Traffic Scheduling Problem Research Articles

Wavelet and VMD enhanced traffic forecasting and scheduling method for edge cloud networks

With the proliferation of Intelligent applications, more and more organizations migrate their applications from cloud to edge cloud network to reduce the latency of applications and alleviate the workload of cloud. When the network congestion occurs, network monitoring and detection system may disable, and edge cloud network will be vulnerable to be attacked. Traffic forecasting can identify the traffic patterns in advance, and dynamically allocate network resources to decrease latency of applications and avoid security risks caused by network congestion. Therefore, we propose a network scheduling framework WVNF (Wavelet VMD Based Network Flow Management) based on traffic prediction, which utilizes neural networks to forecast network traffic and deploys route strategies to optimize network scheduling. Specifically, in order to accurately forecast network traffic, we propose a neural network model, named TSWNet (Traffic Sequence Wavelet Network). TSWNet uses VMD (variational mode decomposition) to decompose time series and extract signal structure information on different time scales, and adopts wavelet transformation to extract the local and global features of the traffic sequence in the time and frequency domain. In addition, we model this traffic scheduling problem and propose a route strategy, which utilizes the result of TSWNet to find the best path. In extensive tests, TSWNet significantly outperformed existing models, reducing MSE and MAE by up to 48.8% and 27.8% respectively, demonstrating its effective traffic prediction and network scheduling capabilities.

Mixed-Criticality Traffic Scheduling in Time-Sensitive Networking Using Multiple Combinatorial Packing Based on Free Time Domain

Time-sensitive networking (TSN) is considered an ideal solution to meet the transmission needs of existing industrial production methods. The traffic scheduling problem of TSN is an NP-hard problem. The traditional traffic scheduling algorithms can lead to issues such as significant computational time consumption and traffic congestion, which are not conducive to the rapid and high-quality deployment of TSN. To simplify the complexity of TSN schedule table generation, the paper studies the scheduling problem of mixed critical traffic in TSN. Using a combinatorial packing traffic scheduling algorithm based on unoccupied space (CPTSA-US), a scheduling table for TSN traffic transmission is generated, proving the feasibility of transforming the TSN traffic scheduling problem into a packing problem. In addition, the initial packing algorithm and traditional traffic scheduling algorithm can cause traffic accumulation, seriously affecting network performance. This paper proposes a mixed-critical traffic scheduling algorithm based on free time domain (MCTSA-FTD), which further partitions the packing space transformed by the time domain. And performs multiple packing of traffic based on the partitioned packing space and generates the TSN schedule table according to the reverse transformation of the packing results. The simulation results show that compared to the CPTSA-US and the traditional traffic scheduling solution algorithm SMT (Satisfiability Modulo Theory), the schedule table generated by the MCTSA-FTD significantly improves the delay, jitter, and packet loss of BE flows in the network while ensuring the transmission requirements of TT flows. This can effectively enhance the transmission performance of the network.

Reinforcement Learning-Based Particle Swarm Optimization for End-to-End Traffic Scheduling in TSN-5G Networks

With the rapid development of the Industrial Internet of Things (IIoT), massive IIoT devices connect to industrial networks via wired and wireless. Furthermore, industrial networks pose new requirements on communications, such as strict latency boundaries, ultra-reliable transmission, and so on. To this end, time-sensitive networking (TSN) embedded fifth-generation (5G) wireless communication technology (i.e., TSN-5G networks), is considered the most promising solution to address these challenges. TSN can provide deterministic end-to-end latency and reliability for real-time applications in wired networks. 5G supports ultra-reliable and low-latency communications (uRLLC), providing increased flexibility and inherent mobility support in the wireless network. Thus, the integration of TSN and 5G provides numerous benefits, including increased flexibility, lower commissioning costs, and seamless interoperability of various devices, regardless of whether they use a wired or wireless interface. Nonetheless, the potential barriers between the TSN and 5G systems, such as clock synchronization and end-to-end traffic scheduling, are inevitable. Time synchronization has been studied in many works, so this paper focuses on the end-to-end traffic scheduling problem in TSN-5G networks. We propose a novel integrated TSN and 5G industrial network architecture, where the 5G system acts as a logical TSN-capable bridge. Based on this network architecture, we design a Double Q-learning based hierarchical particle swarm optimization algorithm (DQHPSO) to search for the optimal scheduling solution. The DQHPSO algorithm adopts a level-based population structure and introduces Double Q-learning to adjust the number of levels in the population, which evades the local optimum to further improve the search efficiency. Extensive simulations demonstrate that the DQHPSO algorithm can increase the scheduling success ratio of time-triggered flows compared to other algorithms.

