The Experts below are selected from a list of 360 Experts worldwide ranked by ideXlab platform
Herwig Bruneel - One of the best experts on this subject based on the ideXlab platform.
-
the impact of a global fcfs service discipline in a two class queue with dedicated servers
Computers & Operations Research, 2016Co-Authors: Willem Melange, Dieter Claeys, Bart Steyaert, Joris Walraevens, Herwig BruneelAbstract:This paper considers a continuous-time queueing model with two types (classes) of customers each having their own dedicated server. We assume that customers all queue together and are served in the order of arrival, regardless of the class they belong to. This global FCFS service discipline creates a blocking effect: if a customer of one type is in the front of the queue, the customers of the other type will not be able to pass it and start their service, even if their server is idle. We want to analyse this blocking effect in the current paper. To this end, two systems, one with and one without blocking effect, are analyzed and compared in terms of total and per-type system occupancy and customer delay. The motivation of our work is real systems where this kind of blocking is encountered, such as road junctions and security checkpoints. HighlightsWe studied a two-class, continuous-time queue with class-dedicated servers.Comparison between a system with a global and per-class FCFS service discipline.Distributions of the total and per-type system occupancies and customer delays.Uncovered the negative impact of a global FCFS service discipline.Well balanced system performs best when handling a high load.
-
a multi class discrete time queueing system under the fcfs service discipline
Annals of Operations Research, 2013Co-Authors: Sofian De Clercq, Koenraad Laevens, Bart Steyaert, Herwig BruneelAbstract:The problem with the FCFS server discipline in discrete-time queueing systems is that it doesn’t actually determine what happens if multiple customers enter the system at the same time, which in the discrete-time paradigm translates into ‘during the same time-slot’. In other words, it doesn’t specify in which order such customers are served. When we consider multiple types of customers, each requiring different service time distributions, the precise order of service even starts to affect quantities such as queue content and delays of arbitrary customers, so specifying this order will be prime. In this paper we study a multi-class discrete-time queueing system with a general independent arrival process and generally distributed service times. The service discipline is FCFS and customers entering during the same time-slot are served in random order. It will be our goal to search for the steady-state distribution of queue content and delays of certain types of customers. If one thinks of the time-slot as a continuous but bounded time period, the random order of service is equivalent to FCFS if different customers have different arrival epochs within this time-slot and if the arrival epochs are independent of customer class. For this reason we propose two distinct ways of analysing; one utilizing permutations, the other considering a slot as a bounded continuous time frame.
-
a two class discrete time queueing model with two dedicated servers and global fcfs service discipline
European Journal of Operational Research, 2012Co-Authors: Herwig Bruneel, Willem Melange, Dieter Claeys, Bart Steyaert, Joris WalraevensAbstract:This paper considers a simple discrete-time queueing model with two types (classes) of customers (types 1 and 2) each having their own dedicated server (servers A and B resp.). New customers enter the system according to a general independent arrival process, i.e., the total numbers of arrivals during consecutive time slots are i.i.d. random variables with arbitrary distribution. Service times are deterministically equal to 1 slot each. The system uses a “global FCFS” service discipline, i.e., all arriving customers are accommodated in one single FCFS queue, regardless of their types. As a consequence of the “global FCFS” rule, customers of one type may be blocked by customers of the other type, in that they may be unable to reach their dedicated server even at times when this server is idle, i.e., the system is basically non-workconserving. One major aim of the paper is to estimate the negative impact of this phenomenon on the queueing performance of the system, in terms of the achievable throughput, the system occupancy, the idle probability of each server and the delay. As it is clear that customers of different types hinder each other more as they tend to arrive in the system more clustered according to class, the degree of “class clustering” in the arrival process is explicitly modeled in the paper and its very direct impact on the performance measures is revealed. The motivation of our work are systems where this kind of blocking is encountered, such as input-queueing network switches or road splits.
-
discrete time models for communication systems including atm
1992Co-Authors: Herwig BruneelAbstract:Preface. 1: Independent Arrivals. 1.1 Discrete-Time Models and Applications. 1.2 Analysis of the GI-G-1 Model. 2: Scheduling Disciplines. 2.1 Single-Class Systems. 2.2 Multi-Class System. 2.3 Priority Disciplines. 2.4 Cyclic Services. 3: More Complicated Models. 3.1 Non-Independent Arrivals. 3.2 Server Interruptions. 4: Applications to ATM. 4.1 ATM Switching Elements and Networks. 4.2 ATM Multiplexer Models. Index.
Geoff Kuenning - One of the best experts on this subject based on the ideXlab platform.
