Abstract: We consider a system of multiple sources generating status update packets, which need to be sent by a single transmitter to a destination over a network. In the model we study, the packet generation time may vary at each source, and the packets go through the network with a random delay. Each update carries a time stamp of its generation, allowing the destination to calculate for each source the so called Age of Information, which measures the timeliness of each status update arriving. Considering that queuing delay can unnecessarily increase the age of a critical status update, we propose here a queue management technique, in which we maintain a queue with only the latest status packet of each source, overwriting any previously queued update from that source. This simple technique drastically limits the need for buffering and can be applied in systems where the history of source status is not relevant. We show that this scheme results in significantly less transmissions compared to the standard M/M/1 queue model. Furthermore, the proposed technique reduces the per source age of information, especially in settings not using queue management with high status update generation rates.

Abstract: The paper presents an analysis of the traffic dynamics in a network of signalized intersections. The intersections are regulated by fixed-time (FT) controls, all with the same cycle length or period, T. The network is modeled as a queuing network. Vehicles arrive from outside the network at entry links in a deterministic periodic stream, also with period T. They take a fixed time to travel along each link, and at the end of the link they join a queue. There is a separate queue at each link for each movement or phase. Vehicles make turns at intersections in fixed proportions, and eventually leave the network, that is, a fraction r ( i , j ) of vehicles that leave queue i go to queue j and the fraction [ 1 - ∑ j r ( i , j ) ] leave the network. The storage capacity of the queues is infinite, so there is no spill back. The main contribution of the paper is to show that if the signal controls accommodate the demands then, starting in any initial condition, the network state converges to a unique periodic orbit. Thus, the effect of initial conditions disappears. More precisely, the state of the network at time t is the vector x ( t ) of all queue lengths, together with the position of vehicles traveling along the links. Suppose that the network is stable, that is, x ( t ) is bounded. Then (1) there exists a unique periodic trajectory x ∗ , with period T; (2) every trajectory converges to this periodic trajectory; (3) if vehicles do not follow loops, the convergence occurs in finite time. The periodic trajectory determines the performance of the entire network.

Abstract: In transportation and other types of facilities, various queues arise when the demands of service are higher than the supplies, and many point and fluid queue models have been proposed to study such queueing systems. However, there has been no unified approach to deriving such models, analyzing their relationships and properties, and extending them for networks. In this paper, we derive point queue models as limits of two link-based queueing model: the link transmission model and a link queue model. With two definitions for demand and supply of a point queue, we present four point queue models, four approximate models, and their discrete versions. We discuss the properties of these models, including equivalence, well-definedness, smoothness, and queue spillback, both analytically and with numerical examples. We then analytically solve Vickrey’s point queue model and stationary states in various models. We demonstrate that all existing point and fluid queue models in the literature are special cases of those derived from the link-based queueing models. Such a unified approach leads to systematic methods for studying the queueing process at a point facility and will also be helpful for studies on stochastic queues as well as networks of queues.

Abstract: A method of operation of a processor core execution unit circuit provides efficient use of area and energy by reducing the per-entry storage requirement of a load-store unit issue queue. The execution unit circuit includes a recirculation queue that stores the effective address of the load and store operations and the values to be stored by the store operations. A queue control logic controls the recirculation queue and issue queue so that that after the effective address of a load or store operation has been computed, the effective address of the load operation or the store operation is written to the recirculation queue and the operation is removed from the issue queue, so that address operands and other values that were in the issue queue entry no longer require storage. When a load or store operation is rejected by the cache unit, it is subsequently reissued from the recirculation queue.

Abstract: A computer system having a plurality of processing resources, including a sub-system for scheduling and dispatching processing jobs to a plurality of hardware accelerators, the subsystem further comprising a job requestor, for requesting jobs having bounded and varying latencies to be executed on the hardware accelerators; a queue controller to manage processing job requests directed to a plurality of hardware accelerators; and multiple hardware queues for dispatching jobs to the plurality of hardware acceleration engines, each queue having a dedicated head of queue entry, dynamically sharing a pool of queue entries, having configurable queue depth limits, and means for removing one or more jobs across all queues.

Abstract: Unmanned aerial vehicles which are used to build flying ubiquitous sensor networks are viewed as a queuing system and their swarm — as a queuing network. It is proved that a sufficiently large number of UAVs swarm can be considered as a network of Jackson. The distribution of the lengths of the shortest paths for the UAVs swarms with a cube and a sphere is determined.

Abstract: In this paper, we study the Markovian queuing system with heterogeneous servers and catastrophes. The customers arrive according to a Poisson process and the service times follow exponential distribution. There are a finite number of c servers with different services rates and each arriving customer requires exactly one server for its service. The queue discipline is FCFS, and the customers select the servers on fastest server first(FSF) basis. We use the generating function technique to derive the transient solution of the model in a direct way. The explicit time dependent probabilities of system size are obtained and a numerical example is presented in order to show the managerial insights of the model. Some important special cases of the model are derived and discussed. Finally, the probability that arriving customer finds system busy and average number of server busy in steady state are obtained numerically.