Reinforcement Learning-Based Delay-Aware Path Exploration of Parallelized Service Function Chains

The parallel processing of the service function chain (SFC) is expected to provide better low-delay service delivery, because it breaks through the bottleneck of traditional serial processing mode in which service delay increases linearly with the SFC length. However, the provision of parallelized SFC (PSFC) is much more difficult due to the unique construction of PSFCs, inevitable parallelization overhead, and delay balancing requirement of PSFC branches; therefore, existing mechanisms for serial SFC cannot be directly applied to PSFC. After a comprehensive review of recent related work, we find that traffic scheduling mechanisms for PSFCs is still lacking. In this paper, a delay-aware traffic scheduling mechanism (DASM) for PSFCs is proposed. DASM first transforms PSFC into several serial SFCs by releasing the upstream VNF constraints so as to handle them independently while keeping their parallel relations. Secondly, DASM realizes delay-aware PSFC traffic scheduling based on the reinforcement learning (RL) method. To the best knowledge of the authors, this is the first attempt to address the PSFC traffic scheduling problem by transforming them into independent serial SFCs. Simulation results show that the proposed DASM outperforms the advanced PSFCs scheduling strategies in terms of delay balance and throughput.

Pheromone Incentivized Intelligent Multipath Traffic Scheduling Approach for LEO Satellite Networks

Low Earth Orbit (LEO) satellite networking has been an indispensable and promising concept for extending the Internet coverage of future space-air-ground integrated networks to oceanic and remote airspace. However, the topology dynamics of the LEO Satellite Network (LEO-SN) for network state perception (Li <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">et al.</i> , 2019) and the intermittent nature of the Inter-Satellite Links (ISLs) for multipath routing discovery (Wang <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">et al.</i> , 2019, Jiang <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">et al.</i> , 2019) both induce new complicated challenges to multipath traffic scheduling for the sake of improving the utility of the LEO-SN facility (Song <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">et al.</i> , 2014, Zhang <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">et al.</i> , 2018, and Yang <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">et al.</i> , 2020). Motivated by these challenges, this paper aims to develop an AI aided intelligent multipath traffic scheduling approach for bolstering autonomous and efficient communications of LEO-SN. To achieve this, we formulate the multipath traffic scheduling problem into a pheromone incentivized Markov Decision Process (MDP) by considering ant routing protocol and adapting pheromone to LEO-SN. Employing enhanced pheromone characterizing network state, we propose ant-inspired multipath routing discovery, which is capable of promptly discovering routing paths available in the dynamic topology. To improve the utility of these discovered routing paths, we employ deep deterministic policy gradient into the pheromone-incentivized MDP-based scheduling problem to derive an intelligent multipath traffic scheduling strategy. The experimental results are further presented to show the achievable performance improvement.

