| Start Date: | 12/5/2013 | Start Time: | 9:00 AM |
| End Date: | 12/5/2013 | End Time: | 11:00 AM |
|
Event Description
Title: Online Learning for Adaptive Wireless Systems
Advisor: Dr. Kapil Dandekar
Date: Thursday, December 5, 2013
Time: 9:00 a.m.
Location: MSE Conference Room 348, 3rd Floor, LeBow Engineering Center
Abstract
The promise of cognitive radio as a disruptive technology innovation for future wireless networks has motivated the research community for over a decade now. Cognitive radios are proposed to be fully programmable adaptive wireless devices having the capability to sense their environment and dynamically adapt their operational state. There are however differing definitions of cognitive radio based on the defining features proposed by different researchers.
In this proposal, we focus our attention on the role antenna systems, RF agility and related propagation issues play in enabling an adaptive wireless system. Specifically, this work proposes to develop algorithms for learning and controlling the operational state of a reconfigurable antenna system tightly integrated with a cognitive radio. With the introduction of reconfigurable antennas, there was a departure from the notion that a wireless device has no control over the wireless channel. Reconfigurable antenna systems are capable of operating under multiple states which provide multiple channels, potentially providing an opportunity to select a state for optimizing a communication link and/or a network state. This comes with an overhead to acquire information about the state of all the channels, a need for a strategy to select the optimal state and most importantly an ability to learn the changes in the channel state in order to adapt.
With these goals in mind, we utilize online learning based on multi-armed bandit theory to design algorithms to control and adapt the state of a reconfigurable antenna system. We investigate the trade-off between the amount and the frequency with which the channel state information is collected and its effect on the system performance. We will first demonstrate the effectiveness of a sequential learning algorithm to select an optimal antenna state for single user noise-limited wireless systems similar to 802.11x WiFi systems. Further, we will propose online learning algorithms for a distributed multi-user network for enhancing interference management techniques. For both these network settings, we will also analyze the cost of learning under unknown statistical model of the channel and compare it with the oracle with full prior knowledge. We will also seek to characterize the performance of proposed algorithms for mobile wireless channels where the statistical model of the link quality metrics derived from the channel information, change of over time. Finally, we will leverage the software defined radio platform to experimentally evaluate the useful of these algorithms in real-world scenarios. |
|
Location:
MSE Conference Room 348, 3rd Floor, LeBow Engineering Center |
Audience:
Current StudentsFacultyStaff |
|
