Semi-Decentralized Network Slicing for Reliable V2V Service Provisioning A Model-free Deep


When it comes to supporting new Vehicle-to-Vehicle (V2V) applications that have a variety of quality of service (QoS) requirements, the application of network slicing in vehicular networks becomes a paradigm that holds a lot of promise. However, achieving effective network slicing in dynamic vehicular Communications still faces many challenges, particularly time-varying traffic of Vehicle-to-Vehicle (V2V) services and the fast-changing network topology. We propose in this paper a semi-decentralized network slicing framework based on the C-V2X Mode-4 standard to provide customized network slices for a variety of vehicle-to-vehicle (V2V) services. This framework takes advantage of the widely deployed LTE infrastructures. The eNodeB (eNB) is able to infer the underlying network situation using only the long-term and partial information of vehicular networks. It can then intelligently adjust the configuration for each slice to ensure the long-term quality of service performance. Each vehicle has the ability to independently and decentralizedly select radio resources for its own V2V transmission, and this is made possible through the coordination of eNB. To be more specific, the slicing control at the eNB is achieved through the implementation of a model-free deep reinforcement learning (DRL) algorithm. This algorithm is a convergence of Long Short Term Memory (LSTM) and actor-critic DRL. In contrast to the algorithms that are currently in use for DRL, the one that has been proposed does not require any prior knowledge and does not assume there is any statistical model of vehicular networks. In addition, the results of the simulation demonstrate the efficiency of the intelligent network slicing scheme that we have proposed.

Did you like this research project?

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

PROJECT TITLE : AdaPool: A Diurnal-Adaptive Fleet Management Framework Using Model-Free Deep Reinforcement Learning and Change Point Detection ABSTRACT: In this paper, an adaptive model-free deep reinforcement approach is presented.
PROJECT TITLE : A Distributed Model-Free Algorithm for Multi-hop Ride-sharing using Deep Reinforcement Learning ABSTRACT: The proliferation of self-driving technology, ridesharing platforms, and autonomous vehicles will bring
PROJECT TITLE :Data-Driven Control for Interlinked AC/DC Micro grids Via Model-Free Adaptive Control and Dual-Droop Control - 2017ABSTRACT:This paper investigates the coordinated power sharing problems of interlinked ac/dc microgrids.
PROJECT TITLE :Alternatives No More: Wind and Solar Power Are Mainstays of a Clean, Reliable, Affordable GridABSTRACT:Wind and solar photovoltaic (PV) generation, no longer different energy sources, have grown rapidly within the
PROJECT TITLE :Model-Free Optimal Control for Affine Nonlinear Systems With Convergence AnalysisABSTRACT:In this paper, a self-learning management scheme is proposed for the infinite horizon optimal management of affine nonlinear

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

Project Enquiry