Abstract: We consider the following queuing system which arises as a model of a wireless link shared by multiple users. There is a finite number N of input flows served by a server. The system operates in discrete time t = 0,1,2,…. Each input flow can be described as an irreducible countable Markov chain; waiting customers of each flow are placed in a queue. The sequence of server states m(t), t = 0,1,2,…, is a Markov chain with finite number of states M. When the server is in state m, it can serve mim customers of flow i (in one time slot).The scheduling discipline is a rule that in each time slot chooses the flow to serve based on the server state and the state of the queues. Our main result is that a simple online scheduling discipline, Modified Largest Weighted Delay First, along with its generalizations, is throughput optimal; namely, it ensures that the queues are stable as long as the vector of average arrival rates is within the system maximum stability region.

Abstract: A software application for recommending workforce resource allocation in a communication center based on requirements of events represented in a communication-center queue has a first interface for accessing information from the queue; a second interface for accessing information from a data source about workforce availability and state information; a processing component for processing queue information and workforce information; and a message generation and delivery component for generating a workforce allocation recommendation based on processing results and sending the recommendation to a target entity. In a preferred embodiment, the application periodically accesses the queue and the data source to obtain the most recent information for processing and generates periodic recommendations based on real-time requirements of events and availability states of resources, the recommendations sent ahead of time before the resources are required.

Abstract: First-in-first-out (FIFO) queues are among the most fundamental and highly studied concurrent data structures. The most effective and practical dynamic-memory concurrent queue implementation in the literature is the lock-free FIFO queue algorithm of Michael and Scott, included in the standard Java TM Concurrency Package.

Abstract: Current end-to-end Internet congestion control under tail-drop (TD) queue management experiences performance degradations such as multiple packet losses, high queueing delay and low link utilization. In this paper, we review recently proposed active queue management (AQM) algorithms for supporting end-to-end transmission control protocol (TCP) congestion control. We focus recently developed control theoretic design and analysis method for the AQM based TCP congestion control dynamics. In this context, we analyze the problems of existing AQM proposals in which congestion is detected and controlled reactively based on current and/or past congestion. Then we argue that AQM based TCP congestion control should be adaptive to the dynamically changing traffic situation in order to detect, control and avoid the current and the incipient congestion proactively. Finally, we survey two adaptive and proactive AQM algorithms, PID-controller and Pro-Active Queue Management (PAQM), designed using classical proportional-integral---derivative (PID) feedback control to overcome the reactive congestion control dynamics of existing AQM algorithms. A comparative study of these AQM algorithms with existing AQM algorithms is given. A simulation study under a wide range of realistic traffic conditions suggests that PID-controller and PAQM outperform other AQM algorithms such as random early detection (RED) [Floyd and Jacobson, 18] and proportional-integral (PI) controller [Hollot et al., 24].

Abstract: A communication system is provided in which a client device can communicate with a server via any one of plural communication networks, such as a WWAN, a WLAN, a wired LAN, a personal area network (e.g., Bluetooth), and any other networking architecture. More specifically, the communication client comprises a connection manager that is adapted to determine availability of each the plural communication networks to communicate data between the client and the server, select one of the communication networks from the available ones of the plural communication networks in accordance with predetermined preferences, and establish a connection with the selected one of the communication networks. The client may further comprise a client application. The connection manager provides a notification message to the client application upon establishment of the communication link. The client application then communicates data to and from the server via the selected one of the communication networks. In an alternative embodiment of the invention, the communication system further includes an intelligent queuing system, comprising a client-side queue on the communication client and a server-side queue on the server. The connection manager is further adapted to determine cost associated with communicating the data on available ones of the plural communication networks and provide that information to the client-side queue. The client-side queue determines whether to communicate the data via the selected one of the communication networks based in part on the determined cost.

Abstract: A method for selecting a queue for service across a shared link. The method includes classifying each queue from a group of queues within a plurality of ingresses into one tier of a number 'N' of tiers. The number 'N' is greater than or equal to 2. Information about allocated bandwidth is used to classify at least some of the queues into the tiers. Each tier is assigned a different priority. The method also includes matching queues to available egresses by matching queues classified within tiers with higher priorities before matching queues classified within tiers with lower priorities.

Abstract: Setting packet queue priority is disclosed. A rate associated with a packet queue is measured. The rate is compared to a quality of service metric. A priority is assigned to the packet queue based at least in part on the comparison between the rate and the quality of service metric. The quality of service metric may be a committed information rate and/or a peak information rate.

Abstract: Mathematical models of congestion control capture the congestion indication mechanism at the router in two different ways: rate-based models, where the queue-length at the router does not explicitly appear in the model, and queue-based models, where the queue length at the router is explicitly a part of the model. Even though most congestion indication mechanisms use the queue length to compute the packet marking or dropping probability to indicate congestion, we argue that, depending upon the choice of the parameters of the AQM scheme, one would obtain a rate-based model or a rate-and-queue-based model as the deterministic limit of a stochastic system with a large number of users. We also consider the impact of implementing AQM schemes in the real queue or a virtual queue. If an AQM scheme is implemented in a real queue, we show that, to ensure that the queuing delays are negligible compared to RTTs, one is forced to choose the parameters of a AQM scheme in a manner which yields a rate-based deterministic model. On the other hand, if the AQM scheme is implemented in a virtual queue, small-queue operation is achieved independent of the choice of the parameters, thus showing a robustness property of virtual queue-based schemes.