Min-Time Coverage in Constricted Environments: Problem Formulations and Complexity Analysis

This work deals with the task allocation and robot routing problems that arise in a class of networked mobile robot systems. The defining characteristics of these systems are: 1) the constricting nature of their operational environment and 2) the need to coordinate the robot motion in order to maintain full connectivity of a multihop wireless communication network connecting the robots with each other and a master controller that supervises the entire operation. These two elements give rise to resource allocation structures and traffic dynamics that transcend the state of the art of the corresponding theory and challenge our current understandings and insights for these dynamics and their effective management. We provide: 1) a systematic introduction of the considered problems and of the elements that differentiate them from similar task allocation and traffic scheduling problems already studied in the literature; 2) complete analytical characterizations of these problems in the form of mathematical programming formulations; and 3) a formal analysis of the worst-case computational complexity of these problems and of certain factors that determine this complexity. Furthermore, the presented results define a base for the development of solution approaches to the considered problems able to effectively and systematically manage the identified tradeoff between the operational efficiency of the derived solutions and their computational cost.

Equitable Vessel Traffic Scheduling in a Seaport

In the global maritime transportation network, the on-time performance of cargo transportation depends largely on the service capacity and accessibility of seaports. When opportunities for infrastructure expansions are not available, seaport congestion mitigation may require effective scheduling of the vessel traffic in the port waters. Although existing works on vessel traffic scheduling focus on minimizing vessel delays, this paper studies a novel vessel traffic scheduling problem that aims to address the inter-shipping line equity issue. We develop a lexicographic optimization model that accounts for two conflicting performance measures: efficiency, which favors minimizing total vessel delay; and equity, which favors balancing the impacts of delays fairly among shipping lines. Our model allows the port operator to quantify the efficiency-equity tradeoff and make the best vessel traffic scheduling decisions. For solving the model, we develop an effective two-stage solution method in which the first stage solves two single-objective models to obtain the maximum system efficiency and equity, whereas the second stage trades between efficiency and equity and seeks the best compromise between the two conflicting objectives. We apply our model and solution method on instances generated from the operational data of the Port of Shanghai. Our computational results show that an efficiency-oriented model can lead to highly inequitable traffic plans, whereas inter-shipping line equity can be achieved at only mild losses in efficiency, indicating that the consideration of inter-shipping line equity can lead to satisfactory service at both the vessel level and the shipping line level.

ScaleDRL: A Scalable Deep Reinforcement Learning Approach for Traffic Engineering in SDN with Pinning Control

As modern communication networks become more complicated and dynamic, designing a good Traffic Engineering (TE) policy becomes difficult due to the complexity of solving the optimal traffic scheduling problem. Traditional methods usually design a fixed model of the network traffic and solve an objective function to get a TE policy, which cannot ensure the solution efficiency.The emerging Deep Reinforcement Learning (DRL) together with the Software-Defined Networking (SDN) technologies provide us with a chance to design a model-free TE scheme through Machine Learning (ML). However, existing DRL-based TE solutions are all faced with a scalability problem, i.e., the solution cannot be applied to large networks. In this paper, we propose to combine the control theory and DRL technology to achieve an efficient network control scheme for TE. The proposed scheme ScaleDRL employs the idea from the pinning control theory to select a subset of links in the network and name them critical links. Based on the traffic distribution information collected by the SDN controller, we use a DRL algorithm to dynamically adjust a set of link weights for the critical links. Through a weighted shortest path algorithm, the forwarding paths of the network flows can be dynamically adjusted using the dynamic link weights. The packet-level simulation shows that ScaleDRL reduces the average end-to-end transmission delay by up to 39% compared to the state-of-the-art DRL-based TE scheme in different network topologies.

Equitable Vessel Traffic Scheduling in a Seaport

In the global maritime transportation network, the on-time performance of cargo transportation depends largely on the service capacity and accessibility of seaports. When opportunities for infrastructure expansions are not available, seaport congestion mitigation may require effective scheduling of the vessel traffic in the port waters. While existing works on vessel traffic scheduling focus on minimizing vessel delays, this paper studies a novel vessel traffic scheduling problem that aims to address the inter-shipping line equity issue. We develop a parameterized lexicographic optimization model that takes into account two conflicting performance measures; namely, efficiency, which favors minimizing total vessel delay, and equity, which favors balancing the impacts of delays fairly among shipping lines. Our model allows the port operator to quantify the efficiency-equity trade-off and make the best vessel traffic scheduling decisions. For solving the model, we develop an effective two-stage solution method in which the first stage solves two single-objective models to obtain the maximum system efficiency and equity, while the second stage trades between efficiency and equity and seeks the best compromise between the two conflicting objectives. We apply our model and solution method on instances generated from the operational data of the Port of Shanghai. Our computational results show that an efficiency-oriented model can lead to highly inequitable traffic plans, while inter-shipping line equity can be achieved at only mild losses in efficiency, indicating that the consideration of inter-shipping line equity can lead to satisfactory service at both the vessel level and the shipping line level.

