交换以太网中实时消息截止期划分算法研究  被引量:2

Research on deadline partitioning schemes for real-time message transmission over switched Ethernet

在线阅读下载全文

作  者:檀明[1,2] 魏臻[2] 韩江洪[2] 

机构地区:[1]合肥学院网络与智能信息处理重点实验室,合肥230601 [2]合肥工业大学计算机与信息学院,合肥230009

出  处:《计算机应用研究》2012年第12期4714-4718,共5页Application Research of Computers

基  金:国家自然科学基金资助项目(60873003;60873195);安徽省教育厅自然科学一般项目(KJ2011B139)

摘  要:为解决交换式以太网中实时消息在发送及接收链路上的截止期划分问题,首先给出了非抢占式EDF调度算法的可调度性分析方法,并分析了消息的提前释放对非抢占式EDF调度算法可调度性的影响,在此基础上提出了新的截止期划分算法(MDPS)。算法通过计算可满足调度条件时消息在发送链路及接收链路截止期应该划分的下限,并结合截止期的松驰量实现实时消息在发送及接收链路上的截止期划分。算法实验比较和分析表明,该算法在提高网络聚合带宽、减小消息的错失率方面明显优于现有的ADPS算法。To solve the problem of dividing deadlines of real-time channels between the in and outgoing link to/from the switch when applying switched Ethernet in real-time industrial communications,this paper presented an improved feasibility analysis method for periodic real-time messages scheduled by non-preemptive EDF algorithm.In addition,the schedulability analysis of real-time periodic messages when instances of messages were early released was given and proved by using real-time scheduling theory.Particularly,based on an algorithm for calculating the minimum non-preemptive EDF-feasible deadline of real-time messages,it developed a novel scheme of asymmetrically dividing deadlines of real-time channels between the in and outgoing link to/from the switch(MDPS).By computing the minimum non-preemptive EDF-feasible deadline of real-time message on the in and outgoing link to/from the switch and combing the slack value of deadline,MDPS could optimize deadline partitioning of real-time channels between the in and outgoing link to/from the switch.The scheme was compared with ADPS.The simulations show that the MDPS performs better than the ADPS in terms of using the aggregated switch throughput and the missing rate of message.

关 键 词:交换式以太网 非抢占EDF调度算法 周期性实时消息 截止期划分方法 可调度性分析 

分 类 号:TP393[自动化与计算机技术—计算机应用技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象