Abstract: A system and method for buffering messages between at least two applications over a network implementing a Quality of Service (QoS) framework. Messages are transmitted from a source application to an intermediary message queue for message buffering. A message queue QoS is imparted at the message queue to the flow of the messages traversing the message queue, and the end-to-end QoS can then be provided for the flow of messages over the network.

Abstract: We study a basic problem in Multi-Queue switches. A switch connects m input ports to a single output port. Each input port is equipped with an incoming FIFO queue with bounded capacity B. A switch serves its input queues by transmitting packets arriving at these queues, one packet per time unit. Since the arrival rate can be higher than the transmission rate and each queue has limited capacity, packet loss may occur as a result of insufficient queue space. The goal is to maximize the number of transmitted packets. This general scenario models most current networks (e.g., IP networks) which only support a “best effort” service in which all packet streams are treated equally. A 2-competitive algorithm for this problem was designed in [4] for arbitrary B. Recently, a \(\frac{17}{9}\approx 1.89\)-competitive algorithm was presented for B>1 in [2]. Our main result in this paper shows that for B which is not too small our algorithm can do better than 1.89, and approach a competitive ratio of \(\frac{e}{e-1}\approx 1.58\).

Abstract: Contacts are managed within a contact centre by representing each contact as a software object which contains skillset and priority identifiers. Contact objects are queued relative to one another by means of references to and/or from the object(s) immediately ahead of and behind each contact. In this way a conventional queue can be dispensed with. Queries can be made to a plurality of contact centres across a network to identify objects matching certain criteria at the top of each local queue. In this way a set of local queues substitutes for a network queue providing increased resilience in the case of the failure of any individual component of the network or of the network itself.

Abstract: Industrial equipment is monitored by at least one industrial controller assigned to each group of industrial equipment. Queues are established by logic within one of the industrial controllers for each group. Each queue holds a number of event records. Logic is established in each industrial controller for storing an indication of a detected event associated with a time stamp as an event record in a queue. A group computer is interconnected with each industrial controller in the group. A scan rate is established for each queue in that group. Event records are read from each queue based on the scan rate for that queue. The event records for all queues in a group are accumulated by the group computer and forwarded to a server. The group computer may dynamically set the scan rate and/or the queue length for each queue based on records read from the queue.

Abstract: A notification system method is disclosed for alerting subscribers to a status of their rental queues. The system includes a number of components that interoperate to improve a subscriber's experience, including an intelligent queue monitor which works on his/her behalf to ensure that an adequate and interesting list of titles are brought to the attention of subscribers.

Abstract: A method of managing critical resource usage comprises monitoring queue depth in at least one critical resource queue for a high level of resource consumption and preventing subsequent commands of a client/server combination in response to a command that increases resource consumption to the high level. The method further comprises queuing an identifier of the client/server combination on a waiting queue, removing the client/server combination identifier from the waiting queue in queuing order as resource consumption declines, and enabling commands of the client/server combination.

Abstract: An apparatus for and method of enforcing precedence of committed traffic over excess traffic that overcomes the difficulty in supporting committed over excess traffic and has particular application to distributed queuing systems. Queue control messages are generated and transmitted to other line cards to guarantee that committed traffic is not dropped when sent from multiple sources such as line interface cards to a single destination. When the level of a queue exceeds a threshold and flow control is received for the corresponding destination, the queue starts dropping excess traffic and messages indicating the queue status are sent to all other lines cards. When a line card receives a queue control message that another line card started dropping excess traffic to a specific destination, it also starts dropping excess traffic to that destination as well.

Abstract: We present a quality of service (QoS) architecture for supporting real-time data transmission in mobile ad hoc networks (MANETs). The QoS architecture includes a QoS transport layer, QoS routing, queue management and a priority MAC protocol. Through simulations, we find that the QoS architecture reduces packet delay and greatly improves the quality of real-time video streams in MANETs.

Abstract: The TCP end-to-end congestion control plus RED router queue management can be modeled as a discrete-time dynamical system, which may create complex bifurcating and chaotic behavior. Based on the basic features of the TCP-RED model, we propose a time-dependent delayed feedback control algorithm to control chaos in the system by perturbing the accessible RED parameter pmax. This method is able to stabilized a router queue occupancy at a level without knowing the exact knowledge of the network. Further, we study the situation of the presence of the UDP traffic.

