Difference between revisions of "Resource:Seminar"
From MobiNetS
| Line 5: | Line 5: | ||
}} | }} | ||
===Latest=== | |||
{{Latest_seminar | {{Latest_seminar | ||
|confname=Topic | |confname=Topic | ||
| Line 22: | Line 23: | ||
}} | }} | ||
=== History === | |||
[[Resource:Previous_Seminars|Link to Previous seminars]]. | |||
<!-- | <!-- | ||
{{Resource:Previous_Seminars}} | {{Resource:Previous_Seminars}} | ||
--!> | --!> | ||
Revision as of 09:27, 8 June 2021
Time: 2021-06-09 16:00
Address: Main Building B1-612
The reading list could be found here. Schedules are here. Previous seminars can be found here.
Latest
- [Topic] Path Reconstruction in Wireless Network, Luwei Fu
- Abstract: This talk is about to expand the recent advances in path reconstruction in wireless networks and my thoughts on dynamic wireless networks with uncertain topologies.
- [INFOCOM'2021] Mobility- and Load-Adaptive Controller Placement and Assignment in LEO Satellite Networks, Linyuanqi Zhang
- Abstract: Software-defined networking (SDN) based LEO satellite networks can make full use of satellite resources through flexible function configuration and efficient resource management of controllers. Consequently, controllers have to be carefully deployed based on dynamical topology and time-varying workload. However, existing work on controller placement and assignment is not applicable to LEO satellite networks with highly dynamic topology and randomly fluctuating load. In this paper, we first formulate the adaptive controller placement and assignment (ACPA) problem and prove its NP-hardness. Then, we propose the control relation graph (CRG) to quantitatively capture the control overhead in LEO satellite networks. Next, we propose the CRG-based controller placement and assignment (CCPA) algorithm with a bounded approximation ratio. Finally, using the predicted topology and estimated traffic load, a lookahead-based improvement algorithm is designed to further decrease the overall management costs. Extensive emulation results demonstrate that the CCPA algorithm outperforms related schemes in terms of response time and load balancing.