Search

Virtual Traffic Lights (VTLs) come under the umbrella of Vehicular Adhoc Networks (VANETs) and are self-organized systems to implement traffic light control systems at a road intersection. During a VTL lifetime, VTLs may fail to maintain the uninterrupted working of the traffic light system. The vehicles arriving after a stable cluster formation and ongoing operation of VTL may go unattended which can weaken its application effect. If a new vehicle approaches the intersection, it either needs to get re-clustered with the current VTL cluster or has to form a new cluster with other arriving vehicles. In this paper, we aim to incorporate the Positive Selection Algorithm (PSA) scheme which is flourished with Artificial Immune System (AIS) behaviour to detect and control this anomalous clustering condition of the VTL traffic management systems. We propose the Adaptive Layer Positive Selection Algorithm (ALPSA) for monitoring the participating and non-participating vehicles; which are detected by appropriate detectors, generated through the algorithm. The algorithm works in layers and has two phases. Prior to the algorithm, we present a mobility model to generate the metrics for appropriate clustering. We extensively evaluate the ALPSA where results validate the management with reduced 'similarity detection time' and better 'similarity detection rate'. The similarity detection time is the response time given to the vehicles to decide whether to join the VTL cluster or not. Therefore, reduction in this time has shown better working for VTLs. [ABSTRACT FROM AUTHOR]

A vehicular Ad hoc NETwork -VANET has been emerged as a novel application for revolutionizing the driving experience and optimizing the traffic flow control networks. The development of high efficiency and optimized routing protocols for VANET remains a challenging task because of characteristics like rapid topology changes, large scale sizes and frequent link disconnections. Hence investigation of security and privacy problems is required to be emphasized. This paper presents a robust and novel method for improving the security in VANET environment and to evaluate the performance of the proposed ODMRP (On Demand Multi Cast Routing Protocol). Hence the study utilized RSA (Rivest-Shamir-Adleman) based key generation integrated with the asymmetric key generation with AES (Advanced Encryption Standard) algorithm.This proposed trust based integrated algorithm for key generation introduces a novel roadside unit message to the base station that enables Road side units- RSU responsible for the verification of the authentication of the encrypted messages received from the vehicles as well as for the notification of the results to the vehicles. The performance analysis represented that the proposed ODMRP with the use of RSA and AES algorithm possess a better adaptation capacity to VANET network in accordance to packet delivery ratio and throughput. The results obtained from the study have been compared with the existing system and proved to be more efficient. [ABSTRACT FROM AUTHOR]

In contemporary urban areas, the construction speed of urban roads lags far behind the growth rate of the number of vehicles. The traffic delay caused by excessive vehicles is a major challenge for modern transportation systems. In this paper, we design an adaptive coordination traffic signal control system based on a three-level framework. In the framework, we propose a hierarchical strategy, which is helpful in avoiding possible offset conflicts and configuring the offsets reasonably. In addition, we establish a multi-intersection traffic signal control model with the goal of minimizing traffic delays. To solve the proposed model, we propose a new algorithm, called the Immune-Fireworks algorithm (IM-FWA), on the basis of the artificial immune and fireworks algorithms. Inspired by the antibody maintenance mechanism, diversity mechanism and communication mechanism of the artificial immune algorithm, IM-FWA can effectively overcome the shortcomings of the fireworks algorithm, such as its limited search range and lack of interaction among fireworks. The experiments show that the proposed model and algorithm have good practicability and that our control system can obtain a better signal timing schedule to effectively reduce traffic delays. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) is an integration of smart sensing devices with connection ability for ease of communication. Introducing decision-making systems (DMSs) in the IoT for request processing improves the ease of access and service reliability for mobile end users. This paper proposes a two-level DMS for user service traffic smoothing (TS) in IoT communications. The two-level decision-making (2LDM) method employs traffic-aware queuing and minimum time scheduling processes for controlling the request message flows. The decision-making algorithm is modeled on time-dependent processing for minimizing the time delay in the queuing and request scheduling. The DMS considers the attributes associated with the cloud and devices to classify the request messages to prevent resource mapping failures. The disagreement between the request processing and cloud response is resolved optimally for improving the end user communication reliability in terms of the delay and resource mapping failures. Simulations evaluate the proposed DMS performance for the following metrics: sum rate, access delay, failure probability, response latency, and queue utilization. The results indicate that the proposed TS-2LDM outperforms the existing traffic controlling methods by improving the sum rate and queue utilization with controlled delay, failure, and response time. [ABSTRACT FROM AUTHOR]

