Next-gen networks require significant evolution of management to enable automation and adaptively adjust network configuration based on traffic dynamics. The advent of software-defined networking (SDN) and programmable switches enables flexibility and programmability. However, traditional techniques that decide traffic policies are usually based on hand-crafted programming optimization and heuristic algorithms. These techniques make non-realistic assumptions, e.g., considering static network load and topology, to obtain tractable solutions, which are inadequate for next-gen networks. In this paper, we design and develop a deep reinforcement learning (DRL) approach for adaptive traffic routing. We design a deep graph convolutional neural network (DGCNN) integrated into the DRL framework to learn the traffic behavior from not only the network topology but also link and node attributes. We adopt the Deep Q-Learning technique to train the DGCNN model in the DRL framework without the need for a labeled training dataset, enabling the framework to quickly adapt to traffic dynamics. The model leverages q-value estimates to select the routing path for every traffic flow request, balancing exploration and exploitation. We perform extensive experiments with various traffic patterns and compare the performance of the proposed approach with the Open Shortest Path First (OSPF) protocol. The experimental results show the effectiveness and adaptiveness of the proposed framework by increasing the network throughput by up to 7.8% and reducing the traffic delay by up to 16.1% compared to OSPF.
Georgia Institute of Technology（佐治亚理工学院）；IBM Watson AI Foundation Group（IBM沃森人工智能基金会组）
Applying Machine Learning (ML) techniques to design and optimize computer architectures is a promising research direction. Optimizing the runtime performance of a Network-on-Chip (NoC) necessitates a continuous learning framework. In this work, we demonstrate the promise of applying reinforcement learning (RL) to optimize NoC runtime performance. We present three RL-based methods for learning optimal routing algorithms. The experimental results show the algorithms can successfully learn a near-optimal solution across different environment states. Reproducible Code: github.com/huckiyang/interco…
Value-Decomposed Reinforcement Learning Framework for Taxiway Routing with Hierarchical Conflict-Aware Observations
National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University（合成视觉基础科学国家重点实验室，四川大学）；College of Computer Science, Sichuan University（计算机学院，四川大学）
Pakistan Institute of Engineering and Applied Sciences（巴基斯坦工程与应用科学学院）；Carleton University（卡尔顿大学）
Deep Reinforcement Learning (DRL) uses diverse, unstructured data and makes RL capable of learning complex policies in high dimensional environments. Intelligent Transportation System (ITS) based on Autonomous Vehicles (AVs) offers an excellent playground for policy-based DRL. Deep learning architectures solve computational challenges of traditional algorithms while helping in real-world adoption and deployment of AVs. One of the main challenges in AVs implementation is that it can worsen traffic congestion on roads if not reliably and efficiently managed. Considering each vehicle's holistic e…
In this paper we have addressed a very important issue of Traffic Management.Our proposed approach provides assistance in traffic routing by integrating VANET and Grid Computing
Method for calculating routing cost of MPLS network is presented in the work. This method allows to minimize routing cost, taking into account traffic fractal properties, choice of traffic transmission path and quality of service requirements. The method uses values of the Hurst parameter and value of normalized spread of traffic values, which makes it possible to apply it to self-similar and multifractal data streams.
