R. Onvural, "Survey of closed queueingnetworks with blocking," ACM Computing Surveys. vol. 22, no. 2, pp. 83--121,June 1990.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....or transfer blocking in open queuing networks. Queuing networks with transfer blocking can be used in modeling communication, computer and manufacturing systems. For example, a disk to tape backup system or mass storage system can be modeled by a closed queuing network with transfer blocking [9]. The following is a good example for an open network with transfer blocking. Consider a FDMA cellular communication system with a set of channels allocated to each base station. Adjoining cells use different sets of channels to avoid adjacent channel interference. Typically, channel allocation is ....

Onvural. Survey of closed queueing networks with blocking. ACM Computing Surveys, 22(2):83--121, Jun 1980.

....network use primarily the following two kinds of blocking: 1. Type I: The upstream node i gets blocked if the service on a customer is completed but it cannot move downstream due to the queue at the downstream node j being full. This is sometimes referred to as Blocking After Service (BAS) [22]. 2. Type II: The upstream node is blocked when the downstream node becomes saturated and service must be suspended on the upstream customer regardless of whether service is completed or not. This is sometimes referred to as Blocking Before Service (BBS) 22] The Expansion Method uses Type I ....

....to as Blocking After Service (BAS) 22] 2. Type II: The upstream node is blocked when the downstream node becomes saturated and service must be suspended on the upstream customer regardless of whether service is completed or not. This is sometimes referred to as Blocking Before Service (BBS) [22]. The Expansion Method uses Type I blocking, which is prevalent in most production and manufacturing, trans DocNum 7 . 4. 0. 0 Networks, Bu er Allocation Problem typeset September 21, 2000 Smith Cruz Table 5: Comparison of pK Formulas K= 11 s 2 = 0.50 new M=M=1=K gelenbe optimal 0.10 ....

Onvural, Raif, 1990. \Survey of Closed Queueing Networks with Blocking," ACM Computing Surveys 22 (2), 83-121.

....its maximum capacity then the flow of customers from other service centers into this queue is stopped, and blocking occurs. Various blocking types have been defined and analyzed in the literature to represent distinct behaviors of real systems with limited resources (Akyildiz and Perros 1989, Onvural 1990, Perros 1994, Van Dijk 1991a, Van Dijk 1991b) Some comparisons and equivalences among blocking types have been presented for queueing networks with various network topologies in (Balsamo and De Nitto Person 1991, Balsamo and De Nitto Person 1994, Balsamo 1994, Onvural and Perros 1989a, Onvural ....

.... 1990, Perros 1994, Van Dijk 1991a, Van Dijk 1991b) Some comparisons and equivalences among blocking types have been presented for queueing networks with various network topologies in (Balsamo and De Nitto Person 1991, Balsamo and De Nitto Person 1994, Balsamo 1994, Onvural and Perros 1989a, Onvural 1990, Perros 1994, Van Dijk 1991a, Van Dijk 1991b) Exact analytical methods cannot be generally applied to analyze queueing networks with finite capacity queues, except for a few special cases, because of the synchronization constraints between the service centers of the network. Hence recourse to ....

[Article contains additional citation context not shown here]

Onvural, R.O. 1990. "Survey of Closed Queueing Networks with Blocking." ACM Computing Surveys, vol. 22, vo. 2: 83-121.

.... nite capacity queues are more appropriate models for systems with nite bu er and blocking, but their analysis is in general more complex than in nite capacity QNMs and it is often carried on with approximated techniques [15] This class of QNMs is referred to as Queueing networks with Blocking [2, 7, 8, 9, 10, 12, 15]. When a user tries to enter a saturated node, i.e. a node node whose queue has attained its maximum capacity, then there is a block. In the literature several proposals exist with respect to di erent types of blocking mechanisms. We just recall the Blocking After Service (BAS) mechanism that we ....

R. O. Onvural "Survey of Closed Queueing Networks with Blocking" ACM Computing Surveys, Vol. 22, No. 2, 83-121, June 1990.

....form. Introduction Queueing networks have been successfully used in modeling a variety of computer systems, communication networks, and manufacturing systems. They can efficiently be analyzed if they have a product form solution. In queueing networks with finite capacities, blocking occurs ([11, 12]) Only in special cases they have a product form solution ( 1] otherwise the analysis is difficult due to complexity. We investigate queueing network models with repetitive service blocking: If a job tries to enter a node, and there is no buffer space available, the job goes back to its former ....