-
paraid a gear shifting power aware raid
ACM Transactions on Storage, 2007Co-Authors: Charles Weddle, Mathew Oldham, Jin Qian, Ani Andy Wang, Peter Reiher, Geoff KuenningAbstract:Reducing power consumption for Server-Class computers is important, since increased energy usage causes more heat dissipation, greater cooling requirements, reduced computational density, and higher operating costs. For a typical data center, storage accounts for 27p of energy consumption. Conventional Server-Class RAIDs cannot easily reduce power because loads are balanced to use all disks, even for light loads. We have built the power-aware RAID (PARAID), which reduces energy use of commodity Server-Class disks without specialized hardware. PARAID uses a skewed striping pattern to adapt to the system load by varying the number of powered disks. By spinning disks down during light loads, PARAID can reduce power consumption, while still meeting performance demands, by matching the number of powered disks to the system load. Reliability is achieved by limiting disk power cycles and using different RAID encoding schemes. Based on our five-disk prototype, PARAID uses up to 34p less power than conventional RAIDs while achieving similar performance and reliability.
-
paraid a gear shifting power aware raid
File and Storage Technologies, 2007Co-Authors: Charles Weddle, Mathew Oldham, Jin Qian, Ani Andy Wang, Peter Reiher, Geoff KuenningAbstract:Reducing power consumption for server computers is important, since increased energy usage causes increased heat dissipation, greater cooling requirements, reduced computational density, and higher operating costs. For a typical data center, storage accounts for 27% of energy consumption. Conventional Server-Class RAIDs cannot easily reduce power because loads are balanced to use all disks even for light loads. We have built the Power-Aware RAID (PARAID), which reduces energy use of commodity Server-Class disks without specialized hardware. PARAID uses a skewed striping pattern to adapt to the system load by varying the number of powered disks. By spinning disks down during light loads, PARAID can reduce power consumption, while still meeting performance demands, by matching the number of powered disks to the system load. Reliability is achieved by limiting disk power cycles and using different RAID encoding schemes. Based on our five-disk prototype, PARAID uses up to 34% less power than conventional RAIDs, while achieving similar performance and reliability.
Joris Walraevens - One of the best experts on this subject based on the ideXlab platform.
-
the impact of a global fcfs service discipline in a two class queue with dedicated servers
Computers & Operations Research, 2016Co-Authors: Willem Melange, Dieter Claeys, Bart Steyaert, Joris Walraevens, Herwig BruneelAbstract:This paper considers a continuous-time queueing model with two types (classes) of customers each having their own dedicated server. We assume that customers all queue together and are served in the order of arrival, regardless of the class they belong to. This global FCFS service discipline creates a blocking effect: if a customer of one type is in the front of the queue, the customers of the other type will not be able to pass it and start their service, even if their server is idle. We want to analyse this blocking effect in the current paper. To this end, two systems, one with and one without blocking effect, are analyzed and compared in terms of total and per-type system occupancy and customer delay. The motivation of our work is real systems where this kind of blocking is encountered, such as road junctions and security checkpoints. HighlightsWe studied a two-class, continuous-time queue with class-dedicated servers.Comparison between a system with a global and per-class FCFS service discipline.Distributions of the total and per-type system occupancies and customer delays.Uncovered the negative impact of a global FCFS service discipline.Well balanced system performs best when handling a high load.
-
a two class discrete time queueing model with two dedicated servers and global fcfs service discipline
European Journal of Operational Research, 2012Co-Authors: Herwig Bruneel, Willem Melange, Dieter Claeys, Bart Steyaert, Joris WalraevensAbstract:This paper considers a simple discrete-time queueing model with two types (classes) of customers (types 1 and 2) each having their own dedicated server (servers A and B resp.). New customers enter the system according to a general independent arrival process, i.e., the total numbers of arrivals during consecutive time slots are i.i.d. random variables with arbitrary distribution. Service times are deterministically equal to 1 slot each. The system uses a “global FCFS” service discipline, i.e., all arriving customers are accommodated in one single FCFS queue, regardless of their types. As a consequence of the “global FCFS” rule, customers of one type may be blocked by customers of the other type, in that they may be unable to reach their dedicated server even at times when this server is idle, i.e., the system is basically non-workconserving. One major aim of the paper is to estimate the negative impact of this phenomenon on the queueing performance of the system, in terms of the achievable throughput, the system occupancy, the idle probability of each server and the delay. As it is clear that customers of different types hinder each other more as they tend to arrive in the system more clustered according to class, the degree of “class clustering” in the arrival process is explicitly modeled in the paper and its very direct impact on the performance measures is revealed. The motivation of our work are systems where this kind of blocking is encountered, such as input-queueing network switches or road splits.
Charles Weddle - One of the best experts on this subject based on the ideXlab platform.
