Abstract:
Future cellular networks will offer multiple virtualized wireless networks for different mobile virtual network operators (MVNOs) on the same physical infrastructure. Auctions have been widely used for wireless virtualization resource allocation.
Due to its simplicity, most auction-based allocation schemes maximize social welfare (the sum of all winning bidder valuations). In reality, MVNOs want to maximize their auction winner payments. Due to the unknown payment price, the revenue-optimal auction problem is more difficult.
This project proposes a revenue-optimal auction for wireless virtualization resource allocation. Complexity necessitates deep learning. We build a multi-layer feed-forward neural network from optimal auction design analysis.
The neural network outputs users’ allocation and conditional payment rules from bids. Individual rationality, incentive compatibility, and budget constraint are desirable properties of the auction mechanism.
Simulations prove the scheme works. For single and multi-MVNO cases, the proposed scheme increases revenue by 10 and 30%, respectively, compared to second-price auction and optimization-based schemes.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
