Ten Paper's repositories
drone-network-onos-and-mininet
[12] Prioritization Based Task Offloading in UAV-Assisted Edge Networks 作者:Kalinagac O, Gür G, Alagöz F. 出处:Sensors, 2023 摘要:在流量激增、覆盖问题和低延迟要求等苛刻的操作条件下,地面网络可能无法为用户和应用程序提供预期的服务水平。此外,当自然灾害或自然灾害发生时,现有网络基础设施可能崩溃,给服务区域的应急通信带来巨大挑战。为了在瞬态高服务负载情况下提供无线连接并促进容量提升,需要替代或辅助快速部署网络。由于其高机动性和灵活性,无人驾驶飞行器(UAV)网络非常适合此类需求。在这项工作中,我们考虑由配备无线接入点的无人机组成的边缘网络。这些软件定义的网络节点在边缘到云
MIMO-D2D
[4] A Power Allocation Scheme for MIMO-NOMA and D2D Vehicular Edge Computing Based on Decentralized DRL 作者:Long D, Wu Q, Fan Q, et al. 出处:Sensors 摘要:在车辆边缘计算(VEC)中,一些任务可以在本地或在基站(BS)或附近车辆的移动边缘计算(MEC)服务器上处理。事实上,任务是否卸载取决于车辆对基础设施(V2I)和车辆对车辆(V2V)通信的状态。在本文中,考虑了基于设备到设备(D2D)的V2V通信和基于多输入多输出和非正交多址(MIMO-NOMA)的V2I通信。在实际通信场景中,基于MIMO-NOMA的V2I通信信道条件不确定,任务到达随机,导致VE
UCMEC-mmWave-Fronthaul
Simulation code of our paper ''Towards Decentralized Task Offloading and Resource Allocation in User-Centric Mobile Edge Computing''
QoE_Offloading_DRL
QoE-Driven Task Offloading in Mobile Edge Computing with Deep Reinforcement Learning
Chengdu_BSs
The location of the base station in the city of Chengdu
Chengdu_Taxi_Track
Chengdu Taxi Track
DVRPSR_PPO
DRL for Dynamic Vehicle Routing Problem with stochastic customer requests
ML-RL-simulations
A multi-layer guided reinforcement learning-based tasks offloading in edge computing - Simulations
Deep-Reinforcment-Learning
This is the repository for the deep reinforcement learning in classic and novel wireless communication scnarios.
edge_simulation1
Designing a Deep Q-Learning Model with Edge-Level Training for Multi-Level Task Offloading in Edge Computing Networks
MDVO
Mean-field reinforcement learning for decentralized task offloading in vehicular edge computing
mec_morl_multipolicy
The python code for paper "Multi-objective Deep Reinforcement Learning for Mobile Edge Computing"
morl-baselines
Multi-Objective Reinforcement Learning algorithms implementations.
Safe-Policy-Optimization
This is a benchmark repository for safe reinforcement learning algorithms
UCMEC_env
Deep Reinforcement Learning Environments for User-Centric Mobile Edge Computing