| 引用本文： |
-
陈怡航,杨守义,郝万明,等.基于轨迹预测的D2D辅助边缘计算资源分配和卸载策略[J].电讯技术，2026，66（2）： - . [点击复制]
- CHEN Yihang,YANG Shouyi,HAO Wanming,et al.Trajectory Prediction Based Resource Allocation and Offloading Strategy for D2D-assisted Edge Computing[J].，2026，66（2）： - . [点击复制]
|
|
| 摘要: |
| 任务卸载和资源分配是移动边缘计算(Mobile Edge Computing，MEC)中两个密不可分的问题，但移动用户位置和任务需求的动态变化给系统任务卸载和资源分配带来了新的挑战。为进一步提升用户体验质量，建立支持设备到设备(Device-to-Device，D2D)协作的多用户多任务场景，在利用无迹卡尔曼滤波预测用户轨迹的基础上提出系统成本最小化卸载算法TP-CMOA，采用遗传算法和潜在博弈论实现任务卸载策略和资源分配策略的联合优化。仿真结果表明所提算法优于其他基准算法。 |
| 关键词: 移动边缘计算 设备到设备协作 轨迹预测 资源分配 |
| DOI：10.20079/j.issn.1001-893x.240705003 |
|
| 基金项目:国家自然科学基金资助项目（62101499）；国家重点研发计划项目（2019YFB1803200） |
|
| Trajectory Prediction Based Resource Allocation and Offloading Strategy for D2D-assisted Edge Computing |
| CHEN Yihang,YANG Shouyi,HAO Wanming,HAN Haojin |
| (School of Information Engineering，Zhengzhou University，Zhengzhou 450001，China) |
| Abstract: |
| Task offloading and resource allocation are two inextricably linked issues in mobile edge computing(MEC)，but the dynamic changes in mobile user location and task requirements bring new challenges to system task offloading and resource allocation.In order to enhance further the quality of user experience and build multi-user multitasking scenarios that support device-to-device(D2D) collaboration，a system cost-minimizing offloading algorithm(TP-CMOA) based on predicting the user trajectory by using unscented Kalman filtering is proposed，and a genetic algorithm and potential game theory are adopted to realize the joint optimization of task offloading strategy and resource allocation strategy.Simulation results show that the proposed algorithm outperforms other benchmark algorithms. |
| Key words: mobile edge computing D2D collaboration trajectory prediction resource allocation |
《电讯技术》编辑部 