PPO-Based Hybrid Optimization for RIS-Assisted Semantic Vehicular Edge Computing

Wei Feng; Jingbo Zhang; Qiong Wu; Pingyi Fan; Qiang Fan

cs.LGMar 10, 2026

PPO-Based Hybrid Optimization for RIS-Assisted Semantic Vehicular Edge Computing

Authors: Wei Feng, Jingbo Zhang, Qiong Wu, Pingyi Fan, Qiang Fan

Organizations: School of Internet of Things Engineering, Jiangnan University, Wuxi 214122, China · State Key Laboratory of Space Network and Communications, Beijing National Research Center for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing 100084, China · Qualcomm, San Jose, CA 95110, USA

Abstract

To support latency-sensitive Internet of Vehicles (IoV) applications amidst dynamic environments and intermittent links, this paper proposes a Reconfigurable Intelligent Surface (RIS)-aided semantic-aware Vehicle Edge Computing (VEC) framework. This approach integrates RIS to optimize wireless connectivity and semantic communication to minimize latency by transmitting semantic features. We formulate a comprehensive joint optimization problem by optimizing offloading ratios, the number of semantic symbols, and RIS phase shifts. Considering the problem's high dimensionality and non-convexity, we propose a two-tier hybrid scheme that employs Proximal Policy Optimization (PPO) for discrete decision-making and Linear Programming (LP) for offloading optimization. {The simulation results have validated the proposed framework's superiority over existing methods. Specifically, the proposed PPO-based hybrid optimization scheme reduces the average end-to-end latency by approximately 40% to 50% compared to Genetic Algorithm (GA) and Quantum-behaved Particle Swarm Optimization (QPSO). Moreover, the system demonstrates strong scalability by maintaining low latency even in congested scenarios with up to 30 vehicles.

Figures & tables

Figure 1: Framework of semantic communication system.

Parameters	Value	Parameters	Value
$\eta_{r,j}$	2.2	$p_{k,j}$	0.2 W
$N$	$6\times 6$	$\sigma^{2}$	$1.44\times 10^{-10}$ W
$K$	15	$\eta_{k,j}$	3.5
$\eta_{k,r}$	2.2	$W$	360 kHz
$C$	1000 cycles/bit	$I_{k}$	100
$f_{k}^{\text{loc}}$	2 GHz	$F^{\text{RSU}}$	6 GHz

Table 1: Simulation environment parameter table.

Figure 3: Reward convergence plot of PPO.

Figure 4: Performance comparison of average delay under varying vehicle transmission powers.

Figure 5: Average delay of V2V and V2I links versus vehicle transmission power.

Figure 6: Boxplot of average delay under different numbers of vehicles.

Figure 7: Average delay versus number of vehicles.

Figure 8: Average delay versus number of RIS-reflecting elements.

Figure 9: Boxplot of total delay under different numbers of RIS-reflecting elements.

Computation Offloading

See all 15 papers

Heterogeneous Tasks Offloading in Vehicular Edge Computing: A Federated Meta Deep Reinforcement Learning Approach
May 18, 2026Yaorong Huang, Jingtao Luo, Xuechao WangFederated RL Edge Computing
∗The Hong Kong University of Science and Technology (Guangzhou) · †Chengdu Neusoft University
Latency-aware Human-in-the-Loop Reinforcement Learning for Semantic Communications
Feb 17, 2026Peizheng Li, Xinyi Lin, Adnan AijazSemantic Communication Task-Oriented Semantic Communication
Bristol Research and Innovation Laboratory, Toshiba Europe Ltd., U.K.
Low-Latency Relay Selection in NR-V2X Vehicular Communications via Graph Isomorphism Networks with Edge Features
Jul 15, 2026Giambattista Amati, Federica Mangiatordi, Emiliano Pallotti +3Mixed-Integer Linear Programming Learning to Optimize
Fondazione Ugo Bordoni (FUB) Rome, Italy · University of Rome Tor Vergata (UniRoma2) Rome, Italy

May 18, 2026J/K move · Enter open · S save

Heterogeneous Tasks Offloading in Vehicular Edge Computing: A Federated Meta Deep Reinforcement Learning Approach

Yaorong Huang, Jingtao Luo, Xuechao Wang

∗The Hong Kong University of Science and Technology (Guangzhou) · †Chengdu Neusoft University

Federated RL Edge Computing Combinatorial Optimization Heterogeneous Computing Meta-Reinforcement Learning

Open paper AskPDF arXiv

Vehicular edge computing (VEC) enables latency-sensitive vehicular applications by offloading computation-intensive tasks to nearby edge servers. However, real-world vehicular workloads are typically modeled as heterogeneous directed acyclic graph (DAG) tasks with complex dependency structures, making joint offloading and resource allocation highly challenging. Moreover, distributed MEC deployment raises privacy concerns when collaboratively training learning-based policies. In this paper, we propose a Federated Meta Deep Reinforcement Learning framework with GAT-Seq2Seq modeling (FedMAGS) for heterogeneous task offloading in VEC systems. The proposed approach leverages Graph Attention Networks to capture DAG dependencies, a Seq2Seq-based policy to generate structured offloading decisions, and federated meta-learning to enable fast adaptation across distributed MEC servers without sharing raw data. Extensive simulations demonstrate that FedMAGS achieves faster convergence, lower execution delay, and better scalability compared with state-of-the-art baselines. In addition, the federated design preserves data privacy while reducing communication overhead, making the framework well suited for dynamic and large-scale VEC environments.

Abstract

Computation Offloading

Explore similar work

Heterogeneous Tasks Offloading in Vehicular Edge Computing: A Federated Meta Deep Reinforcement Learning Approach

Latency-aware Human-in-the-Loop Reinforcement Learning for Semantic Communications

Low-Latency Relay Selection in NR-V2X Vehicular Communications via Graph Isomorphism Networks with Edge Features