Mobility-Aware Federated NOMA User Pairing with DBSCAN Clustering for Energy-Efficient IoT-Enabled VANETs
Abstract
The increasing density and mobility of IoT-enabled Vehicular Ad Hoc Networks (VANETs) create major challenges for energy-efficient wireless communication. Conventional orthogonal access mechanisms may lead to inefficient spectrum use, while centralized learning-based control may introduce excessive communication overhead and privacy concerns. This paper proposes a mobility-aware cross-layer framework for energy-efficient NOMA user pairing in IoT-enabled VANETs. The framework combines NOMA at the communication layer, DBSCAN-based clustering at the mobility-organization layer, and Federated Learning (FL) at the control layer. DBSCAN groups vehicles according to local mobility and spatial density, while FL enables distributed learning of energy-aware pairing decisions without centralizing raw vehicular data. The proposed pairing policy jointly considers channel-gain disparity, mobility stability, and battery awareness to select suitable intra-cluster NOMA pairs. The framework is implemented through an ns-3/Python co-simulation environment, where ns-3 models vehicular communication and mobility, while Python performs clustering and FL-based pairing decisions using Flower. Simulation results show that the proposed approach can substantially reduce transmission energy and improve energy efficiency compared with OMA and heuristic NOMA baselines under the adopted simulation assumptions. Limitations related to ideal SIC, channel estimation, and simplified mobility are discussed, and…
Read the paper
Related studies
- Active Learning during Federated Learning for Object Detection
- Fairness-aware federated learning
- Decentralized Federated Learning
- Building a Personally Identifiable Information Recognizer in a Privacy Preserved Manner Using Automated Annotation and Federated Learning
- Preservation of Patient Level Privacy: Federated Classification and Calibration Models
- Efficient explainable federated learning
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.