VANET is an emerging area of wireless ad-hoc networks to contribute in the success of connected vehicles projects. The extremely changeable number of mobile nodes and high mobility are challenging issues. Furthermore, this particular network has several problems in term of defining suitable schemes and protocols like rate adaptation mechanisms. The overall performance of diverse applications in VANET such as traffic control and multimedia delivery is based on the achievement ratio these networks can offer and the network throughput. Rate adaptation is an essential technique to evade the performance network degradation and to maximize the throughput by using the estimation of the present channel characteristics and determining the optimal bitrate for subsequent transmissions. Despite there are several available rate control algorithms for 802.11 WLANs standards, there are few works devoted to the rate adaptation for the standard of vehicular networks. In this paper, we compare and evaluate the existing data rate adaptation schemes in numerous vehicular environments to recognize their behavior and analyze their performance in diverse scenarios. Six algorithms were chosen for comparison using the NS-3 simulator: AARF, AARF-CD, AMRR, CARA, Onoe, and Minstrel. The simulation outcomes demonstrate that Minstrel algorithm outperforms the remaining five mechanisms in dense and dynamic situations. [ABSTRACT FROM AUTHOR]

Reinforcement learning (RL) methods learn optimal decisions in the presence of a stationary environment. However, the stationary assumption on the environment is very restrictive. In many real world problems like traffic signal control, robotic applications, etc., one often encounters situations with non-stationary environments, and in these scenarios, RL methods yield sub-optimal decisions. In this paper, we thus consider the problem of developing RL methods that obtain optimal decisions in a non-stationary environment. The goal of this problem is to maximize the long-term discounted reward accrued when the underlying model of the environment changes over time. To achieve this, we first adapt a change point algorithm to detect change in the statistics of the environment and then develop an RL algorithm that maximizes the long-run reward accrued. We illustrate that our change point method detects change in the model of the environment effectively and thus facilitates the RL algorithm in maximizing the long-run reward. We further validate the effectiveness of the proposed solution on non-stationary random Markov decision processes, a sensor energy management problem, and a traffic signal control problem. [ABSTRACT FROM AUTHOR]

Recent research in communication moves towards cyber space with modern applications such as multimedia surveillance, smart autonomous traffic control, advanced health care monitoring, industrial automation, and continuous remote environmental and structural monitoring. Such applications are extensively generates multimedia information and converse through Wireless Multimedia Sensor Networks (WMSNs). Path selection plays vital role in transmitting the multimedia data over wireless networks. Single path selection incurs routing failure due to the energy hole because of power shortage and traffic congestion. Due to energy hole in any particular node the packet gets dropped in the route from source to destination. The multipath routing algorithm selects more than one path to increase the rate of the packet delivery than the single path routing. The prediction of energy deficiency in sensor nodes is becoming over head in WSMNs. In order to improve the packet delivery and performance of the network, in this paper a Priority Based Multipath Routing Algorithm (PBMRA) is proposed. It consists of three modules: The Neighbourhood Selection identifies the neighbours; Multipath Construction constructs multiple paths from the indentified neighbours; and Priority Selection selects the high energized routes based on the priority of node attributes such as liveliness, path delay and hop count. The proposed algorithm is experimentally compared with other existing algorithms such as AODV, DSR, DSDV and OLSR. The experimental results show that the PBMRA algorithm increases the overall throughput, packet received rate and provides the reliable route than existing algorithms. [ABSTRACT FROM AUTHOR]

