Revenue-Optimal Auction For Resource Allocation in Wireless Virtualization: A Deep Learning Approach


Virtualization of wireless networks has emerged as an essential component of future cellular networks. These networks will be able to support multiple virtualized wireless networks for a variety of mobile virtual network operators (MVNOs) despite sharing the same physical infrastructure. In wireless virtualization, resource allocation is one of the most challenging issues, and auctioning approaches have been used extensively to solve this problem. Due to the ease with which it can be accomplished, however, the goal of the vast majority of existing auction-based allocation schemes is to maximize social welfare (also known as the sum of all valuations achieved by winning bidders). In spite of this, MVNOs are more concerned with increasing their own revenue as much as possible (i.e., received payments from auction winners). The revenue-optimal auction problem, on the other hand, is significantly more difficult to solve given that the payment price cannot be determined in advance of the calculation. In this paper, our objective is to develop a revenue-optimal auction mechanism for allocating resources in wireless virtualization environments. In light of the difficulty, "Deep Learning" strategies are put into practice. To be more specific, we build a multi-layer feed-forward neural network on the basis of an analysis of the best possible auction design. The bids placed by users are used as input into the neural network, and the allocation rule and conditional payment rule for users are the outputs of the neural network. The mechanism for holding auctions that has been suggested has a number of advantageous properties, such as individual rationality, incentive compatibility, and budget constraint, to name a few. In conclusion, the results of the simulation illustrate how successful the proposed strategy is. In contrast to optimization-based schemes and second-price auction-based schemes, the proposed scheme has the potential to boost revenue by an average of ten and thirty percent, depending on the number of MVNOs involved in the scenario.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here

PROJECT TITLE : CNN-LSTM: Hybrid Deep Neural Network for Network Intrusion Detection System ABSTRACT: The importance of network security to our day-to-day interactions and networks cannot be overstated. The importance of having
PROJECT TITLE : Traffic Anomaly Detection in Wireless Sensor Networks Based on Principal Component Analysis and Deep Convolution Neural Network ABSTRACT: Because of the proliferation of wireless networks, wireless sensor networks
PROJECT TITLE : Traffic Signal Control Using End-to-End Off-Policy Deep Reinforcement Learning ABSTRACT: However, road intersections have historically been among the most significant traffic bottlenecks that have contributed
PROJECT TITLE : Spatio-Contextual Deep Network Based Multimodal Pedestrian Detection For Autonomous Driving ABSTRACT: The most important component of an autonomous driving system is the module that is responsible for pedestrian
PROJECT TITLE : SWNet A Deep Learning Based Approach for Splashed Water Detection on Road ABSTRACT: Unfavorable weather conditions pose a significant risk to the public's safety on the roads, and this is especially true during

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry