Abstract:
Network slicing in vehicular networks could support emerging Vehicle-to-Vehicle (V2V) applications with diverse QoS requirements. However, time-varying V2V traffic and fast-changing network topology make network slicing in dynamic vehicular communications difficult. This paper proposes a semi-decentralized network slicing framework based on the C-V2X Mode-4 standard to customize network slices for diverse V2V services using LTE infrastructures. eNodeB (eNB) can infer the underlying network situation and intelligently adjust the slice configuration to ensure long-term QoS performance using only long-term and partial vehicular network information. eNB coordinates each vehicle’s decentralized V2V radio resource selection. A model-free deep reinforcement learning (DRL) algorithm that converges Long Short Term Memory (LSTM) and actor-critic DRL controls eNB slicing. Unlike other DRL algorithms, the proposed DRL does not require prior knowledge or a statistical model of vehicular networks. Simulations prove our intelligent network slicing scheme works.
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
