Task offloading mechanism based on federated reinforcement learning in mobile edge computing
Task offloading mechanism based on federated reinforcement learning in mobile edge computing
复制标题
移动边缘计算中基于联邦强化学习的任务卸载机制
DOI：
10.1016/j.dcan.2022.04.006
复制
发表时间：
2022-04
影响因子：
7.9
通讯作者：
Shijian Ni
中科院分区：
文献类型：
--
作者：
Jie Li;Zhiping Yang;Xingwei Wang;Yichao Xia;Shijian Ni
随着5G的到来，对延迟敏感的应用变得越来越多样化。移动边缘计算（MEC）技术具有高带宽、低时延、低能耗等特点，备受研究者关注。为了提高服务质量 (QoS)，本研究重点关注 MEC 中的计算卸载。我们从计算成本、维度灾难、用户隐私和新用户的灾难性遗忘的角度来考虑服务质量。 QoS模型是基于延迟和能耗建立的，并且基于DDQN和MEC中的联邦学习（FL）自适应任务卸载算法。该算法结合QoS模型和深度强化学习算法，根据信道相干时间内本地链路和节点状态信息获得最优分流策略，解决传输信道时变问题，降低计算能耗和任务处理延迟。为了解决隐私和灾难性遗忘问题，我们利用FL分布式利用多个用户的数据来获取决策模型，保护数据隐私并提高模型的通用性。在FL迭代过程中，个别设备的通信延迟过大，影响整体延迟成本。因此，我们采用基于一元异常值检测机制的通信延迟优化算法来降低FL的通信延迟。仿真结果表明，与现有方案相比，该方法显着降低了设备上的计算成本，提高了处理复杂任务时的服务质量。
With the arrival of 5G, latency-sensitive applications are becoming increasingly diverse. Mobile Edge Computing (MEC) technology has the characteristics of high bandwidth, low latency and low energy consumption, and has attracted much attention among researchers. To improve the Quality of Service (QoS), this study focuses on computation offloading in MEC. We consider the QoS from the perspective of computational cost, dimensional disaster, user privacy and catastrophic forgetting of new users. The QoS model is established based on the delay and energy consumption and is based on DDQN and a Federated Learning (FL) adaptive task offloading algorithm in MEC. The proposed algorithm combines the QoS model and deep reinforcement learning algorithm to obtain an optimal offloading policy according to the local link and node state information in the channel coherence time to address the problem of time-varying transmission channels and reduce the computing energy consumption and task processing delay. To solve the problems of privacy and catastrophic forgetting, we use FL to make distributed use of multiple users’ data to obtain the decision model, protect data privacy and improve the model universality. In the process of FL iteration, the communication delay of individual devices is too large, which affects the overall delay cost. Therefore, we adopt a communication delay optimization algorithm based on the unary outlier detection mechanism to reduce the communication delay of FL. The simulation results indicate that compared with existing schemes, the proposed method significantly reduces the computation cost on a device and improves the QoS when handling complex tasks.
登录
查看更多内容
多接入边缘计算中具有可靠性和延迟要求的节能卸载快速算法
影响因子：
3.9
作者：
Liu Haolin;Cao Le;Pei Tingrui;Deng Qingyong;Zhu Jiang
通讯作者：
Zhu Jiang
DOI：
10.1145/2307849.2307858
发表时间：
2012-06
期刊：
--
影响因子：
--
作者：
Tim Verbelen;P. Simoens;F. de Turck;B. Dhoedt
通讯作者：
Tim Verbelen;P. Simoens;F. de Turck;B. Dhoedt
DOI：
10.1109/infocom.2018.8486305
发表时间：
2018-04
期刊：
IEEE INFOCOM 2018 - IEEE Conference on Computer Communications
影响因子：
--
作者：
S. Sundar;B. Liang
通讯作者：
S. Sundar;B. Liang
影响因子：
11.2
作者：
Bockelmann, Carsten;Pratas, Nuno;Dekorsy, Armin
通讯作者：
Dekorsy, Armin
DOI：
10.1109/icassp.2018.8462686
发表时间：
2018-04
期刊：
2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
影响因子：
--
作者：
Haoqi Li;Naveen Kumar;Ruxin Chen;P. Georgiou
通讯作者：
Haoqi Li;Naveen Kumar;Ruxin Chen;P. Georgiou