Because of the hierarchical significance of traffic sign images, the traditional methods do not effectively control and extract the brightness and features of layered images. Therefore, an automatic recognition algorithm for traffic signs based on a convolution neural network is proposed in this paper. First, the histogram equalization method is used to pre-process the traffic sign images, with details of the images being enhanced and contrast of the images improved. Then, the traffic sign images are recognized by a convolution neural network and the large scale structure of information in the traffic sign images are obtained by using a hierarchical significance detection method based on graphical models. Next, the area of interest in the traffic sign images are extracted by using the hierarchical significance model. Finally, the Softmax classifier is selected to classify the input feature images to realize the automatic recognition of traffic signs. Experimental results show that the proposed algorithm can control the brightness of traffic sign images, which can accurately extract image regions of interest and complete the automatic recognition of traffic signs. [ABSTRACT FROM AUTHOR]

Short-term prediction of traffic flow is one of the most essential elements of all proactive traffic control systems. The aim of this paper is to provide a model based on neural networks (NNs) for multi-step-ahead traffic prediction. NNs' dependency on parameter setting is the major challenge in using them as a predictor. Given the fact that the best combination of NN parameters results in the minimum error of predicted output, the main problem is NN optimization. So, it is viable to set the best combination of the parameters according to a specific traffic behavior. On the other hand, an automatic method—which is applicable in general cases—is strongly desired to set appropriate parameters for neural networks. This paper defines a self-adjusted NN using the non-dominated sorting genetic algorithm II (NSGA-II) as a multi-objective optimizer for short-term prediction. NSGA-II is used to optimize the number of neurons in the first and second layers of the NN, learning ratio and slope of the activation function. This model addresses the challenge of optimizing a multi-output NN in a self-adjusted way. Performance of the developed network is evaluated by application to both univariate and multivariate traffic flow data from an urban highway. Results are analyzed based on the performance measures, showing that the genetic algorithm tunes the NN as well without any manually pre-adjustment. The achieved prediction accuracy is calculated with multiple measures such as the root mean square error (RMSE), and the RMSE value is 10 and 12 in the best configuration of the proposed model for single and multi-step-ahead traffic flow prediction, respectively. [ABSTRACT FROM AUTHOR]

Due to the rapid topology change, frequent link failure, high vehicle mobility and hard delay constraints, the vehicular ad hoc network (VANET) became a hot research topic in this smart era. VANET has vast application areas including road congestion notification, parking, traffic management, smart transportation, road-side business advertisements. In all these applications, the messages should reach the target location within certain time limits. So, there must be efficient soft computing-enabled routing in VANET which meets these delay constraints. Two soft computing algorithms were proposed in this paper: First, a hybrid clustering algorithm is proposed which combines the geographic- and context-based clustering approaches. The hybrid clustering reduces the control overhead and traffic in the network. Second, the destination-aware routing protocol is proposed for inter-clustering routing which improves the overall packet delivery ratio and reduces the end-to-end delay. The performance of the proposed approach is compared with the well-known cluster-based approaches. The result shows that the proposed approach outperforms the existing approaches. [ABSTRACT FROM AUTHOR]

