PLATO: A Generic Modeling Technique for Optical Packet-Switched Networks

A photonic 2x2 node architecture for synchronous all-optical packet switching networks, able to process ultra-fast packet signals is presented. All node functions (label recognition and processing, contention detection and resolution, switch control, actual switching, and regeneration) are optically performed. Combinations of the proposed 2times2 element can be used in order to obtain more complex NtimesN photonic nodes. Implementations of all subsystems needed to realize the describe 2times2 photonic node are reported, and different solutions for several blocks are compared in order to optimize the node performances.

This paper aims the solution of the reroute sequence planning problem for protected traffic flows. This problem arises when a service provider recalculates the path set by a global optimization tool in order to achieve a better resource utilization. In this case a sequence of the one-by-one reconfiguration of the traffic flows from their original paths to the optimized paths has to be found, with the constraint that the link capacities should not be violated at any time during the rerouting process. This optimization problem is related to discrepancy theory and it is NP-complete. It is computationally hard in realworld situations because of the large amount of routers and traffic flows in the network, therefore exact and approximation algorithms have little practical relevance. We present a number of heuristic approaches, which are tested on various network situations. We assume generalized multi-protocol label switching context but the methods can be applied for other types of networks as well. The results show that in most cases these methods are appropriate for calculating the reroute sequence, mainly when the objective of the path optimization is load balancing.

The explosion of Internet traffic has brought about an acute need for high-performance networks. The bandwidth available on a single fiber has increased dramatically by the wavelength division multiplexing (WDM) technologies. How to use the huge bandwidth flexibly and efficiently is one of the hot topics of optical networks. It is high time that the high-performance switches/routers should be designed. All-optical switching network is a networking platform with effective and agile utilization of the available optical bandwidth. Some promising optical switching networks, such as optical packet switched, optical burst switched, and optical label switched networks are proposed. The benefit of these networks compared to the existing optical WDM networks rises from the higher network utilization at sub-wavelength granularity and from the supporting of more various services. However, there are still a lot of challenges. One challenge of them is contention. Due to the fact that the viable optical random access memory is not available in the optical domain so far, there exists a real possibility that packets may contend with one another at a switching node. In this paper, a novel node architecture called packet calking switch is proposed for all-optical switching networks. The proposed architecture is accompanied by a signaling protocol for packet-based traffic handling. This proposed node architecture is introduced into a simple network and a mesh network through simulation. The simulation results show that it is suitable for prioritized packet transmission. And it is more cost-effective than the existing node architectures because it requires much smaller optical switches and wavelength conversion to achieve nearly the same packet drop performance as the node configured partial wavelength conversion.

This paper presents a comparative study of contention-resolution schemes based on wavelength, time, and space domains in an unslotted optical packet-switched network with a large irregular mesh topology consisted of 15 nodes. For the first time, to the best of our knowledge, we investigated the effect of selective deflection and limited wavelength conversion. Features and performances of different combinational schemes are listed and compared. While simulation results show the effectiveness of wavelength conversion for resolving contentions over optical buffering and space deflection, physical explanations of the different effectiveness in resolving contentions of these schemes are also discussed.

To address the issue of spatiotemporal illusion in short-term traffic flow prediction and deeply explore the underlying short-term traffic flow network characteristics, a traffic flow prediction model that combines long-term spatiotemporal heterogeneity with short-term spatiotemporal features is proposed. In the long-term spatiotemporal branch, the Transformer structure is employed, and a self-supervised masking mechanism is utilized to pretrain the heterogeneity in long-term temporal and spatial dimensions separately. Additionally, a spatiotemporal adaptive module is designed, which adapts to and guides short-term traffic flow prediction across time series and traffic flow networks. In the short-term spatiotemporal branch, a recurrent neural ordinary differential equation (ODE) module is devised. This module is capable of continuously and dynamically adjusting short-term spatiotemporal features, better capturing and exploring potential short-term spatiotemporal characteristics. Through multiple cycles, this module gradually and accurately extracts and compresses road network features, integrates the adapted spatiotemporal heterogeneity, and reconstructs future short-term traffic flows in the decoder. Experiments are conducted on four traffic flow and two traffic speed datasets, showing that compared to traditional time series models, the proposed model’s prediction accuracy indicators have relatively improved by 45.09%, 39.14%, and 0.47% on average; compared to recurrent neural network (RNN) series models, the improvements are 18.91%, 15.77%, and 0.18% on average; compared to graph convolution series models, the improvements are 21.31%, 16.65%, and 0.21% on average; and compared to Transformer series models, the improvements are 6.57%, 6.23%, and 0.05% on average. The model’s general applicability and good performance in transportation speed scenarios were verified through a multi-step experiment conducted on the transportation speed dataset.

All-optical core node modeling and optimization using hybrid wavelength conversion for QoS provision

Multi-wavelength optical buffer will be a key element in Wavelength Division Multiplexing (WDM) system and all-optical packet-switched networks. In this paper we have presented and demonstrated the dual-wavelength signal buffering in Dual-Loop Optical Buffer (DLOB) based on Semiconductor Optical Amplifier (SOA). The dual-wavelength packets are written in and read out of DLOB by single control signal. As the power of the control signal increasing, the output of the signals is better. In simulation confirmed by experiments, we obtained suitable control power, where the gain and phase-shift difference between "1" bit and "1+1" bit is minimum. More than 12 cycles' buffering results have been obtained and the power loss is lower than 4db.