A Scalable Deep Reinforcement Learning Approach for Traffic Engineering Based on Link Control

As modern communication networks are growing more complicated and dynamic, designing a good Traffic Engineering (TE) policy becomes difficult due to the complexity of solving the optimal traffic scheduling problem. Deep Reinforcement Learning (DRL) provides us with a chance to design a model-free TE scheme through machine learning. However, existing DRL-based TE solutions cannot be applied to large networks. In this article, we propose to combine the control theory and DRL to design a TE scheme. Our proposed scheme ScaleDRL employs the idea from the pinning control theory to select a subset of links in the network and name them critical links. Based on the traffic distribution information, we use a DRL algorithm to dynamically adjust the link weights for the critical links. Through a weighted shortest path algorithm, the forwarding paths of the flows can be dynamically adjusted. The packet-level simulation shows that ScaleDRL reduces the average end-to-end transmission delay by up to 39% compared to the state-of-the-art in different network topologies.

An MPC Scheme for Traffic Coordination in Open and Irreversible, Zone-Controlled, Guidepath-Based Transport Systems

Zone-controlled, guidepath-based transport system (ZC-GBTS) is a modeling abstraction that has been used extensively for the modeling of the safe interaction of a number of agents that circulate in a constricted medium. The traffic scheduling problem in these transport systems is very hard, and in some recent work of ours, we have proposed a model predictive control (MPC) scheme for simplifying this problem. The detailed implementation of this MPC scheme depends on certain structural and operational properties of the underlying ZC-GBTS. In this article, we detail the aforementioned MPC scheme for a ZC-GBTS subclass that is characterized as “open and irreversible”; the presented results leverage some earlier similar developments of ours for the subclass of “open and reversible” ZC-GBTS.

Path‐flow matching: Two‐sided matching and multiobjective evolutionary algorithm for traffic scheduling in cloud data* center network

AbstractImproving the operational efficiency of data center has always been an important direction for the development of ICT. In this paper, we apply two‐sided matching decision‐making process in game theory to traffic scheduling problem in data center network. From the perspective of matching between flow and path, the traffic scheduling is properly arranged. We first propose and model the path‐flow matching problem, considering the preference ordering, then formulate the problem as a multiobjective optimization problem with the target to ensure the stability and satisfaction from the matching scheme, and design a preference‐based path‐flow ordering method Extended PIAS, and finally propose a lightweight scheduling algorithm LinkGame based on multiobjective evolutionary algorithm. Compared with the previous scheduling methods (ECMP, Hedera, and Fincher), experiment results demonstrate that LinkGame can simultaneously consider the stability and satisfaction of the matching results, with improved bandwidth utilization and flow completion time.

A Hierarchical Heuristic Approach for Solving Air Traffic Scheduling and Routing Problem With a Novel Air Traffic Model

Efficient flight routing and scheduling play an important role in air traffic flow management, which aims to maximize the utilization of airport and enroute capacities to ensure safety and efficiency of air transportation. In this paper, we first propose a novel discrete-time flow dynamic model for an air traffic network, consisting of airports, waypoints, and air links, upon which we formulate an air flow routing and scheduling problem as an integer linear programming problem. Considering the NP-hard nature of the problem, we present a novel hierarchical flow routing and scheduling approach, where the hierarchical architecture is derived naturally from the network containment relationship, and computation is carried out in a bottom-up manner, which relies on an incremental strategy. On the resulting flow routes and schedules, a heuristic algorithm is carried out to determine flight plans for individual aircrafts. The effectiveness of the proposed hierarchical approach is illustrated by air traffic data in four flight information regions in the association of Southeast Asian nations.