Traffic congestion is a major mobility problem, which generates enormous economic resources and causes serious problems for the most dense of cities. Intelligent transportation systems based on vehicular ad-doc network (VANET) communications will improve many services, expressively, related to transport, security, reliability, management and including the assistance in the reduction of traffic congestion. In this context, we propose an intelligent system based, firstly, on a new clustering technique to control and maintain the stability of routes during inter-vehicular communications, and secondly, a bio-inspired systematically conducting mobility measurement of agent, intervening in cases of traffic congestion, in order to find new routes to those offered by the global positioning system. Obviously, by providing an appropriate route selection process, such routing concept could be helpful in exchanging control messages to inform the nearest medics willing to give first aid and routing of another alert to the nearest ambulance. Thus, in order to deal with these sophisticated optimization techniques, we evaluate in this article means of simulation experiments. According to that, we have anticipated particular incidents suitable to estimate the pertinence of the proposed system. The analysis and implementation in VANET will be based on three simulators, especially, SUMO, MOVE and NS2. The results prove the effectiveness of the approach by reducing fuel consumption and $$\hbox {CO}_{2}$$ emissions along with the rest of pollutant emissions in the case of an incident. [ABSTRACT FROM AUTHOR]

The approximation of the traversal cost is a critical component of dynamic traffic assignment model. In link based traffic assignment, it assumes that the constraints sets are linear or convex and it is not realistic in general traffic networks. Comparing with the link based model, the path cost in the objective function of the path based traffic assignment model is implicitly nonlinear or non-convex, which is difficult to solve. In this paper, a path based traffic assignment model combining the generalized expansion method in M/G/c/c model with the point queue model is proposed to extend the link traversal cost to the travel cost along the path. Comparing with the link based model without considering intersection effects, this proposed path based model can take into account queuing delays between intersections and it is easy to implement. In order to validate the proposed path based model, a comparative experiment is implemented by comparing with the traditional travel cost models in Sydney traffic networks. Taking into account travel flow changes and blocking time, the proposed path based model is more effective for travellers from the uncongested traffic to congested traffic networks. In addition, the results from traffic assignment model show that the proposed model can achieve feasible results. [ABSTRACT FROM AUTHOR]

Robotic swarms are decentralized systems formed by a large number of robots. A common problem encountered in a swarm is congestion, as a great number of robots often must move towards the same region. This happens when robots have a common target, for example during foraging or waypoint navigation. We propose three algorithms to alleviate congestion: in the first, some robots stop moving towards the target for a random number of iterations; in the second, we divide the scenario in two regions: one for the robots that are moving towards the target, and another for the robots that are leaving the target; in the third, we combine the two previous algorithms. We evaluate our algorithms in simulation, where we show that all of them effectively improve navigation. Moreover, we perform an experimental analysis in the real world with ten robots, and show that all our approaches improve navigation with statistical significance. [ABSTRACT FROM AUTHOR]

Wireless network sensors and their use in traffic monitoring, traffic density determination or vehicle speed detection and classification have recently been the focus of interest for researchers. This article describes how a new sensor circuit was designed to deliver instantaneous, real-time and novel solutions as a vehicle detection system, which is more powerful than the nodes used in other studies, and gives results with smaller error margins due to its serial communication qualification. With the proposed logic algorithm, it was possible to categorise the instantaneous traffic status of a road in four levels: no traffic, mild traffic, heavy traffic and very heavy traffic. Additionally, with the nodes placed at the beginning and the end of the road, the number of vehicles per hour for a day was determined and traffic was analysed. Then, vehicles passing by were classified with a proposed classification algorithm and magnetic signature length (MSL) parameter as cars, minibuses, buses and trucks, and an accuracy rate of 95% was obtained. As the last application, the direction of motion of the vehicle on the x-axis as well as left-to-right or right-to-left directions was determined, and the result was 94% accurate. The simplicity of the proposed algorithms, the absence of any complex mathematical calculations, the low cost of the sensor node and circuit and the low power consumption of the communication system demonstrate the superiority of this system in comparison with other studies. [ABSTRACT FROM AUTHOR]