Abstract: An apparatus and method for a memory controller for managing scheduling requests in a solid state memory device. The memory includes a set of units wherein a unit within the set of units is erasable as a whole by a unit reclaiming process resulting in a free unit available for writing data to. The memory controller further includes a first queue for queuing user requests for reading and/or writing data from/to the memory, and a second queue for queuing unit reclaiming requests for executing the unit reclaiming process. A scheduler is provided for selecting user requests from the first queue and unit reclaiming requests from the second queue for execution according to a defined ratio. The defined ratio is a variable ratio, is dependent on the current number of free units, and permits the memory controller to select requests from both the first queue and the second queue.

Abstract: In this paper, we design a new virtual queue-based back-pressure scheduling algorithm (VBR) for achieving significant delay reduction in wireless sensor networks (WSN). Our algorithm design comes from an observation that classical back-pressure scheduling algorithm usually needs a long period of time to form a queue backlog-based gradient in a network, which decreases towards the sink in the network, before achieving stable packet delivery performance. To address this issue, VBR is designed to pre-build proper virtual queue-based gradient at nodes in a WSN, which is chosen to be a function of traffic arrival rate, link rate, and distance to sink, in order to be adaptive to different network and application environments while achieving high network performance. Moreover, the queue backlog differential between each pair of neighbor nodes is decided by their actual queue lengths and also their virtual queue lengths (gradient values). We prove that VBR can maintain back-pressure scheduling’s throughput optimality. Simulation result shows that VBR can obtain significant performance improvement in terms of packet delivery ratio, average end-to-end delay, and average queue length as compared with existing work.

Abstract: In this paper, we design a new virtual queue-based back-pressure scheduling algorithm (VBR) for achieving significant delay reduction in wireless sensor networks (WSN). Our algorithm design comes from an observation that classical back-pressure scheduling algorithm usually needs a long period of time to form a queue backlog-based gradient in a network, which decreases towards the sink in the network, before achieving stable packet delivery performance. To address this issue, VBR is designed to pre-build proper virtual queue-based gradient at nodes in a WSN, which is chosen to be a function of traffic arrival rate, link rate, and distance to sink, in order to be adaptive to different network and application environments while achieving high network performance. Moreover, the queue backlog differential between each pair of neighbor nodes is decided by their actual queue lengths and also their virtual queue lengths (gradient values). We prove that VBR can maintain back-pressure scheduling’s throughput optimality. Simulation result shows that VBR can obtain significant performance improvement in terms of packet delivery ratio, average end-to-end delay, and average queue length as compared with existing work.

Abstract: This paper proposes a smart queue management system for delivering real-time service request updates to clients' smartphones in the form of audio and visual feedback The proposed system aims at reducing the dissatisfaction with services with medium to long waiting times To this end, the system allows carriers of digital ticket to leave the waiting areas and return in time for their turn to receive service The proposed system also improves the waiting experience of clients choosing to stay in the waiting area by connecting them to the audio signal of the often muted television sets running entertainment programs, advertisement of services, or news The system is a web of things including connected units for registering and verifying tickets, units for capturing and streaming audio and queue management, and participating client units in the form of smartphone applications We implemented the proposed system and verified its functionality and report on our findings and areas of improvements

Abstract: A method and apparatus are provided for scheduling a heterogeneous communication flow. A heterogeneous flow is a flow comprising packets with varying classes or levels of service, which may correspond to different priorities, qualities of service or other service characteristics. When a packet is ready for scheduling, it is queued in order in a flow queue that corresponds to the communication flow. The flow queue then migrates among class queues that correspond to the class or level of service of the packet at the head of the flow queue. Thus, after the head packet is scheduled, the flow queue may be dequeued from its current class queue and requeued at the tail of another class queue. If the subsequent packet has the same classification, it may be requeued at the tail of the class queue or may remain in place for another servicing round.

Abstract: Taxi waiting queues or passenger waiting queues usually reflect the imbalance between taxi supply and demand, which consequently decrease a city’s trac system productivity and commuters’ satisfaction. In this paper, we present a queue detection and analysis system to conduct analytics on both taxi and passenger queues. The system utilizes the event-driven taxi traces and the taxi state transition knowledge to detect queue locations at a coordinate level and subsequently identify 4 di↵erent types of queue context (e.g., only passengers queuing or only taxis queuing). More specifically, it adopts the novel and easy-to-implement algorithms to selectively extract taxi pickup events and their critical features. The extracted taxi pickup locations are then used to detect queue locations, and the extracted critical features are used to infer queue context. The extensive empirical evaluations, which run on daily 12.4 million taxi trace records from nearly 15000 taxis in Singapore, demonstrate the high accuracy and stability of the queue analytics results. Finally, we discuss the real world deployment issues and the gained insights from the queue analysis results.

