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.

Validation en temps réel des données hydrométriques

2003 ◽  
Vol 30 (1) ◽  
pp. 212-225
Author(s):  
Berrada Faouzi ◽  
Khalili Malika ◽  
Bennis Saad
Keyword(s):  
Kalman Filter ◽  
Real Time ◽  
Multiple Regression Equation ◽  
Variation Trend ◽  
Regressive Model ◽  
Analytical Redundancy ◽  
Optimal Resource ◽  
Auto Regressive ◽  
Optimal Resource Management ◽  
Auto Regressive Model

The managers of hydrological systems take real-time level and discharge measurements on several reservoirs and river reaches. The measurements are frequently tainted with errors that are reflected by uncertainties in decision making and by non-optimal resource management. This article aims at developing a methodology for the validation of levels in real-time. The proposed approach is based on material and analytical redundancy, and uses two models. The first one is spatial and enables linking of the measurements carried out at different stations with the help of a multiple regression equation. The second one is temporal, which enables the determination of variation trend at the different stations with the help of an auto-regressive model. These two models are incorporated into a diagnosis system for breakdowns based on a logic vote principle. Among the values that are measured and estimated by the linear regression model, the one which is the most consistent with the variation trend indicated by the auto-regressive model is selected. The Kalman filter is used to filter the measurements and identify the parameters of the models used in real-time. The proposed methodology turned out to be conclusive when applied to both measured data and synthetic hydrographs.Key words: validation, real-time, material redundancy, analytical redundancy, regressive, auto-regressive, Kalman filter.

Sign in / Sign up

Export Citation Format

Share Document