Route planning and recommendation have received significant attention in recent years. In this light, we study a novel problem of planning unobstructed paths in traffic-aware spatial networks (TAUP queries) to avoid potential traffic congestions. We propose two probabilistic TAUP queries: (1) a time-threshold query like 'what is the path from the check-in desk to the flight SK 1217 with the minimum congestion probability to take at most 45 minutes?', and (2) a probability-threshold query like 'what is the fastest path from the check-in desk to the flight SK 1217 whose congestion probability is less than 20 %?'. These queries are mainly motivated by indoor space applications, but are also applicable in outdoor spaces. We believe that these queries are useful in some popular applications, such as planning unobstructed paths for VIP bags in airports and planning convenient routes for travelers. The TAUP queries are challenged by two difficulties: (1) how to model the traffic awareness in spatial networks practically, and (2) how to compute the TAUP queries efficiently under different query settings. To overcome these challenges, we construct a traffic-aware spatial network G( V, E) by analyzing uncertain trajectories of moving objects. Based on G( V, E), two efficient algorithms are developed to compute the TAUP queries. The performances of TAUP queries are verified by extensive experiments on real and synthetic spatial data. [ABSTRACT FROM AUTHOR]

In this paper, we brought out a novel pedestrian detection framework for the advanced driver assistance system of mobile platform under the normal urban street environment. Different from the conventional systems that focus on the pedestrian detection at near distance by interfusing multiple sensors (such as radar, laser and infrared camera), our system has achieved the pedestrian detection at all (near, middle and long) distance on a normally driven vehicle (1-40 km/h) with monocular camera under the street scenes. Since pedestrians typically exhibit not only their human-like shape but also the unique human movements generated by their legs and arms, we use the spatio-temporal histogram of oriented gradient (STHOG) to describe the pedestrian appearance and motion features. The shape and movement of a pedestrian will be described by a unique feature produced by concatenating the spatial and temporal histograms. A STHOG detector trained by the AdaBoost algorithm will be applied to the images stabilized by the structure from motion (SfM) algorithm with geometric ground constraint. The main contributions of this work include: (1) ground constraint with monocular camera to reduce the computational cost and false alarms; (2) preprocessing by stabilizing the successive images captured from mobile camera with the SfM algorithm; (3) long-distance (maximum 100 m) pedestrian detection at various velocities (1-40 km/h). Through the extensive experiments under different city scenes, the effectiveness of our algorithm has been proved. [ABSTRACT FROM AUTHOR]

Traffic lights are installed at intersections mostly for traffic management. Traffic signals turn on during the amount of time determined. Intelligent traffic management systems emerge as a need to handle the dynamicity of traffic. These systems are first implemented on simulators in order to mimic the real life situations before realization. Yet, we have implemented a real time traffic simulator with an adaptive fuzzy inference algorithm that arranges the foreseen light signal duration. It changes the time duration of lights depending on waiting vehicles behind green and red lights at crossroad. The simulation has also been supported with real time graphical visualization. Given a scenario, it creates random traffic flows according to specified parameters. Next, obtained results have been interpreted in the simulation environment. According to inferences from adaptive environment, TSK (Takagi-Sugeno-Kang) and Mamdani models have also been implemented to give baselines for verification. Several experiments have been conducted and compared against classical techniques such as Webster () Road research technical paper No 39 and HCM () TRB, special report 209, statistically to demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Routing configurations that have been optimized for a nominal traffic scenario often display significant performance degradation when they are subjected to real network traffic. These degradations are due to the inherent sensitivity of classical optimization techniques to changes in model parameters combined with the significant traffic variations caused by demand fluctuations, component failures and network reconfigurations. In this paper, we review important sources for traffic variations in data networks and describe tractable models for capturing the associated traffic uncertainty. We demonstrate how robust routing settings with guaranteed performance for all foreseen traffic variations can be effectively computed via memory efficient iterative techniques and polynomial-time algorithms. The techniques are illustrated on real data from operational IP networks. [ABSTRACT FROM AUTHOR]