-
paraid a gear shifting power aware raid
ACM Transactions on Storage, 2007Co-Authors: Charles Weddle, Mathew Oldham, Jin Qian, Ani Andy Wang, Peter Reiher, Geoff KuenningAbstract:Reducing power consumption for Server-Class computers is important, since increased energy usage causes more heat dissipation, greater cooling requirements, reduced computational density, and higher operating costs. For a typical data center, storage accounts for 27p of energy consumption. Conventional Server-Class RAIDs cannot easily reduce power because loads are balanced to use all disks, even for light loads. We have built the power-aware RAID (PARAID), which reduces energy use of commodity Server-Class disks without specialized hardware. PARAID uses a skewed striping pattern to adapt to the system load by varying the number of powered disks. By spinning disks down during light loads, PARAID can reduce power consumption, while still meeting performance demands, by matching the number of powered disks to the system load. Reliability is achieved by limiting disk power cycles and using different RAID encoding schemes. Based on our five-disk prototype, PARAID uses up to 34p less power than conventional RAIDs while achieving similar performance and reliability.
-
paraid a gear shifting power aware raid
File and Storage Technologies, 2007Co-Authors: Charles Weddle, Mathew Oldham, Jin Qian, Ani Andy Wang, Peter Reiher, Geoff KuenningAbstract:Reducing power consumption for server computers is important, since increased energy usage causes increased heat dissipation, greater cooling requirements, reduced computational density, and higher operating costs. For a typical data center, storage accounts for 27% of energy consumption. Conventional Server-Class RAIDs cannot easily reduce power because loads are balanced to use all disks even for light loads. We have built the Power-Aware RAID (PARAID), which reduces energy use of commodity Server-Class disks without specialized hardware. PARAID uses a skewed striping pattern to adapt to the system load by varying the number of powered disks. By spinning disks down during light loads, PARAID can reduce power consumption, while still meeting performance demands, by matching the number of powered disks to the system load. Reliability is achieved by limiting disk power cycles and using different RAID encoding schemes. Based on our five-disk prototype, PARAID uses up to 34% less power than conventional RAIDs, while achieving similar performance and reliability.
Samim Ghamami - One of the best experts on this subject based on the ideXlab platform.
-
dynamic scheduling of a two server parallel server system with complete resource pooling and reneging in heavy traffic asymptotic optimality of a two threshold policy
Mathematics of Operations Research, 2013Co-Authors: Samim Ghamami, Amy R WardAbstract:We consider a dynamic control problem for a parallel server system commonly known as the N-system. An N-system is a two-server parallel server system with two job classes, one server that can serve both classes, and one server that can only serve one class. We assume that jobs within each class arrive according to a renewal process. The random service time of a job has a general distribution that may depend on both the job's class and the server providing the service. Each job independently reneges, or abandons the queue without receiving service, if service does not begin within an exponentially distributed amount of time. The objective is to minimize the expected infinite horizon discounted cost of holding jobs in the system and having customers abandon, by dynamically scheduling waiting jobs to available servers. It is not possible to solve this control problem exactly, and so, we consider an asymptotic regime in which the system satisfies both a heavy traffic and a resource pooling condition. Then, we solve the limiting Brownian control problem, and interpret its solution as a policy in the original N-system. We label the servers and job classes so that server 1 can only serve class 1 and server 2 can serve both classes. The policy we propose has two thresholds. There is one threshold on the total number of jobs in the system, and one threshold on the number of class 1 jobs in the system. These thresholds are used to determine which job class server 2 should serve. We show that this proposed policy is asymptotically optimal within a specified class of admissible policies in the heavy traffic limit, and has the same limiting cost as the Brownian control problem solution.
-
dynamic scheduling of a two server parallel server system with complete resource pooling and reneging in heavy traffic asymptotic optimality of a two threshold policy
Social Science Research Network, 2013Co-Authors: Samim Ghamami, Amy R WardAbstract:We consider a dynamic control problem for a parallel server system commonly known as the N-system. An N-system is a two-server parallel server system with two job classes, one server that can serve both classes, and one server that can only serve one class. We assume that jobs within each class arrive according to a renewal process. The random service time of a job has a general distribution that may depend on both the job’s class and the server providing the service. Each job independently reneges, or abandons the queue without receiving service, if service does not begin within an exponentially distributed amount of time. The objective is to minimize the expected infinite horizon discounted cost of holding jobs in the system and having customers abandon, by dynamically scheduling waiting jobs to available servers. It is not possible to solve this control problem exactly, and so, we consider an asymptotic regime in which the system satisfies both a heavy traffic and a resource pooling condition. Then, we solve the limiting Brownian control problem, and interpret its solution as a policy in the original N-system. We label the servers and job classes so that server 1 can only serve class 1 and server 2 can serve both classes. The policy we propose has two thresholds. There is one threshold on the total number of jobs in the system, and one threshold on the number of class 1 jobs in the system. These thresholds are used to determine which job class server 2 should serve. We show that this proposed policy is asymptotically optimal in the heavy traffic limit, and has the same limiting cost as the Brownian control problem solution.