Burst contention is a well-known challenging problem in Optical Burst Switching (OBS) networks. Contention resolution approaches are always reactive and attempt to minimize the BLR based on local information available at the core node. On the other hand, a proactive approach that avoids burst losses before they occur is desirable. To reduce the probability of burst contention, a more robust routing algorithm than the shortest path is needed. This paper proposes a new routing mechanism for JET-based OBS networks, called Graphical Probabilistic Routing Model (GPRM) that selects less utilized lin…
Traffic-Adaptive Per-Hop Multipath Routing in Multi-Hop UAV Networks
Beijing University of Posts and Telecommunications（北京邮电大学）；China Mobile Zijin (Jiangsu) Innovation Research Institute（中国移动紫金（江苏）创新研究院）；Queen Mary University of London（伦敦大学玛丽女王学院）；China Telecom Beijing Research Institute（中国电信北京研究院）；Chongqing University（重庆大学）
We present a simple yet effective routing strategy inspired by coverage control, which delays the onset of congestion on traffic networks, by introducing a control parameter. The routing algorithm allows a trade-off between the congestion level and the distance to the destination. Numerical verification of the strategy is provided on a number of representative examples in SUMO, a well known micro agent simulator used for the analysis of traffic networks. We find that it is crucial in many cases to tune the given control parameters to some optimal value in order to reduce congestion in the most…
Today in fast technology development in wireless mobile adhoc network there is vast scope for research. As it is known that wireless communication for mobile network has many application areas like routing services, security services etc. The mobile adhoc network is the wireless network for communication in which the mobile nodes are organized without any centralized administrator. There are many Manet routing protocols like reactive, proactive, hybrid etc. In this paper the reactive Manet routing protocol like DSR is simulated for traffic analysis for 50 mobile nodes for IP traffic flows. Als…
This paper proposes a Traffic-Differentiated Two-Hop Routing protocol for Quality of Service (QoS) in Wireless Sensor Networks (WSNs). It targets WSN applications having different types of data traffic with several priorities. The protocol achieves to increase Packet Reception Ratio (PRR) and reduce end-to-end delay while considering multi-queue priority policy, two-hop neighborhood information, link reliability and power efficiency. The protocol is modular and utilizes effective methods for estimating the link metrics. Numerical results show that the proposed protocol is a feasible solution t…
We design dynamic routing policies for an overlay network which meet delay requirements of real-time traffic being served on top of an underlying legacy network, where the overlay nodes do not know the underlay characteristics. We pose the problem as a constrained MDP, and show that when the underlay implements static policies such as FIFO with randomized routing, then a decentralized policy, that can be computed efficiently in a distributed fashion, is optimal. Our algorithm utilizes multi-timescale stochastic approximation techniques, and its convergence relies on the fact that the recursion…
Delay Tolerant Networking (DTN) has been proposed as a new architecture to provide efficient store-carry-and-forward data transport in satellite networks. Since these networks relay on scheduled contact plans, the Contact Graph Routing (CGR) algorithm can be used to optimize routing and data delivery performance. However, in spite of the various improvements that have been made to CGR, there have been no significant proposals to prioritize traffic with different quality of service requirements. In this work we propose adaptations to CGR that allow performance improvements when sending traffic …
Traffic Engineering (TE) in IP carrier networks is one of the functions that can benefit from the Software Defined Networking paradigm. By logically centralizing the control of the network, it is possible to "program" per-flow routing based on TE goals. Traditional per-flow routing requires a direct interaction between the SDN controller and each node that is involved in the traffic paths. Depending on the granularity and on the temporal properties of the flows, this can lead to scalability issues for the amount of routing state that needs to be maintained in core network nodes and for the req…
Wide-area network traffic engineering enables network operators to reduce congestion and improve utilization by balancing load across multiple paths. Current approaches to traffic engineering can be modeled in terms of a routing component that computes forwarding paths, and a load balancing component that maps incoming flows onto those paths dynamically, adjusting sending rates to fit current conditions. Unfortunately, existing systems rely on simple strategies for one or both of these components, which leads to poor performance or requires making frequent updates to forwarding paths, signific…
The current specification of the Segment Routing (SR) architecture requires enhancements to the intra-domain routing protocols (e.g. OSPF and IS-IS) so that the nodes can advertise the Segment Identifiers (SIDs). We propose a simpler solution called PMSR (Poor Man's Segment Routing), that does not require any enhancement to routing protocol. We compare the procedures of PMSR with traditional SR, showing that PMSR can reduce the operation and management complexity. We analyze the set of use cases in the current SR drafts and we claim that PMSR can support the large majority of them. Thanks to t…
Segment routing is an emerging technology to simplify traffic engineering implementation in WANs. It expresses an end-to-end logical path as a sequence of segments through a set of middlepoints. Traffic along each segment is routed along shortest paths. In this paper, we study practical traffic engineering (TE) with segment routing in SDN based WANs. We consider two common types of TE, and show that the TE problem can be solved in weakly polynomial time when the number of middlepoints is fixed and not part of the input. However, the corresponding linear program is of large scale and computatio…
