Towards Intelligent Computation Offloading in Dynamic Vehicular Networks: A Scalable Multilayer Pipeline

• URL: http://arxiv.org/abs/2604.26416v1
• Date: Wed, 29 Apr 2026 08:27:35 GMT
• Title: Towards Intelligent Computation Offloading in Dynamic Vehicular Networks: A Scalable Multilayer Pipeline
• Abstract summary: Software Defined Vehicles face an increasing computational gap as advanced algorithms and frequent software updates demand more processing power while onboard hardware remains static.<n>This mismatch threatens the performance of safety-critical functions including driver-assistance systems and real-time perception tasks.<n>We propose a novel four-layer offloading pipeline that dynamically distributes vehicular functions to cloud and edge resources while meeting strict Round Trip Time constraints.
• Score: 0.3324986723090369
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Software Defined Vehicles face an increasing computational gap as advanced algorithms and frequent software updates demand more processing power while onboard hardware remains static throughout a vehicle's 10+ year lifespan. This mismatch threatens the performance of safety-critical functions including advanced driver-assistance systems and real-time perception tasks. We propose a novel four-layer computation offloading pipeline that dynamically distributes vehicular functions to cloud and edge resources while meeting strict Round Trip Time constraints. Our key contribution is an enhanced Particle Swarm Optimization algorithm that integrates distance- and direction-based penalties with functional requirements to optimize edge server selection for mobile vehicles. Evaluation using a Kubernetes-based cloud infrastructure with realistic vehicular mobility patterns demonstrates that our approach reduces average response time compared to conventional Brute-Force methods while maintaining the success rate for latency-critical tasks. The modified Particle Swarm Optimization algorithm achieves an average execution time of 26 ms across ten servers and tasks on Central Processing Unit, and 550ms across 15 servers with 1000 tasks on Graphics Processing Unit. These results confirm the pipeline's effectiveness in bridging the computational gap for next-generation Software Defined Vehicles (SDV).