The seaport traffic scheduling problem: Formulations and a column-row generation algorithm

Traffic congestion in seaports can lead to uncontrolled execution of berth plans, causing severe vessel delays and long waiting times. In this paper, we schedule the vessel traffic of a seaport by optimizing the utilization of the navigation channel and the anchorage areas in the terminal basin. We model the traffic scheduling problem as a mixed integer linear program (MILP), which takes as inputs the physical layout of a seaport and the berth plans devised by the terminal operators, to minimize the berthing and departure delays of vessels and the number of vessels that cannot berth or depart successfully. We reformulate the MILP into a more compact set-partitioning formulation, develop a column generation algorithm for solving the problem, and propose three performance enhancement strategies, namely, a row generation method, a pricing problem reduction method, and a heuristic pricing method, to accelerate the convergence of the column generation algorithm. Computational performance of the proposed algorithm is evaluated on benchmark instances that are generated from the physical layout and operational data of the Yangshan Deep-water Port in Shanghai.

The Seaport Traffic Scheduling Problem: Formulations and a Column-Row Generation Algorithm

Traffic congestion in seaports can lead to uncontrolled execution of berth plans, causing severe vessel delays and long waiting times. In this paper, we schedule the vessel traffic of a seaport by optimizing the utilization of the navigation channel and the anchorage areas in the terminal basin. We model the traffic scheduling problem as a mixed integer linear program (MILP), which takes as inputs the physical layout of a seaport and the berth plans devised by the terminal operators, to minimize the berthing and departure delays of vessels and the number of vessels that cannot berth or depart successfully. We reformulate the MILP into a more compact set-partitioning formulation, develop a column generation algorithm for solving the problem, and propose three performance enhancement strategies, namely, a row generation method, a pricing problem reduction method, and a heuristic pricing method, to accelerate the convergence of the column generation algorithm. Computational performance of the proposed algorithm is evaluated on benchmark instances that are generated from the physical layout and operational data of the Yangshan Deep-water Port in Shanghai.

Efficient generation of performance bounds for a class of traffic scheduling problems

This work seeks to develop (lower) performance bounds for a traffic scheduling problem that arises in many application contexts, ranging from industrial material handling and robotics to computer game animations and quantum computing. In a first approach, the sought bounds are obtained by applying the Lagrangian relaxation method to a MIP formulation of the considered scheduling problem that is based on a natural notion of “state” for the underlying traffic system and an analytical characterization of all the possible trajectories of this state over a predefined time horizon. But it is also shown that the corresponding “dual” problem that provides these bounds, can be transformed to a linear program (LP) with numbers of variables and constraints polynomially related to the size of the underlying traffic system and the employed time horizon in the MIP formulation. Furthermore, the derived LP formulation constitutes the LP relaxation of a second MIP formulation for the considered scheduling problem that can be obtained through an existing connection between this problem and the “integral multi-commodity flow” (IMCF) model of network optimization theory. Finally, the theoretical developments of the paper are complemented with a computational part that demonstrates the efficacy of the pursued methods in terms of the quality of the derived bounds, and their computational tractability.

Ship Traffic Optimization for the Kiel Canal

In “Ship Traffic Optimization for the Kiel Canal,” Lübbecke, Lübbecke, and Möhring develop graph-based models and algorithms to solve a practical traffic scheduling problem. It arises in the operational planning of bidirectional traffic where vehicles can pass each other only at dedicated locations—e.g., vessels that navigate narrow waterways. The authors provide decision support for the particular planning problem at the German Kiel Canal, the world’s most frequented artificial waterway, but their findings generalize, e.g., to scheduling trains on a stretch of single tracks or collision-free routing of robot arms. Mathematically, these planning problems expose a rich combinatorial structure. Ideas from quickest path algorithms and job-shop scheduling are integrated to handle all practical constraints at a high level of detail. The modelling does not need any time or space discretization. The software tool developed during the study was also used to assess strategic options of enlarging the canal.