This investigation addresses an important and difficult combinatorial optimization problem in the design and management of telecommunication systems known as the path assignment problem. The path assignment problem is specified by a set of demands on a network with given link capacities. Each demand must be assigned to exactly one routing path in such a way that the total amount of traffic routed over any link does not exceed that link's capacity. Given a network and a path assignment, the problem of interest is to maximize the available bandwidth (throughput) for a new demand. Network managers are concerned with the quality of service provided by their networks, and so they are reluctant to make major changes to an operating network that may inadvertently result in service disruptions for numerous clients simultaneously. Therefore, the objective of this investigation is to develop and test optimization models and algorithms that produce a series of throughput-improving modifications to the original path assignment. This allows network managers to implement the improved routing in stages with minimal changes to the overall routing plan between any two consecutive stages. Although the procedure may only reroute a few demands at each stage, the routing after the last stage should be as close as possible to an optimal routing. That is, it must maximize the throughput for the new demand. We present integer programming models and associated solution algorithms to maximize the throughput with a sequence of incremental path modifications. The algorithms were implemented with the AMPL modeling language and the CPLEX ILP solver, and tested on a family of five different data sets based on a European network widely studied in the literature. Empirical results show that the incremental approach finds near-optimal results within reasonable limits on CPU time. [ABSTRACT FROM AUTHOR]

This paper addresses the toll pricing problem in which the objective is to minimize the number of required toll facilities in a traffic network. The problem is shown to be NP-hard. To obtain a solution in a reasonable time, an effective metaheuristic algorithm is developed. The algorithm uses a local search technique in which the neighborhood function employs the dynamic slope scaling procedure to deal with the fixed charge nature of the objective function. Numerical results from 50 randomly generated and three real networks are reported. [ABSTRACT FROM AUTHOR]

We discuss models and algorithms of distributing traffic flows in the network of a large city or an algomeration. We provide comparative analysis of different algorithms for finding an equilibrium distribution in a transportation network. We discuss the problem of ambiguity in distributing correspondences by the paths in equilibrium and the use of entropy models to avoid this ambiguity. [ABSTRACT FROM AUTHOR]

The ever-increasing volume of spatial data has greatly challenged our ability to extract useful but implicit knowledge from them. As an important branch of spatial data mining, spatial outlier detection aims to discover the objects whose non-spatial attribute values are significantly different from the values of their spatial neighbors. These objects, called spatial outliers, may reveal important phenomena in a number of applications including traffic control, satellite image analysis, weather forecast, and medical diagnosis. Most of the existing spatial outlier detection algorithms mainly focus on identifying single attribute outliers and could potentially misclassify normal objects as outliers when their neighborhoods contain real spatial outliers with very large or small attribute values. In addition, many spatial applications contain multiple non-spatial attributes which should be processed altogether to identify outliers. To address these two issues, we formulate the spatial outlier detection problem in a general way, design two robust detection algorithms, one for single attribute and the other for multiple attributes, and analyze their computational complexities. Experiments were conducted on a real-world data set, West Nile virus data, to validate the effectiveness of the proposed algorithms. [ABSTRACT FROM AUTHOR]

Service providers rely on the management systems housed in their Network Operations Centers (NOCs) to remotely operate, monitor and provision their data networks. Lately there has been a tremendous increase in management traffic due to the growing complexity and size of the data networks and the services provisioned on them. Traffic engineering for management flows is essential for the smooth functioning of these networks to avoid congestion, which can result in loss of critical data such as billing records, network alarms, etc. As is the case with most intra-domain routing protocols, the management flows in many of these networks are routed on shortest paths connecting the NOC with the service provider’s POPs (points of presence). This collection of paths thus forms a “confluent” tree rooted at the gateway router connected to the NOC. The links close to the gateway router may form a bottleneck in this tree resulting in congestion. Typically this congestion is alleviated by adding layer two tunnels (virtual links) that offload the traffic from some links of this tree by routing it directly to the gateway router. The traffic engineering problem is then to minimize the number of virtual links needed for alleviating congestion. In this paper we formulate a traffic engineering problem motivated by the above mentioned applications. We show that the general versions of this problem are hard to solve. However, for some simpler cases in which the underlying network is a tree, we design efficient algorithms. In particular, we design fully polynomial-time approximate schemes (FPTAS) for different variants of this problem on trees. We use these algorithms as the basis for designing efficient heuristics for alleviating congestion in general (non-tree) service provider network topologies. [ABSTRACT FROM AUTHOR]