Abstract: Oversaturated intersection control is a long-standing problem in traffic science and engineering. The problem becomes even harder when we consider a system of oversaturated intersections. Most of the research works in this area are off-line studies that require fully knowledge of origin–destination demand, which would be difficult to obtain in reality. Although several on-line feedback control methods are proposed, they only aim at preventing queue spillover, not able to minimize vehicular delay time. Moreover, these on-line control strategies are not theoretically evaluated how optimal (or sub-optimal) they are. We propose in this paper a quasi-optimal decentralized QUEUE-based feedback (abbreviated as QUEUE) control strategy for a system of oversaturated intersections. The QUEUE strategy is applied cycle-by-cycle based on measurement of current queue sizes, but its overall result is able to approximate the optimal one derived from off-line studies. Details of the feedback control laws for upstream and downstream intersections, in the queueing period and the queue dissipation period, are discussed. Superior to the existing feedback control strategies, the upper bounds of sub-optimality of the QUEUE strategy generating from demand fluctuation and coupling of intersections are specified quantitatively. It is also theoretically proved that the queue measurement error or demand estimation error would not be amplified by the QUEUE strategy. Numerical examples show that the QUEUE strategy performs very well and is robust to errors.

Abstract: This paper deals with a finite source retrial queueing system of type M/M/1//N with collision of the customers. This means that the system has one server and N sources. Analysis of the sojourn time in the system is presented. The analysis is performed under an asymptotic condition of infinitely increasing number of sources. The approximation of the distribution of the total sojourn time in the system is derived.

Abstract: The invention discloses a remote queuing method and a remote queuing system for banking business handling. The remote queuing method comprises the following steps: a user sends a reservation request through a remote terminal; a data processing center receives the reservation request, recommends outlets for the received reservation request according to the information of all outlets, and sends an outlet recommendation result to the remote terminal for display; the user determines a target outlet according to the outlet recommendation result and returns the target outlet to the data processing center through the remote terminal; the data processing center generates a corresponding reservation number according to the returned target outlet, and sends the reservation number to the remote terminal; and the data processing center assigns a corresponding queuing number for the reservation request according to the reservation number based on the time when the user arrives at the target outlet. According to the invention, remote queuing is carried out through reservation, and outlets are recommended for a reservation request according to the queuing condition of all outlets. Therefore, users can be effectively guided to a relatively idle outlet for handling business, and the on-site queuing time is reduced greatly for users.

Abstract: Modern web apps handle huge and increasing numbers of users and operations. A rise of event-driven architecture approach and message queue systems provide a new alternative to face this scenario evidencing the lack of quantitative measurements comparing performance and scalability between specific message queue products. This article proposes a prototype architecture applied in ZeroMQ and RabbitMQ, used for measure the impact of (1) the number of messages over performance, and (2) the numbers of consuming nodes over scalability. The results show that for both criteria, the degradation threshold of ZeroMQ is higher than RabbitMQ, thus more scalable and faster.

Abstract: We present QueueVadis, a system that addresses the problem of estimating, in real-time, the properties of queues at commonplace urban locations, such as coffee shops, taxi stands and movie theaters. Abjuring the use of any queuing-specific infrastructure sensors, QueueVadis uses participatory mobile sensing to detect both (i) the individual-level queuing episodes for any arbitrarily-shaped queue (by a characteristic locomotive signature of short bursts of "shuffling forward" between periods of "standing") and (ii) the aggregate-level queue properties (such as expected wait or service times) via appropriate statistical aggregation of multi-person data. Moreover, for venues where multiple queues are too close to be separated via location estimates, QueueVadis also uses a novel disambiguation technique to separate users into multiple distinct queues. User studies, performed with 138 cumulative total users observed at 23 different real-world queues across Singapore and Japan, show that QueueVadis is able to (a) identify all individual queuing episodes, (b) predict service and wait times fairly accurately (with median estimation errors in the 10%--20% range), independent of the queue's shape, (c) separate users in multiple proximate queues with close to 80% accuracy and (d) provide reasonable estimates when the participation rate (the fraction of QueueVadis-equipped people in the queue) is modest.

Abstract: We develop a queueing model for an appointment-based service system that consists of two queues in tandem: the appointment queue followed by the service queue. Customers join the appointment queue when they call for appointments, stay there (not physically) until the appointment time comes, and then leave the appointment queue and may physically join the service queue, and wait there until served, or become a no-show. The probability of becoming a no-show depends on the time spent in the appointment queue. We build a Tandem Queue model that explicitly captures the dependence between these two queues. We then derive several performance measures of interest, such as service utilization and customer long-run average waiting times in both queues. We also develop several approximation methods to compute the long-run average waiting time in the service queue, including one which is particularly useful when service times in that queue are not exponential.

