| 摘要: |
| 传统泵闸站系统采用的“端-主站”信息传输及处理体系容易导致网络堵塞以及时延的增加，而边缘计算可将泵闸站中大量实时的数据处理任务在终端或边缘端进行处理。分析了基于边缘计算的泵闸站数据处理任务分发机制，将其建模为混合整数非线性规划问题。为求解该问题，首先使用拉格朗日乘子法得到给定任务分发决策下的最佳计算资源分配，然后利用樽海鞘群算法（Salp Swarm Algorithm，SSA）得到优化计算资源下的任务分发决策，通过不断迭代寻找最优解。仿真结果表明，与其他算法相比，所提算法能有效减少任务处理总时延，提高泵闸站整体的性能。 |
| 关键词: 泵闸站数据处理 边缘计算 任务分发 樽海鞘群算法（SSA） |
| DOI：10.20079/j.issn.1001-893x.220523004 |
|
| 基金项目:江苏省水利科技项目(2020028)； 广东省水利科技创新项目(2020-04)；江苏省教育厅未来网络科研基金资助(FNSRFP-2021-YB-7)；南通市社会民生科技项目 (MS22021042) |
|
| Research on data processing task distribution mechanism of pump gate station based on edge computing |
| LI Xujie,ZANG Zhennan,SUN Ying,LIU Chunyan,HUANG Fengchen |
| (1.Institute of Ocean and Offshore Engineering,Hohai University(Nantong),Nantong 226300,China;
2.College of Computer and Information Technology Engineering,Hohai University,Nanjing 210098,China) |
| Abstract: |
| The end-master station information transmission and processing system applied in traditional pump gate system is easy to cause network congestion and delay increase，while edge computing can process a large amount of real-time data in pump gate station at terminal or edge end.In this paper,the task distribution scheme of pump gate data processing based on edge computing is analyzed and modeled as mixed integer nonlinear optimization problem.To solve this problem,the Lagrange multiplier method is used to obtain the optimal allocation of computing resources under the given task allocation decision at first.And then the Slap Swarm Algorithm(SSA) is used to obtain the task allocation decision under the optimized computing resources,and the optimal solution is found through continuous iteration.Simulation results show that compared with other algorithms,the proposed algorithm can effectively reduce the total delay of task processing and improve the overall performance of pump gate station. |
| Key words: pump gate station data processing edge computing task distributing slap swarm algorithm(SSA) |