The lack of effective and efficient schedule-based pathfinding algorithms for transit networks has limited the application of GIS in transit trip planning services. This paper introduces a schedule-based path finding algorithm for transit networks. Based on a pattern-centered spatiotemporal transit network model, the algorithm searches the network by following route patterns. A pattern is a spatial layout of a route in transit terminology. A route usually has many patterns to serve various locations at different times. This path search algorithm is significantly different from traditional shortest path algorithms that are based on adjacent node search. By establishing a set of lemmas and theorems the paper proves that paths generated by the PFS algorithm are schedule-coordinated fastest paths for trips with given constraints. After analyzing computation and database query complexities of the algorithm the paper indicates that the PFS is efficient in computation and database query. Finally, effectiveness and efficiency of the algorithm are demonstrated by implementations in GIS-based online transit trip planners in Wisconsin, US. [ABSTRACT FROM AUTHOR]

ÀRouting protocols can decide for data packets which route is reachable and co-optimal, and may cause data packets to swarm into certain links, thus causing congestion on those links. General traffic engineering (GTE) technology provides ER-LSP/CR-LSP in MPLS networks to avoid this kind of congestion. However, GTE takes only the current data flow into account and establishes an ER-LSP/CR-LSP for this current data flow in order to guarantee QoS. Although this could resolve the issue raised by routing protocols, it may also waste some resource. In this article we focus on optimization of traffic engineering and propose an automatic traffic balance algorithm based on GTE technology. [ABSTRACT FROM AUTHOR]

This paper describes an improvement of borrowing channel assignment (BCA) for patterned traffic load by using the short-term traffic prediction ability of cellular probabilistic self-organizing map (CPSOM). The fast growing cellular mobile systems demand more efficient and faster channel allocation techniques today. In case of patterned traffic load, the traditional BCA methods are not efficient to further enhance the performance because heavy-traffic cells cannot borrow channels from their neighboring cells with light or medium traffic that may have unused nominal channels. The performance can be increased if the short-term traffic load can be predicted. The predicted results can then be used for channel re-assignment. Therefore, the unused nominal channels of the light-or-medium-traffic cells can be transferred to the heavy-traffic cells that need more nominal channels. In this paper, CPSOM is used online for traffic prediction. In this sense, the proposed CPSOM-based BCA method is able to enhance the performance for patterned traffic load compared with the traditional BCA methods. Simulation results corroborate that the proposed method enables the system to work with better performance for patterned traffic load than the traditional BCA methods. [ABSTRACT FROM AUTHOR]

A mathematical model for the distributed traffic control algorithm used in modern data transfer networks is designed and distributions of the important characteristics of the algorithm are derived. Numerical examples are given. [ABSTRACT FROM AUTHOR]

In this paper, an off-line traffic engineering algorithm is presented that optimizes the single-path routing of Label Switched Paths in a Differentiated Services IP domain by means of explicit, Multi-Protocol Label Switching controlled nonshortest paths. This algorithm allows traffic engineering up to 2500 traffic trunks in flat networks with sizes up to 150 nodes while supporting protection, pre-emption, quality-of-service, oversubscription, and resource class affinity. The algorithm with proper extensions can be applied to hierarchical networks, thus increasing the scalability properties for network size with a factor of about 50. First the single-area algorithm is detailed, then the concept and implementation of hierarchy is introduced for inter-area traffic engineering. These topics are illustrated with simulation results. KEY WORDS: Traffic engineering; hierarchy; differentiated services; quality-of-service; explicit routing. [ABSTRACT FROM AUTHOR]