R. O. Onvural. Survey of closed queueing networks with blocking. ACM Computing Surveys, 22(2):83--121, 1990.

....of processors. 3. 1 Measurements on a Small Scale Multiprocessor The application that we used is the solution of a sparse linear system by means of Successive Over Relaxation (SOR) The linear equations are the global balance equations [10] corresponding to a queueing network model with blocking [15]. The model itself consists of a number of service centers in series, each with a finite capacity queue. Such models are commonly used to evaluate the performance of communication networks built from switches with finite buffer space. The results for two models are presented here. Model A has a ....

Raif O. Onvural. Survey of closed queueing networks with blocking. ACM Computing Surveys, 22(2):83-- 121, June 1990.

....BS, DY, KR, P, R, SD] These networks are difficult to analyze, and even simple, intuitively obvious properties are hard to prove. For example, one expects that the throughput of a closed network will be higher if its finite buffers are replaced by infinite buffers, but this has not been proved [O]. We address this and related problems here in the case of tandem queues. Consider a network of first come first served queues in tandem. The queues may have finite or infinite buffers. If a finite buffer is full, the blocking scheme may be transfer blocking or service blocking. A transaction ....

....Consider a network of first come first served queues in tandem. The queues may have finite or infinite buffers. If a finite buffer is full, the blocking scheme may be transfer blocking or service blocking. A transaction processing system, for example, may have such a mix of blocking schemes [O]. For a given job, its service times at different servers may be correlated (as is the case for the transmission times of a message as it hops from node to node in a communication network [CP] We give a transient analysis that shows, for an open system, the response time of a job decreases if ....

[Article contains additional citation context not shown here]

R.O. Onvural, Survey of closed queueing networks with blocking, ACM Computing Surveys 22 (1990), 83--121.

....It is interesting to note that the effect of pure delay on server utilisation, and hence the related performance measures, will decrease as the source population increases. This is because, in some senses, open queueing systems represent an upper bound on the properties of closed queueing systems [99]. Given this property it is likely N w s q Processor 1 Processor 2 Processor K fl Server Delay fl = operating time = composite rate of requests w = total wait time q = time in queue s = time receiving service N = number in queue or receiving service Figure 4.11: Outline of the ....

....with full buffers will have differing effects on where this maximum occurs and on how the system behaves beyond this point. The inclusion of finite buffering in the model can take the solution of the system outside the product form solutions of the BCMP theorem, however work reported by Onvural [99] allows for the bounding of the performance of systems with finite buffer space. He also gives algorithms for the evaluation of the maximum performance point and reports that their practical use can yield results that are within 1 relative error of the exact results. The inclusion of finite ....

Raif O. Onvural. Survey of closed queueing networks with blocking. ACM Computing Surveys, 22(2):83--121, 1990.

....the source loop was manually transformed into its corresponding inspector and executor because we did not have compiler support for this conversion. 4. 2 Results We applied the SOR technique to solve the global balance equations [2] corresponding to a queueing network model with blocking [4]. The model itself consists of a number of service centers in series, each with a finite capacity queue. This sort of model is commonly used to evaluate the performance of communication networks built from switches with finite buffer space. Measurements were taken on a Sequent Symmetry shared ....

Raif O. Onvural. Survey of closed queueing networks with blocking. ACM Computing Surveys, 22(2):83--121, June 1990.

....this processor is solely dependent on which of the above conditions prevails. Under the assumption that there is no overhead in switching between clients there is no difference in the processor s observed request rate under any workpreserving scheduling policy. By reference to the BCMP theorem [2, 7] combined with the derived properties below, this leads to the following cohort probabilities: P i;j = population(C i )u i d j r j P 0;0 (4) where P 0;0 = 2 4 1 NM X i=1 i X j=0 population(C i )u i d j r j 3 5 Gamma1 (5) C n;1 Cn 1;1 C n;2 C n;0 Cn 1;0 ....

Raif O. Onvural. Survey of closed queueing networks with blocking. ACM Computing Surveys, 22(2):83--121, 1990.

....buffers. Service times of these components are assumed deterministic (fixed) Hence, they are modeled as M=D=1=L queueing centers (exponential arrival time, deterministic service time, single server and finite length buffer) A survey of queueing networks with blocking can be found in [12], and the detailed analysis of an M=D=1=L queue is reported in [13] Here, we directly state the results required for this study. Let be the arrival rate at a queueing center. The traffic intensity, ae, is equal to Delta d, where d is the service time. Let L be the buffer length. The ....

R. O. Onvural, "Survey of Closed Queueing Networks with Blocking," ACM Computing Surveys, pp. 83-121, June 1990.

No context found.

R. Onvural, "Survey of closed queueingnetworks with blocking," ACM Computing Surveys. vol. 22, no. 2, pp. 83--121,June 1990.

No context found.

R. O. Onvural. Survey of Closed Queueing Networks with Blocking. ACM Computing Surveys, 22(2):83--121, 1990.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC