Average Queue Length Research Articles

An Intelligent IoT Based Traffic Light Management System: Deep Reinforcement Learning

Traffic is one of the indispensable problems of modern societies, which leads to undesirable consequences such as time wasting and greater possibility of accidents. Adaptive Traffic Signal Control (ATSC), as a key part of Intelligent Transportation Systems (ITS), plays a key role in reducing traffic congestion by real-time adaptation to dynamic traffic conditions. Moreover, these systems are integrated with Internet of Things (IoT) devices. IoT can lead to easy implementation of traffic management systems. Recently, the combination of Artificial Intelligence (AI) and the IoT has attracted the attention of many researchers and can process large amounts of data that are suitable for solving complex real-world problems about traffic control. In this paper, we worked on the real-world scenario of Shiraz City, which currently does not use any intelligent method and works based on fixed-time traffic signal scheduling. We applied IoT approaches and AI techniques to control traffic lights more efficiently, which is an essential part of the ITS. Specifically, sensors such as surveillance cameras were used to capture real-time traffic information for the intelligent traffic signal control system. In fact, an intelligent traffic signal control system is provided by utilizing distributed Multi-Agent Reinforcement Learning (MARL) and applying the traffic data of adjacent intersections along with local information. By using MARL, our goal was to improve the overall traffic of six signalized junctions of Shiraz City in Iran. We conducted numerical simulations for two synthetic intersections by simulated data and for a real-world map of Shiraz City with real-world traffic data received from the transportation and municipality traffic organization and compared it with the traditional system running in Shiraz. The simulation results show that our proposed approach performs more efficiently than the fixed-time traffic signal control scheduling implemented in Shiraz in terms of average vehicle queue lengths and waiting times at intersections.

Signal timing and geometric design at contraflow left-turn lane intersections

As a type of innovative intersection, Contraflow left-turn lane (CLL) intersection, has been increasingly implemented at the signalized intersections for increasing the leftturn capacity. This study developed a systematic method for determining the length of CLL and the signal timing plan for implementing CLL at signalized intersections. At first, the signal timing and geometric design requirements in the implementation of CLL were analyzed. Then, these requirements were thoroughly considered in the development of the proposed method. A case study was conducted for evaluating the operational benefits of redesigning a real-world CLL intersection using the recommended signal timing plan and CLL lengths. The results of the case study show that the redesigned CLL intersection outperforms the existing CLL intersection in terms of the average traffic delay, average vehicle travel time, and average queue length, and the CLL intersection can achieve its best performance at the recommended CLL lengths. These results indicate that the proposed method can provide useful guidelines to traffic engineers in the implementation of this innovative intersection design.

Improving RED algorithm congestion control by using the Markov decision process

Congestion control plays an essential role on the internet to manage overload, which affects data transmission performance. The random early detection (RED) algorithm belongs to active queue management (AQM), which is used to manage internet traffic. The RED is used to eliminate weakness in default control of the Transport Control Protocol (TCP) drop-tail mechanism. The drawback of RED is parameter tuning, while adaptive RED (ARED) automatically adjusts these parameters. In this study, the suggested algorithm, the Markov decision process RED (MDPRED) uses the Markov decision process (MDP) to suitably adapt values for queue weight in the RED algorithm based on average queue length to enhance the performance of the traditional RED during TCP Slow Startup phase. This study is conducted based on fluctuations among the rate of service, queuing weight, and the mean queue length by using open-source network simulator NS3. The study shows efficient results by fluctuating end-to-end packet throughput and fast response to the inception of congestion in the network. The modified algorithm achieves a low level of drop packets by evaluating the results with other five algorithms, which is done by increasing the algorithm’s response when the average queue size becomes close to the maximum queue length threshold.

Mitigating long queues and waiting times with service resetting.

What determines the average length of a queue, which stretches in front of a service station? The answer to this question clearly depends on the average rate at which jobs arrive at the queue and on the average rate of service. Somewhat less obvious is the fact that stochastic fluctuations in service and arrival times are also important, and that these are a major source of backlogs and delays. Strategies that could mitigate fluctuations-induced delays are, thus in high demand as queue structures appear in various natural and man-made systems. Here, we demonstrate that a simple service resetting mechanism can reverse the deleterious effects of large fluctuations in service times, thus turning a marked drawback into a favorable advantage. This happens when stochastic fluctuations are intrinsic to the server, and we show that service resetting can then dramatically cut down average queue lengths and waiting times. Remarkably, this strategy is also useful in extreme situations where the variance, and possibly even mean, of the service time diverge-as resetting can then prevent queues from "blowing up." We illustrate these results on the M/G/1 queue in which service times are general and arrivals are assumed to be Markovian. However, the main results and conclusions coming from our analysis are not specific to this particular model system. Thus, the results presented herein can be carried over to other queueing systems: in telecommunications, via computing, and all the way to molecular queues that emerge in enzymatic and metabolic cycles of living organisms.

A load balancing system in the many-server heavy-traffic asymptotics

We study the load balancing system operating under Join the Shortest Queue (JSQ) in the many-server heavy-traffic regime. If $N$ is the number of servers, we let the difference between the total service rate and the total arrival rate be $N^{1-\alpha}$ with $\alpha>0$. We show that for $\alpha>4$ the average queue length behaves similarly to the classical heavy-traffic regime. Specifically, we prove that the distribution of the average queue length multiplied by $N^{1-\alpha}$ converges to an exponential random variable. Moreover, we show a result analogous to state space collapse. We provide two proofs for our result: one using the one-sided Laplace transform, and one using Stein's method. We additionally obtain the rate of convergence in the Wasserstein's distance.

A deep reinforcement learning-based cooperative approach for multi-intersection traffic signal control

Recently, Adaptive Traffic Signal Control (ATSC) in the multi-intersection system is considered as one of the most critical issues in Intelligent Transportation Systems (ITS). Among the proposed AI-based approaches, Deep Reinforcement Learning (DRL) has been largely applied while showing better performances. This paper proposes a new DRL-based cooperative approach for controlling multiple intersections. The problem is modelled as a Multi-Agent Reinforcement Learning (MARL) system, while each agent is trained to select the best action to control an intersection by obtaining information about its local lanes state. The cooperation aspect is manifested in this approach by considering the effect of the state, action and reward of neighbour agents in the process of policy learning. An intersection controller applies a Deep Q-Network (DQN) method, while transferring state, action and reward received from their neighbour agents to its own loss function during the learning process. The experimental results under different scenarios shows that the proposed approach outperforms many state-of-the-art approaches in terms of three metrics: Average Waiting Time (AWT), Average Queue Length (AQL) and Average Emission CO2 (AEC). In addition, the cooperation between the different trained DRL-based controllers allows the system to continuously learn and improve its performance by interacting with the environment, particularly when the traffic is congested.

Performance Analysis of \(M^X/M/1\) Queue With Working Vacation, \(N\)-Policy and Customer Impatience

This paper deals the transient analysis of a queueing system with working vacation in which the server may encounter with breakdowns. Customers enter in batches according to a Poisson process and receive service in FCFS mode. Whenever the server finds nobody, the server starts a working vacation during which the server renders service at a slower rate than the normal one. Further, we considered two types of customer’s impatience balking and reneging. We solved the system of differential equations to find transient state probabilities and computed various performance indices like average queue length of system, the mean waiting time etc. We then executed sensitivity analysis and observed the impact on different parameters.

TSBS: A Two-Stage Backpressure Scheduling scheme over multihop wireless networks

The backpressure algorithm has been considered a promising routing and scheduling scheme in multihop wireless networks. However, path detours or loop problems and the last packet problem have always troubled the performance improvement of the backpressure algorithm. Existing backpressure algorithms cannot simultaneously prevent both path detours or loop and the last packet problems and thus fail to improve network performance further. To this end, this paper proposes a Two-Stage Backpressure Scheduling (TSBS) scheme that presents a new link weight design and develops a two-stage execution algorithm to resolve the above two problems. In the first stage, we use the shortest path and queue backlog metrics to build link weight to prevent path detours or loop problems and obtain the scheduling link set with the maximum queue backlog. In the second stage, considering the delay differential of the Head-of-Line (HOL) packets in link weight design, an optimal scheduling link is selected from the scheduling link set to inhibit the last packet problem. By Lyapunov drift theory, our analysis proves that TSBS achieves network stability and optimal throughput within the network’s capacity region. Simulation results show that TSBS improves average end-to-end delay by up to 26.78%, the percentage of packet forwarding by up to 18.92%, average queue length by up to 27.91%, and network throughput by up to 283.86%, compared with the baseline D-BP algorithm, respectively.

Double-ended queues with non-Poisson inputs and their effective algorithms

It is interesting and challenging to study double-ended queues with First-Come-First-Match discipline under customers’ impatient behavior and non-Poisson inputs. The system stability can be guaranteed by the customers’ impatient behavior, while the existence of impatient customers makes analysis of such double-ended queues more difficult or even impossible to find an explicitly analytic solution, thus it becomes more and more important to develop effective numerical methods in a variety of practical matching problems. This paper studies a block-structured double-ended queue, whose block structure comes from two independent Markovian arrival processes (MAPs), which are non-Poisson inputs. We show that such a queue can be expressed as a new bilateral quasi birth-and-death (QBD) process which has its own interest. Based on this, we provide a detailed analysis for both the bilateral QBD process and the double-ended queue, including the system stability, the queue size distributions, the average stationary queue lengths, and the sojourn time of any arriving customers. Furthermore, we develop three effective algorithms for computing the performance measures (i.e., the probabilities of stationary queue lengths, the average stationary queue lengths, and the average sojourn times) of the double-ended queue with non-Poisson inputs. Finally, we use some numerical examples in tabular and graphical to illustrate how the performance measures are influenced by some key system parameters. We believe that the methodology and results described in this paper can be applicable to deal with more general double-ended queues in practice, and develop some effective algorithms for the purpose of many actual uses.

A Reinforcement Learning Based Traffic Control Strategy in a Macroscopic Fundamental Diagram Region

Urban traffic control systems (UTCSs) are deployed to a great number of urban cities despite lacking feedback when adjusting the traffic signals. The development of reinforcement learning (RL) makes it possible to apply feedback to UTCS, and great efforts have been made on RL-based traffic control strategies. However, those studies are regardless of the traffic flow theory of the network and the road users’ perspectives on the performance of traffic. This study proposes a multiagent reinforcement learning (MARL) based traffic control strategy, in which each intersection in a macroscopic fundamental diagram (MFD) region was controlled by one agent using the level of services (LOS) and MFD-based parameters as rewards. The proposed MARL strategy was evaluated by simulation in a 3×3 grid network compared with pretimed, actuated, and MFD-based traffic control strategies. The evaluation results showed that, at different demand levels, the proposed MARL strategy outperforms the other three traffic control strategies in terms of average intersection queue length and average intersection waiting time to a different extent. Results also showed that the proposed MARL dissipated the congestion faster than the other three control strategies. Results of the Friedman test indicated that the differences in performances between the proposed MARL and other strategies were statistically significant regardless of the demand level. The MFD in the testbed network controlled by the proposed MARL was different from that controlled by the pretimed strategy, especially the MFD scatter plot. It provides insights on considering the traffic flow theory of the network when applying MARL to traffic control strategies.

A Comparision of Node Detection Algorithms Over Wireless Sensor Network

MANET is standing for Network as Mobile Ad-hoc which is a self-directed mobile handlers group which communicates over relatively bandwidth constrained wireless channels. Many services with different classes of Quality of Services (QoS) could be provided through the MANET such as data, voice, and video streaming. Thus, efficient packets routing is an essential issue especially over this kind of burst channel. To settle this issue, many scheduling techniques are proposed to reduce the packets dropping and channel collision when a huge demand of data is transferred from a sender to a receiver. In this paper, four MANET scheduling algorithms are selected and investigated in mobile ad hoc network which are Strict Preference (SP), Round Robin (RR), Weighted Round Robin (WRR), and Weighted Fair (WF). The network simulator EXata 2.0.1 is used to build the scenario which is consist of 50 nodes and performed the simulation. The results showed the performance metrics difference of the network such as the throughput and the end-end delay as well as queuing metrics like peak queue size, average queue length, in queue average time, and droppe of whole packets. Regrading throughput, the SP algorithm has a greater throughput than WF, RR, and WRR by 4.5%, 2.4%, and 1.42%, but WRR has outperformed others regarding the end-end delay. Moreover, WRR represents the best scheduling algorithm regarding both peak queue size since its greater than RP, WF, and WRR by 10.13%, 9.6%, and 5.32%, in order, and average output queue length in contrast, WRR worsts more time in queuing but it is the best in preventing the packets from dropping.

Deep Reinforcement Learning-Based Traffic Light Scheduling Framework for SDN-Enabled Smart Transportation System

This work proposes a traffic-light scheduling framework using the deep reinforcement learning technique to balance the traffic flow and to prevent congestion in the dense regions of the city via a software-defined control interface. A software-defined control enabled architecture is proposed to monitor the traffic conditions and it generates the traffic light control signal (Red/Yellow/Green) accordingly. For an intelligent traffic light control signal, a Deep Reinforcement Learning (DRL) model is proposed which takes vehicular dynamics as inputs from the real-time traffic environment such as heterogeneous vehicles count, speed, traffic density etc. To determine the congestion, a threshold policy is proposed and deployed on control server which generates the congestion prevention signal. A DRL agent operates in the coordination of congestion prevention signal and generates an effective traffic light control signal. The proposed model is evaluated through a realistic simulation on Indian city OpenStreetMap by using a well-known open-source simulator (SUMO). The comparative results show that the proposed solution improves several performance metrics such as average waiting time, throughput, average queue length, and average speed in the interval of 28.34% – 66.62%, 24.76% – 66.60%, 30.89% – 69.80%, and 16.62% – 43.67% respectively over other states of the art approaches.

Optimizing signal timing of the arterial‐branch intersection: A fuzzy control and nonlinear programming approach

AbstractArterial‐branch intersections are important components of urban road network but are greatly ignored of its role in maintaining an efficient traffic operation in regional networks. Arterial‐branch intersections are generally featured with significant fluctuations in the flow ratio of the branch road to the arterial road. So, in order to adapt the signal timing to this kind of intersection, an optimization control algorithm based on fuzzy control and nonlinear programming (FCNP) was proposed. To verify this optimization algorithm, the Python and Vissim joint simulation was employed. Prior to the simulation, traffic flow data were collected in 12 consecutive hours at an arterial‐branch intersection in China. The simulation results show that, after signal timing optimization with FCNP, the average vehicle queue length and delay reduced 25.8% and 17.3%, respectively, when compared with the performance of the traffic‐actuated control, which also outperformed previous equivalent research. Besides, the overall operation of the intersection was verified to be greatly improved and stabilized by using the proposed algorithm. The findings of this study provide a reasonable solution of distributing the right‐of‐way at arterial‐branch intersections and suggest the advantage of combining fuzzy control and nonlinear programming in dealing with the signal timing optimization.

Dynamic Rebalancing Strategy in Free-Float Bicycle Sharing Systems: Orbit Queues and Two-Sided Matching

In populous metropolitan areas, the free-floating bicycle-sharing system (FFBSS) acts as an innovative urban mobility as a service, which provides an ease-of-use feature and extra flexibility in contrast to the traditional shared bicycles with docks. In consideration of customer behaviors, such as abandonment and retrial, which occur in FFBSS, a redistribution strategy for shared bicycles among different user-density locations is presented with an aim to diminish the total operational cost while enhancing the overall service level. To formulate the user and multitype shared bicycle–arrival patterns as nonhomogeneous queues, our results provide a tractable analytical paradigm for a time-varying balancing strategy for FFBSS. The bicycle variation at each virtual zone after each redistribution is determined via a nonstationary queueing model, in which the service time, patience time, and research delay are all subject to general distribution. Then, the bicycle-deployment strategy is evaluated with respect to average queueing length and abandonment rate during a normal workday based on a tailored nonhomogeneous probabilistic matching queue. To verify the efficacy and cost-effectiveness of the proposed bicycle-redistribution strategy, multiple simulation runs are conducted with respect to various times of the day. It shows that the resulting optimal rebalancing strategy is batch-based in synchrony with the time heterogeneity in the traffic demand. Furthermore, several managerial insights are provided to shed light on the rule of thumb in practical FFBSS redistribution coordination.

Optimization of Emergency Transportation Organization of Holiday Tourism Traffic

The purpose of the optimization of holiday traffic emergency traffic organization is to solve the problem of serious traffic jams in holiday scenic spots. Based on the prediction of traffic volume and traffic mode division in the future years of the scenic spot, the traffic accident route is analyzed to provide theoretical support for the emergency traffic organization and planning of the scenic spot. This article takes the Shijiazhuang Jinta Bay scenic area as the research object, based on the traffic volume of the Jinta Bay tourist scenic area from 2009 to 2016, analyzes the traffic environment of the scenic area, predicts the traffic demand, and builds a one-way traffic organization double-layer optimization model. The simulated annealing algorithm is used to solve the model, an emergency transportation organization optimization plan is formulated, and the feasibility of the plan is verified through VISSIM simulation. The results of the study show that the one-way traffic organization method reduces the average vehicle delay by 32.2% and the average queue length by 14.5%. The one-way traffic organization based on branch diversion can more effectively solve the main road jamming and congestion caused by traffic accidents, prevent the occurrence of secondary accidents, and reduce the economic losses of scenic area managers. At the same time, the purpose of ensuring the tourist quality of tourists and the economic interests of scenic spot management departments is ensured.

A Novel Active Queue Management Algorithm Based on Average Queue Length Change Rate

The rapid development of information technology has promoted the transformation of traditional networks into intelligent networks. Huge data traffic is generated by various types of traffic services in the intelligent networks, which can easily lead to network congestion, system instability, and other problems. These problems may incur great requirements and pose challenges for queue management algorithms. Most traditional active queue management (AQM) algorithms judge the congestion level of the network based only on the size of the average queue length while ignoring the network traffic variations. This makes these algorithms difficult to achieve effective improvement of congestion control efficiency. To address this problem, a novel network congestion control algorithm, namely the average queue length and change rate –RED (AC-RED) is proposed in this paper. AC-RED can better relieve network congestion by reconfiguring the packet loss strategy model based on the average queue length change rate. The simulation results of NS2 show that in complex and dynamic network environments, the performance of AC-RED algorithm in the average queue length, packet loss rate, delay, and delay jitter is improved in most load conditions compared with the other five algorithms.

An Analytical Performance Evaluation of MapReduce Model Using Transient Queuing Model

Today the MapReduce frameworks become the standard distributed computing mechanisms to store, process, analyze, query and transform the Bigdata. While processing the Bigdata, evaluating the performance of the MapReduce framework is essential, to understand the process dependencies and to tune the hyper-parameters. Unfortunately, the scope of the MapReduce framework in-built functions is limited to evaluate the performance till some extent. A reliable analytical performance model is required in this area to evaluate the performance of the MapReduce frameworks. The main objective of this paper is to investigate the performance effect of the MapReduce computing models under various configurations. To accomplish this job, we proposed an analytical transient queuing model, which evaluates the MapReduce model performance for different job arrival rates at mappers and various job completion times of mappers as well as the reducers too. In our transient queuing model, we appointed an efficient multi-server queuing model M/M/C for optimal waiting queue management. To conduct the experiments on proposed analytics model, we selected the Bigdata applications with three mappers and two reducers, under various configurations. As part of the experiments, the transient differential equations, average queue lengths, mappers blocking probability, shuffle waiting probabilities and transient states are evaluated. MATLAB based numerical simulations presented the analytical results for various combinations of the input parameters like λ, µ1 and µ2 and their effect on queue length.

UMVUEs and Bayes estimators for various performance measures on a Poisson queue with discouraged arrivals

To prevent overcrowding during the COVID-19 pandemic, numerous businesses, and public service systems have to limit the number of people entering the premises to reduce infection risks. Such a realistic situation prompts us to revisit an adaptive queueing model from a statistical perspective, which allows us to extensively analyze and explore the stochastic service system arising in the pandemic period. In order to avoid long waiting lines, we assume that the arrival rate of customers into the system depends on the system size instead of a constant rate. This article attempts to study the uniformly minimum variance unbiased estimators and closed-form Bayes estimators of various queueing characteristics, such as the probability that the server is busy, the proportion of lost customers, mean system length, and average queue length. The estimates and their behaviors are compared by Monte-Carlo simulation with different sample sizes. The simulation results show that we may choose different estimation techniques for different performance indicators to obtain a more precise estimate.

A Multipath Cluster-Based Routing Protocol For Mobile Ad Hoc Networks

A MANET (Mobile Ad-hoc Network) is a group of mobile network nodes dynamically forming a network without any pre-existing infrastructure. Multi-path routing protocols in MANETs try to discover and use multiple routes between source and destination nodes. Multipath routing is typically used to reduce average delay, increase transmission reliability, provide load balancing among multiple routes, and improve security and overall QoS (Quality of Service). In this paper, the Cluster-Based Routing Protocol (CBRP), which is a single path MANET protocol is enhanced to use multiple paths. The traffic will be distributed among multiple paths to reduce network traffic congestion and decrease delay. An analytical model is used for multipath and single path CBRP routing protocols in MANETs to estimate the end-to-end delay and queue length. The analytical results show that the average delay and average queue length in multipath CBRP are less than the average delay and queue length in single path CBRP.

Active Queue Management in RED Considering Critical Point on Target Queue

The basic philosophy behind RED is to prevent congestion. When the average queue length exceeds the minimum threshold, packets are randomly dropped, or the explicit congestion notification bit is marked. Since network requirements differ significantly, it is not an optimal approach to establish RED parameters with constant value. There is a new algorithm we are proposing called Critical Point on Target Queue (AQM-RED-CPTQ), provide greater congestion management over the network while also preserving the value of RED. To overcome the problem in RED without changing queue weight parameter, we have proposed few models to control the congestion by introducing range parameter with probability and control mechanism which will belong between minimum and maximum threshold. The current queue size is controlled together with average queue size. A new range variable has been introduced to improve the performance of priority queue of existing RED based algorithm which improves the overall performance of networks. For each packet, minimum and maximum threshold has been updated and dropped with probability (Pa) for a special condition. Instead of multiplicative increase and decrease the maximum probability, the scheme uses additive-increase and multiplicative-decrease. Once the AVG queue length is close to the minimum threshold value, our approach automatically sets queue parameter according to queue conditions and handles queuing delay and improve throughput. The simulated results proof that our approaches are better than RED in terms of throughput, end to end delay, packet delivery ratio and goodput.