Network traffic flow is an aggregated result of a huge number of travelers' route choices, which is influenced by the travelers' choice behaviors. So day-to-day traffic flow is not static, but presents a complex and tortuous day-to-day dynamic evolution process. Studying day-to-day dynamic evolution of network traffic flow, we can not only know whether the traffic network equilibrium can be reached and how the process is achieved, but also can know what phenomenon will occur in the evolution of network traffic flow if the equilibrium is not reached. In a real traffic system, taking day as scale unit, the day-to-day network traffic demand is variable and changes with everyday's traffic network state. The travelers' route choices are also influenced by the previous day's behaviors and network state. Then, will the day-to-day network traffic flow evolution be stable? If it is unstable, when will bifurcation and chaos occur? In this paper we discuss the day-to-day dynamic evolution of network traffic flow with elastic demand in a simple two-route network. The dynamic evolution model of network traffic flow with elastic demand is formulated. Based on a nonlinear dynamic theory, the existence and uniqueness of the fixed point of dynamic evolution model are proved, and an equilibrium stability condition for the dynamic evolution of network traffic flow with elastic demand is derived. Then, the evolution of network traffic flow is investigated through numerical experiments by changing the three parameters associated with travelers, which are the sensitivity of travelers' travel demand to travel cost, the randomness of travelers' route choices, and travelers' reliance on the previous day's actual cost. Our findings are as follows. Firstly, there are three kinds of final states in the evolution of network traffic flow: stability and convergence to equilibrium, periodic motion and chaos. The final state of the network traffic flow evolution is related to the above three parameters. It is found that under certain conditions the bifurcation diagram of the network traffic flow evolution reveals a complicated phenomenon of period doubling bifurcation to chaos, and then period-halving bifurcation. Meanwhile, the chaotic region is interspersed with odd periodic windows. Moreover, the more sensitive to cost the travelers' travel demand the more likely the system evolution is to be stable. The smaller the randomness of travelers' route choices, the less likely the system evolution is to be stable. The lower the degree of travelers' reliance on the previous day's actual cost, the more likely the system evolution is to be stable.

Recent development in ITS (intelligent transportation systems) methods and technologies has moved traffic operating systems from passive to proactive control and management, where real-time and accurate traffic flow information is critical to actual implementation. So far many algorithms have been proposed for traffic network flow forecasting, but problems in accuracy and timeliness still remain to be the major obstacle for their successful applications. For example, presumed human travel habit and vehicle turning probabilities at intersections have greatly limited the use of dynamic assignment algorithm. In order to improve the forecasting and real-time responsiveness, a new algorithm based on data mining which can do association rules mining and association analysis is proposed here for predicting traffic network flow. Simulation results using Corsim 5.0 have demonstrated effectiveness of the new algorithm in both accuracy and timeliness.

Spatial temporal incidence dynamic graph neural networks for traffic flow forecasting

Traditional queueing models for traffic flows in communications networks are based on Markovian assumptions. However, recent studies within Bellcore of large sets of real-time network traffic measurements have revealed that traffic in computer and emerging high-speed networks has features that are more accurately and more efficiently described in terms of fractal models, rather than traditional Markovian models. This paper briefly reviews these measurement studies, and motivates the application of fractals to describe and analyze traffic flows in modern communications networks.

On-line distributed prediction of traffic flow in a large-scale road network

Comparison in power consumption of static and dynamic WDM networks

We consider a processing system, composed of several parallel queues and a processor, which operates in a time-varying environment that fluctuates between various states or modes. The service rate at each queue depends on the processor bandwidth allocated to it, as well as the environment mode. Each queue is driven by a job traffic flow, which may also depend on the environment mode. Dynamic processor scheduling policies are investigated for maximizing the system throughput, by adapting to queue backlogs and the environment mode. We show that allocating the processor bandwidth to the queues, so as to maximize the projection of the service rate vector onto a linear function of the workload vector, can keep the system stable under the maximum possible traffic load. The analysis of the system dynamics is first done under very general assumptions, addressing rate stability and flow conservation on individual traffic and environment evolution traces. The connection with stochastic stability is later discussed for stationary and ergodic traffic and environment processes. Various extensions to feed-forward networks of such nodes, the multi-processor case, etc., are also discussed. The approach advances the methodology of trace-based modelling of queueing structures. Applications of the model include bandwidth allocation in wireless channels with fluctuating interference and allocation of switching bandwidth to traffic flows in communication networks with fluctuating congestion levels.

Two statistical applications for estimation and prediction of flows in traffic networks are presented. In the first, the number of route users are assumed to be independent α-shifted gamma Γ(θ, λ0) random variables denoted H(α, θ, λ0), with common λ0. As a consequence, the link, OD (origin-destination) and node flows are also H(α, θ, λ0) variables. We assume that the main source of information is plate scanning, which permits us to identify, totally or partially, the vehicle route, OD and link flows by scanning their corresponding plate numbers at an adequately selected subset of links. A Bayesian approach using conjugate families is proposed that allows us to estimate different traffic flows. In the second application, a stochastic demand dynamic traffic model to predict some traffic variables and their time evolution in real networks is presented. The Bayesian network model considers that the variables are generalized Beta variables such that when marginally transformed to standard normal become multivariate normal. The model is able to provide a point estimate, a confidence interval or the density of the variable being predicted. Finally, the models are illustrated by their application to the Nguyen Dupuis network and the Vermont-State example. The resulting traffic predictions seem to be promising for real traffic networks and can be done in real time.