An adaptive model for traffic flow optimisation in dynamic environments

Formulating the solution as an optimisation problem has proven to be effective in developing solutions to many real world problems. We generally obtain the best possible solution using these methods. In this work, the traffic scheduling problem has been formulated as a waiting time minimisation problem, and appropriate cost functions have been developed, in pursuit of finding the optimal solution. A first-in, first-out queuing model is used, with the vehicles arriving in a Poisson process, and the service time being exponentially distributed. The key feature of this model is that it adapts to varying service and arrival rates of the lanes. These rates are forecast using a neural network model, and appear in the objective function. It was observed that the use of the neural network greatly improved the robustness of the model. Although the model has been developed for a four lane, two way architecture, it can be generalised to any architecture. Results have been analysed by comparing the proposed method to a proportional time distribution. It is shown that the proposed model performs relatively well, when there is rapid variation in the arrival and service rates.

An adaptive model for traffic flow optimisation in dynamic environments

Formulating the solution as an optimisation problem has proven to be effective in developing solutions to many real world problems. We generally obtain the best possible solution using these methods. In this work, the traffic scheduling problem has been formulated as a waiting time minimisation problem, and appropriate cost functions have been developed, in pursuit of finding the optimal solution. A first-in, first-out queuing model is used, with the vehicles arriving in a Poisson process, and the service time being exponentially distributed. The key feature of this model is that it adapts to varying service and arrival rates of the lanes. These rates are forecast using a neural network model, and appear in the objective function. It was observed that the use of the neural network greatly improved the robustness of the model. Although the model has been developed for a four lane, two way architecture, it can be generalised to any architecture. Results have been analysed by comparing the proposed method to a proportional time distribution. It is shown that the proposed model performs relatively well, when there is rapid variation in the arrival and service rates.

Optimized Multiagent Routing for a Class of Guidepath-Based Transport Systems

This paper presents a heuristic algorithm for minimizing the makespan required to route a set of agents inhabiting a shared guidepath network from their initial locations to their respective destinations while observing a set of regulations that seek to ensure the safety and the integrity of the generated traffic. From an application standpoint, the presented developments are motivated by the traffic coordination challenges that arise in the context of many automated unit-load material handling systems and also in the transport of the ionized atoms that takes place in the context of quantum computing. From a methodological standpoint, our developments constitute a customization of the general “local-search” framework of combinatorial optimization theory to the traffic management problem that is considered in this paper. Hence, the presented results include a rigorous characterization of the considered problem and its solution space, detailed algorithms for the construction of the necessary initial solutions and the improving step for the pursued search, a complexity analysis of these algorithms, and a set of computational experiments that reveal and assess the computational efficiency of the presented algorithms and the efficacy of the derived solutions. The paper concludes with some suggestions for potential extensions of the presented results. Note to Practitioners —In many contemporary applications of automation science and engineering, a number of entities—or “agents”—must be transported expediently from their initial locations to certain destinations using a set of links that define the underlying “guidepath network.” Furthermore, various safety considerations require that the agents must be adequately separated during these transports, and the imposed restrictions turn the corresponding traffic coordination problem into a complex resource allocation problem, where the contested resources are the guidepath-network links. This paper presents a set of algorithms that can provide high-quality schedules for the resulting traffic-scheduling problems in a computationally efficient manner. These properties of our algorithms are established through the necessary theoretical analysis, but they are also demonstrated through a series of numerical experiments where they are shown capable to provide near-optimal solutions for some very complex problem instances in no more than a few seconds. In addition, our algorithms are “complete,” i.e., they will always provide a feasible schedule for any instantiation of the traffic-scheduling problem considered in this paper. Hence, they can effectively address the needs for “real-time” traffic management that arise in the context of the considered applications.