Related papers

• A Neural Network Based Teleoperation for Remote Controlled Vehicles [98.38733381483934]
  Direct teleoperation of vehicles faces critical technical bottlenecks.<n> communication latency and the operator's inability to physically perceive unmodeled environmental disturbances.<n>We propose a tailored unilateral teleoperation framework.
  arXiv  Detail & Related papers  (2026-08-11T01:51:08Z)
• An Agentic AI Framework with Large Language Models and Chain-of-Thought for UAV-Assisted Logistics Scheduling with Mobile Edge Computing [47.615329461292504]
  In cloud manufacturing, unmanned aerial vehicles (UAVs) can support both product collection and mobile edge computing (MEC)<n>In this paper, we propose an agentic-AI-assisted optimization framework with two components.<n>First, we develop an agentic AI that combines large language models, retrieval-augmented generation, and chain-of-thought reasoning to translate user input into an interpretable mathematical formulation for the hybrid scheduling problem.
  arXiv  Detail & Related papers  (2026-05-13T09:13:19Z)
• CSGO: Generalized Optimization for Cold Start in Wireless Collaborative Edge LLM Systems [62.24576366776727]
  We propose a latency-aware scheduling framework to minimize total inference latency.<n>We show that the proposed method significantly reduces cold-start latency compared to baseline strategies.
  arXiv  Detail & Related papers  (2025-08-15T07:49:22Z)
• Computation Pre-Offloading for MEC-Enabled Vehicular Networks via Trajectory Prediction [38.493882483362135]
  We present a Trajectory Prediction-based Pre-offloading Decision (TPPD) algorithm for analyzing the historical trajectories of vehicles. We devise a dynamic resource allocation algorithm using a Double Deep Q-Network (DDQN) that enables the edge server to minimize task processing delay.
  arXiv  Detail & Related papers  (2024-09-26T09:46:43Z)
• DNN Partitioning, Task Offloading, and Resource Allocation in Dynamic Vehicular Networks: A Lyapunov-Guided Diffusion-Based Reinforcement Learning Approach [49.56404236394601]
  We formulate the problem of joint DNN partitioning, task offloading, and resource allocation in Vehicular Edge Computing. Our objective is to minimize the DNN-based task completion time while guaranteeing the system stability over time. We propose a Multi-Agent Diffusion-based Deep Reinforcement Learning (MAD2RL) algorithm, incorporating the innovative use of diffusion models.
  arXiv  Detail & Related papers  (2024-06-11T06:31:03Z)
• V2N Service Scaling with Deep Reinforcement Learning [0.0]
  We employ Deep Reinforcement Learning (DRL) for vertical scaling in Edge computing to support vehicular-to-network communications. We show that DDPG outperforms existing solutions, reducing the average number of active CPUs by 23% while increasing the long-term reward by 24%.
  arXiv  Detail & Related papers  (2023-01-30T23:13:18Z)
• Teal: Learning-Accelerated Optimization of WAN Traffic Engineering [68.7863363109948]
  We present Teal, a learning-based TE algorithm that leverages the parallel processing power of GPUs to accelerate TE control. To reduce the problem scale and make learning tractable, Teal employs a multi-agent reinforcement learning (RL) algorithm to independently allocate each traffic demand. Compared with other TE acceleration schemes, Teal satisfies 6--32% more traffic demand and yields 197--625x speedups.
  arXiv  Detail & Related papers  (2022-10-25T04:46:30Z)
• Dynamic Unicast-Multicast Scheduling for Age-Optimal Information Dissemination in Vehicular Networks [10.934800950965336]
  In a vehicular network, a roadside unit (RSU) provides timely updates about a set of physical processes to vehicles. A framework is proposed to optimize the decisions to unicast, multicast, broadcast, or not transmit updates to vehicles.
  arXiv  Detail & Related papers  (2022-09-19T16:04:49Z)
• QoS-SLA-Aware Artificial Intelligence Adaptive Genetic Algorithm for Multi-Request Offloading in Integrated Edge-Cloud Computing System for the Internet of Vehicles [14.978000952939404]
  Internet of Vehicles (IoV) over Vehicular Ad-hoc Networks (VANETS) is an emerging technology enabling the development of smart cities applications for safer, efficient, and pleasant travel. Considering vehicles limited computational and storage capabilities, applications requests are offloaded into an integrated edge-cloud computing system. This paper proposes a novel Artificial Intelligence (AI) deadline-SLA-aware genetic algorithm (GA) for multi-request offloading in a heterogeneous edge-cloud computing system.
  arXiv  Detail & Related papers  (2022-01-21T10:11:55Z)
• A Deep Value-network Based Approach for Multi-Driver Order Dispatching [55.36656442934531]
  We propose a deep reinforcement learning based solution for order dispatching. We conduct large scale online A/B tests on DiDi's ride-dispatching platform. Results show that CVNet consistently outperforms other recently proposed dispatching methods.
  arXiv  Detail & Related papers  (2021-06-08T16:27:04Z)
• Multi-Exit Semantic Segmentation Networks [78.44441236864057]
  We propose a framework for converting state-of-the-art segmentation models to MESS networks. specially trained CNNs that employ parametrised early exits along their depth to save during inference on easier samples. We co-optimise the number, placement and architecture of the attached segmentation heads, along with the exit policy, to adapt to the device capabilities and application-specific requirements.
  arXiv  Detail & Related papers  (2021-06-07T11:37:03Z)
• Computation Offloading in Heterogeneous Vehicular Edge Networks: On-line and Off-policy Bandit Solutions [30.606518785629046]
  In a fast-varying vehicular environment, the latency in offloading arises as a result of network congestion. We propose an on-line algorithm and an off-policy learning algorithm based on bandit theory. We show that the proposed solutions adapt to the traffic changes of the network by selecting the least congested network.
  arXiv  Detail & Related papers  (2020-08-14T11:48:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.