Abstract: It is quite common to adopt a static approach or computer simulation method for the performance estimation of the Automated Storage/Retrieval System (AS/RS). In most research, the authors assume that the storage/retrieval machine performs only either single command or dual command at each operation and, in addition, the type of request is known in advance, which is not adequate in the real system. In this paper, we propose a stochastic approach for the performance estimation of a unit-load AS/RS by using an M/G/1 queuing model with a single server and two queues. In particular, the steady state probability distribution of the number of storage and retrieval commands waiting in the queues is obtained in the form of transform. According to the computational comparison with the simulation, the proposed approach gives satisfactory results with very high accuracy.

Abstract: Routing system for defining an alternate channel routing mechanism in a messaging middleware system wherein messages are transmitted through a transmission network (14) from a source application (10) to a destination application by means of message queues. The messages which are put by the source application in a transmission queue (20) are sent over a primary channel through the transmission network. The messages are received in a reception queue from which they are got by the destination application. This system comprises a finite-state machine (52) for receiving from an event queue (44) the channel events relating to the primary channel as activating inputs and providing actions to be taken for each channel event, one of these actions being to route messages on an alternate channel when the primary channel has failed.

Abstract: Router queues can impact both round-trip times and throughput. Yet little is publicly known about queue provisioning employed by Internet services providers for the routers that control the access links to home computers. This paper proposes QFind, a black-box measurement technique, as a simple method to approximate the size of the access queue at last mile router. We evaluate QFind through simulation, emulation, and measurement. Although precise access queue results are limited by receiver window sizes and other system events, we find there are distinct difference between DSL and cable access queue sizes.

Abstract: Multi-server queuing analysis can be used to estimate average wait times and queue lengths at toll and parking exit plazas given arrival rates, number of servers, and service rates. These queuing models approximate the performance of queuing systems with multiple queues. While the queuing equations are useful where there are multiple servers, they do not fully reflect the operation of a toll plaza where vehicles can stack in multiple queues and can change lanes. To gain an understanding of how such a system will operate, a traffic simulation model that reflects the specified vehicle arrival and service rates, and allows for multiple channel arrivals was applied to several parking exit plaza concepts. This paper compares the results obtained from both methods and describes how these estimations compared with queue and waiting time data collected at exit plazas in actual operation. The analysis described in this paper was based on the application of the analytical queuing model in conjunction with traffic simulation in parking exit plazas at four different airports: the Ronald Regan Washington National Airport, the Dulles International Airport, the Salt Lake City International Airport, and the Atlanta Hartsfield International Airport. The measures of effectiveness used to evaluate the models performance were average and maximum queuing delay, and average and maximum queuing length. Additionally, the output values, including the throughput volume estimated by the simulation model were compared to collected field values. The paper shows that simulation provides a more comprehensive understanding of the toll plaza operation allowing for a more in-depth analysis of its performance. While the simple queuing models could be used as an initial, in some cases more conservative estimation in early stages of planning, simulation should be used for advance planning, design, operation and management of toll and exit plaza facilities.

Abstract: In this paper, we present a quality of service (QoS) architecture for supporting real-time data transmission in mobile ad hoc networks (MANETs). The QoS architecture includes a QoS transport layer, QoS routing, queue management and a priority MAC protocol. Through simulations, we find that the QoS architecture reduces packet delay and greatly improves the quality of realtime video streams in MANETs.

Abstract: Provided are a method, system, network processor, network device, and article of manufacture for enqueueing entries in a packet queue referencing packets. When adding a packet to a first memory area, an entry is written to a packet queue in a second memory area referencing the added packet. A pointer is read referencing one end of the packet queue from a queue descriptor in the second memory area into a third memory area in one read operation. The pointer is updated in the third memory area to point to the added entry in the packet queue and the updated pointer in the third memory area is written to the queue descriptor in the second memory area in one write operation.

Abstract: The present invention provides a method and apparatus for resource allocation in a system which includes work items which are to be completed in both business time and real time. Work items are placed in a delta queue which has a calendar associated therewith indicating business time and non-business time for resources associated with the delta queue. When the calendar associated with the delta queue enters into a non-business time, a scheduler pushes an item at the head of the delta queue which corresponds to the amount of non-business time. Work items in the delta queue are thus delayed by the appropriate amount of time corresponding to the non-business time.

Abstract: An intelligent queue monitor works on behalf of subscribers to an electronic media service provider to ensure that an adequate and interesting list of titles is made available to the subscriber. The queue monitor can be integrated as part of the e-commerce website, at a separate monitoring site, or as a stand alone package based at the user's client computing system.

Abstract: Apparatus and methods, including computer program products, for providing a network-accessible queue. The queue is stored on a network-accessible file system having a locking mechanism providing strictly-enforced, network-wide file locking. The data structures of the queue are stored in the file system. The file system is preferably implemented on a network accessible RAID array storage device providing a native CIFS file system for storing queue entries received over a network from sender clients and for delivery of such queue entries to receiver clients. Synchronization is implemented using file locks enforced by the file system, so there is no need for a master synchronization process. Notification of the availability of queue entries to receiver clients is also done by a decentralized process.

Abstract: A new model for call centre queue management is described. It incorporates important features of call centre queues and is shown to produce results that are very different from those produced by the more usual models. The analytic approach is easy to apply, and is used to offer some interesting insights for call center queue management.