Modeling and analysis of response time in vehicular networks using Markov chains

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: April 14, 2025

The rapid growth of vehicular networks has led to the emergence delay-sensitive software such as automatic driving and navigation. Vehicles with limited resources cannot provide required service quality reduce processing delay, which is a bottleneck in development vehicle networks. In this study, we utilize Mobile Edge Computing (MEC) offload certain time-critical operations servers located on roadsides. This approach, coupled network intelligence, enhances capability mobile nodes consequently, results decrease response time latency. With mathematical modeling traffic networks, made it possible for stakeholders field without need simulate their ideas, just by placing desired values introduced model, suitable picture changes related getting your idea net. experiment, using data state-of-the-art calculated average modeling. output our work shows relatively similar time, indicating that have achieved close those obtained from other expensive time-consuming methods approach presented, consider an accomplishment paper.

Language: Английский

---

Deep Reinforcement Learning-Based Task Offloading and Load Balancing for Vehicular Edge Computing

Electronics, Journal Year: 2024, Volume and Issue: 13(8), P. 1511 - 1511

Published: April 16, 2024

Vehicular edge computing (VEC) effectively reduces the computational burden on vehicles by offloading tasks from resource-constrained to nodes. However, non-uniformly distributed a large number of cause load imbalance problems among nodes, resulting in performance degradation. In this paper, we propose deep reinforcement learning-based decision scheme for task and balancing with optimization objective minimizing system cost considering split dynamics First, model mutual interaction between mobile Mobile Edge Computing (MEC) servers using Markov process. Second, optimal task-offloading resource allocation is obtained utilizing twin delayed deterministic policy gradient algorithm (TD3), server achieved through collaboration selection based technique order preference similarity ideal solution (TOPSIS). Finally, have conducted extensive simulation experiments compared results several other baseline schemes. The proposed can more reduce increase utilization.

Language: Английский

---

Double deep Q-network-based dynamic offloading decision-making for mobile edge computing with regular hexagonal deployment structure of servers

Applied Soft Computing, Journal Year: 2024, Volume and Issue: 169, P. 112594 - 112594

Published: Dec. 9, 2024

Language: Английский

---

Congestion Management Using K-Means for Mobile Edge Computing 5G System

Wireless Personal Communications, Journal Year: 2024, Volume and Issue: 136(4), P. 2105 - 2124

Published: June 1, 2024

Language: Английский

---