Abstract: A method for two level quality of service scheduling for latency and queue depth control in a storage system is provided. The method includes determining queue depth as input/output operations per unit time that a storage subsystem can sustain, for each of a plurality of queues corresponding to storage subsystems in the storage system and determining system capacity as total input and output operations per unit time that the storage system can sustain, based on the queue depth of each of the plurality of queues. The method includes determining whether to accept or deny an input/output request for placement onto an input/output stack, based on a comparison of credits of the input/output request to the system capacity as determined on an ongoing basis, and placing the input/output request from the input/output stack onto one of the plurality of queues based on whether doing so maintains the queue depth of the one of the plurality of queues.

Abstract: Ticket queues are systems that issue tickets to customers upon their arrival. Although ticket queues are preferred by many service providers, there is limited research on ticket queues, especially on customer perceptions of, preferences for, and behavior in these systems. We conducted a series of surveys to understand customer preferences and patience in a ticket queue and a physical queue stand-in-line system and to investigate whether the assumptions used in analytical queuing models for customer abandonment behavior are realistic. Study results indicate that subjects generally prefer ticket queues over physical queues and have greater patience in ticket queues than they do in physical queues. In addition, we observe that subjects are willing to wait longer than they initially were, assuming that they already have spent some time waiting in line. Using the survey results, we ran a series of simulation models by adjusting the traditional queuing assumptions and showed the impact of customer behavior on system performance measures in ticket and physical queues. Our results can assist managers, in determining the type of queue to implement under various service settings, and researchers, in modeling more realistic queuing systems.

Abstract: An apparatus is configured to perform a method for congestion control in an Ethernet network. The method includes determining an egress queue congestion state for each of a plurality of egress queues. The method also includes determining an ingress queue congestion state for each of a plurality of ingress queues. The method further includes determining a flow control state for at least one of the ingress queues based on the determined egress queue congestion states and ingress queue congestion states. In addition, the method includes transmitting a flow control message to the at least one ingress queue based on the determined flow control state.

Abstract: Heavy traffic load in current LTE networks calls for effective radio resource allocation methods and tools for performance evaluation. In this work, we provide an analytical framework for LTE resource allocation in terms of queuing theory. We consider a multiservice queuing system with a finite amount of resources of several types, and allow the customers occupy a random amount of resources upon their arrival. Random resource requirements lead to more accurate performance evaluation compared to conventional multiservice models. For the considered model, we prove that the stationary probability distribution has a multiplicative form. Our findings are illustrated with a numerical example.

Abstract: Tandem queues with a finite buffer capacity are the common structures embedded in practical production systems. We study the properties of tandem queues with a finite buffer capacity and non-overlapping service times subject to time-based preemptive breakdowns. Different from prior aggregation and decomposition approaches, we view a tandem queue as an integrated system and develop an innovative approach to analyze the performance of a dual tandem queue through the insight from Friedman's reduction method. We show that the system capacity of a dual tandem queue with a finite buffer and breakdowns can be less than its bottleneck-sees-initial-arrivals system due to the existence of virtual interruptions. Furthermore, the virtual interruptions depend on job arrival rates in general. Approximate models are derived using priority queues and the concept of virtual interruptions.

Abstract: This technical note analyzes strategic overtaking equilibria in a single server queue, where customers observe the queue length and have the option of overtaking some of the customers already present in the queue by paying a fixed amount per overtaken customer.

Abstract: Over the years, the population of the university has increased with the introduction of double intake system which in turn has led to long waiting times and long queues in students finance department, due to few service stations, inefficiencies in the payment system used and students being disorderly. To enhance service delivery, a proper queuing system is needed. This is achieved by putting in place proper measures to ensure a good flow of students at the service counters. Focusing only on the main queue we collect data and do an empirical analysis of the model in use. Using queuing theory principles and formulas the study showed that on average 22 customers arrive every hour and the service rate is 23.7 customers per hour. The system utilization factor was 92.95%, the probability of zero customers waiting 7.05; average number of customers waiting is 12.252 and average waiting time 33.415 min. The study compared the single server model against multi-server model and concluded that M/M/1 model was not the best for the Finance department. Using a questionnaire of 384 respondents, the study found out that almost all customers are not satisfied about the nature of waiting lines and some students have turned away at regular occasions due to the long queues. The time students wait to be served should not be overlooked; constant check for their changing needs and improvement in the time spent when serving them has been emphasized by the study. In today’s competitive business environment, the modern society is progressively turning into a service dominating one. Customer satisfaction and service operation capabilities have given an organization a competitive advantage in the marketplace and this has consequently led to an increasing importance in service operations management. As a result, waiting has drawn great attention to all business operation management specialists.