, to avoid invalid request dispatching.
Please use this identifier to cite or link to this item: