面向边缘光算力网络的上行链路资源协同调度算法OA北大核心
Uplink resource coordinated scheduling algorithm for edge-oriented optical computing power networks
为满足冷、热业务实时、高效的算力调度需求,提出一种基于自适应噪声完全集合经验模态分解(CEEMDAN)与时间卷积网络(TCN)的算力负载预测模型(简称C-TCN模型),并设计了基于C-TCN与Q学习的资源协同调度算法(CTQ算法),利用C-TCN模型提前感知下一时刻负载变化,通过Q学习协同调度波长与存储资源,寻找最佳波长划分与边缘存储分配方案.实验结果表明:CTQ算法的调度性能不仅优于现有调度算法,能满足冷、热业务调度性能要求,而且还能提高波长利用率.
In order to meet the real-time and efficient computing power scheduling requirements of hot and cold services,a com-putational load prediction model(abbreviated as C-TCN model)based on adaptive noise complete set empirical mode decompo-sition(CEEMDAN)and time convolutional network(TCN)is proposed,and a resource cooperative scheduling algorithm(CTQ algorithm)based on C-TCN and Q learning is designed.The C-TCN model is used to sense the load change at the next time in advance,and the optimal wavelength partitioning and edge storage allocation scheme is found through Q learning.The experi-mental results show that the CTQ algorithm not only has better scheduling performance than the existing scheduling algorithms,but also can meet the requirements of hot and cold service scheduling performance,and improve the wavelength utilization rate.
王蕴;林霄;楼芝兰;李军;孙卫强
福州大学物理与信息工程学院,福州 350116浙江财经大学数据科学学院,杭州 310018苏州大学江苏省新型光纤技术与通信网络工程研究中心,江苏苏州 215006上海交通大学区域光纤通信网与新型光通信系统国家重点实验室,上海 200240
电子信息工程
边缘光算力网络算力调度数据传输资源调度网络优化
edge optical computing power networkcomputing power schedulingdata transferresource schedulingnetwork optimization
《光通信技术》 2024 (003)
45-51 / 7
国家自然科学基金青年项目(批准号:61901118、12001483)资助;上海交通大学"区域光纤通信网与新型光通信系统国家重点实验室"开放基金(批准号:2023GZKF020)资助;江苏省新型光纤技术与通信网络工程研究中心开放研究课题(批准号:SDGC2232)资助.
评论