scholarly journals Inter-Machine Exchange of Real Time in Distributed Computer Systems

2020 ◽  
pp. short50-1-short50-8
Author(s):  
Vladimir Bogatyrev ◽  
Stanislav Bogatyrev ◽  
Anatoly Bogatyrev
Keyword(s):  
Real Time ◽  
Analytical Model ◽  
Waiting Time ◽  
Computer Systems ◽  
Delivery Time ◽  
Network Nodes ◽  
Average Waiting Time ◽  
Service Delays ◽  
Distributed Computer Systems

The possibilities of increasing the likelihood of timely service and reducing the average waiting time for requests for inter-machine exchange in distributed real-time computer systems are investigated. The analyzed effect is achieved as a result of redundant multi-way transmissions of packets that are critical to delays, which provide for the replication of transmitted packets with the task for each replica of the path (route) of the sequential passage of network nodes. The condition for the timeliness of the reserved transmissions is that the accumulated waiting in the queues of the nodes making up the path, at least for one of the replicas, does not exceed the maximum permissible time. An analytical model is proposed for estimating the average delays of multi-path redundant transmissions, when determined by the average delivery time of the first of the replicas transmitted in different ways. For requests critical to service delays, the influence of the frequency of reservation (replication) of requests on the probability of their timely service and the average waiting time accumulated at the nodes of the path for the replica delivered first was analyzed.

scholarly journals Scheduling Schemes in Dynamic Multilevel Packet Scheduling in WSN

2019 ◽  
Vol 8 (2) ◽  
pp. 3800-3804
Keyword(s):  
Real Time ◽  
Waiting Time ◽  
Packet Scheduling ◽  
Turnaround Time ◽  
Priority Level ◽  
Average Waiting Time ◽  
Level 3 ◽  
Overall Performance ◽  
The Individual ◽  
Priority Levels

As focusing on the scheduling schemes, there are many scheduling schemes for multilevel. So the paper is concentrating to compare the scheduling schemes and producing the average waiting time and turnaround time. If it is minimized then the overall performance may shoot up. In this paper comparison is done between three scheduling schemes Enhanced Dynamic Multilevel Packet scheduling (EDMP), Circular Wait Dynamic Multilevel Packet scheduling (CW-DMP) and Starvation-Free Dynamic Multilevel Packet scheduling (SF-DMP). In all the above schemes there are three priority levels say priority level 1(Pr1), priority level 2(Pr2) and priority level 3(Pr3). Pr1 will comprise the real time tasks, Pr2 containing the non real time remote tasks and non real time local tasks are there in Pr3. In each and every scheme, each and every priority level will be using the individual scheduling technique to schedule the tasks. Also the comparison is done based on waiting time and the turnaround time of the task thereby the average waiting time and the average turnaround time are calculated.

scholarly journals The Timeliness of the Reserved Service in the Cluster with the Regulation of the Time of Destruction of Overdue Requests in the Node Queues

2021 ◽  
Author(s):  
Vladimir Bogatyrev ◽  
Stanislav Bogatyrev ◽  
Anatoly Bogatyrev
Keyword(s):  
Distributed Computing ◽  
Real Time ◽  
Distributed Control ◽  
Waiting Time ◽  
Significant Influence ◽  
Queuing Systems ◽  
Time Limits ◽  
Average Waiting Time ◽  
Insufficient Time ◽  
Maximum Allowable Time

With the increasing complexity of distributed control tasks based on their intellectualization, there are problems of insufficient time and computing resources for functioning in real time. In this regard, there is a need to develop methods for organizing distributed real-time computer systems, based on the consolidation of distributed computing resources with their integration into clusters. The possibilities of increasing the probability of timely servicing of waiting- critical requests in the cluster as a result of query replication and controlling the time of destruction of potentially expired replicas in node queues are investigated. The cluster is represented as a group of queuing systems with infinite queues with a limited average waiting time. The effectiveness of the reserved service of a real-time request is determined by the probability of executing at least one of the generated copies of the request in the maximum allowable time without losing it due to errors and waiting time limits in the queues of cluster nodes. It is shown that there is an optimal multiplicity of query replication with a significant influence of the choice of restrictions on the waiting time for requests in queues before they are destroyed.

scholarly journals Multipath Redundant Real-Time Transmission with the Destruction of Expired Packets in Intermediate Nodes

2021 ◽  
Author(s):  
Vladimir Bogatyrev ◽  
Stanislav Bogatyrev ◽  
Anatoly Bogatyrev
Keyword(s):  
Real Time ◽  
Waiting Time ◽  
Data Transmission ◽  
Single Channel ◽  
Packet Transmission ◽  
Total Delay ◽  
Network Nodes ◽  
Time Operation ◽  
Real Time Operation ◽  
The Given

The possibilities of increasing the probability of timely service and reducing the average waiting time for requests for machine-to-machine exchange in distributed computer systems are investigated. Improving the reliability, timeliness and error-free transmission in automated distributed control systems focused on intelligent and cognitive methods of data and image analysis is fundamental in their real-time operation. The effect is achieved as a result of the reserved multipath transfers of packets critical to delays, at which their replication is provided with a task for each replica of the path (route) of sequential passage of network nodes. An analytical model is proposed for estimating the probability of timely delivery and the average total waiting time in the queues of route nodes with reserved and non-reserved packet transmission. The communication nodes that make up the data transmission route are represented by single-channel queuing systems with an infinite queue. The influence of the multiplicity of redundancy (replication) of transmissions on the probability of their timely maintenance is analyzed. The condition for the success of reserved transfers is that the accumulated total waiting in the queues of nodes that make up the path for at least one of the replicas of the packet should not exceed the given maximum allowed time. The efficiency of destroying expired packets in the intermediate nodes that make up the data transmission paths is shown. The existence of an optimal redundancy multiplicity critical to the total delay in the queues of packets is shown.

Real-Time Distributed Computer Systems

1981 ◽  
pp. 39-82 ◽  
Author(s):  
W.R. Franta ◽  
E. Douglas Jensen ◽  
R.Y. Kain ◽  
George D. Marshall
Keyword(s):  
Real Time ◽  
Computer Systems ◽  
Distributed Computer Systems

Load Sharing in Soft Real-Time Distributed Computer Systems

1987 ◽  
Vol C-36 (8) ◽  
pp. 993-1000 ◽  
Author(s):  
James F. Kurose ◽  
Renu Chipalkatti
Keyword(s):  
Real Time ◽  
Computer Systems ◽  
Load Sharing ◽  
Distributed Computer Systems
Sign in / Sign up

Export Citation Format

Share Document