In this paper, we evaluate and analyze the impact of different network loads and varying no. of nodes on distance vector and link state routing algorithms. We select three well known proactive protocols; Destination Sequenced Distance Vector (DSDV) operates on distance vector routing, while Fisheye State Routing (FSR) and Optimized Link State Routing (OLSR) protocols are based on link state routing. Further, we evaluate and compare the effects on the performance of protocols by changing the routing strategies of routing algorithms. We also enhance selected protocols to achieve high performance…
The advent of real-time multimedia services over the Internet has stimulated new technologies for expanding the information carrying capacity of optical network backbones. Multilayer wavelength division multiplexing (WDM) packet switching is an emerging technology for increasing the bandwidth of optical networks. Two algorithms for the routing of the multimedia traffic flows were applied: (i) Capacitated Shortest Path First (CSPF) routing, which minimizes the distance of each flow linking the given source and destination nodes and satisfying capacity constraints; and (ii) Flow Deviation Algori…
Filtering packet traffic and rules of permit/denial of data packets into network nodes are granted by facilitating Access Control Lists (ACL). This paper proposes a procedure of adding a link load threshold value to the access control list rules option, which acts on the basis of threshold value. The ultimate goal of this enhanced ACL is to avoid congestion in targeted subnetworks. The link load threshold value allows to decide that packet traffic is rerouted by the router to avoid congestion, or packet drop happens on the basis of packet priorities. The packet rerouting in case of high traffi…
Aerial networks, composed of Unmanned Aerial Vehicles (UAVs) acting as Wi-Fi access points or cellular base stations, are emerging as an interesting solution to provide on-demand wireless connectivity to users, when there is no network infrastructure available, or to enhance the network capacity. This article proposes a traffic-aware topology control solution for aerial networks that holistically combines the placement of UAVs with a predictive and centralized routing protocol. The synergy created by the combination of the UAV placement and routing solutions allows the aerial network to seamle…
Emerging applications such as the metaverse, telesurgery or cloud computing require increasingly complex operational demands on networks (e.g., ultra-reliable low latency). Likewise, the ever-faster traffic dynamics will demand network control mechanisms that can operate at short timescales (e.g., sub-minute). In this context, Traffic Engineering (TE) is a key component to efficiently control network traffic according to some performance goals (e.g., minimize network congestion). This paper presents Routing By Backprop (RBB), a novel TE method based on Graph Neural Networks (GNN) and different…
Network traffic classification using machine learning techniques has been widely studied. Most existing schemes classify entire traffic flows, but there are major limitations to their practicality. At a network router, the packets need to be processed with minimum delay, so the classifier cannot wait until the end of the flow to make a decision. Furthermore, a complicated machine learning algorithm can be too computationally expensive to implement inside the router. In this paper, we introduce flow-packet hybrid traffic classification (FPHTC), where the router makes a decision per packet based…
The present study proposes a novel collaborative traffic engineering scheme for networks of autonomous systems. Backpressure routing principles are used for deriving priority routing rules that optimally stabilize a network, while maximizing its throughput under latency considerations. The routing rules are deployed to the network following simple SDN principles. The proposed scheme requires minimal, infrequent interaction with a central controller, limiting its imposed workload. Furthermore, it respects the internal structure of the autonomous systems and their existing peering relations. In …
State-of-the-art Internet traffic engineering uses source-based explicit routing via MPLS or Segment Routing. Though widely adopted in practice, source routing can face certain inefficiencies and operational issues, caused by its use of bandwidth reservations. In this work, we make the case for Hop-by-Hop (HBH) Traffic Engineering: splitting traffic among nexthops at every router, rather than splitting traffic among paths only at edge routers. We show that HBH traffic engineering can achieve the original goals of MPLS (i.e., efficient use of network resources), with a much simpler design that …
Elastic Optical Network (EON) has been considered as a promising optical networking technology to architect the next-generation backbone networks. Routing and Spectrum Assignment (RSA) is the fundamental problem in EONs to realize service provisioning. Generally, the RSA is solved by routing the requests with lightpaths first and then assigning spectrum resources to the lightpaths to optimize the spectrum usage. Thus, the spectrum assignment explicitly decide the final spectrum usage of EONs. However, besides the spectrum assignment, there are three other factors, the network topology, traffic…
This Study proposes a routing strategy of combining a packet scheduling with congestion control policy that applied for LEO satellite network with high speed and multiple traffic. It not only ensures the QoS of different traffic, but also can avoid low priority traffic to be "starve" due to their weak resource competitiveness, thus it guarantees the throughput and performance of the network. In the end, we set up a LEO satellite network simulation platform in OPNET to verify the effectiveness of the proposed algorithm.
Autonomous vehicles (AV) is an advanced technology that can bring convenience, improve the road-network throughput, and reduce traffic accidents. To enable higher levels of automation (LoA), massive amounts of sensory data need to be uploaded to the network for processing, and then, maneuvering decisions must be returned to the AV. Furthermore, passengers might have a higher transmission rate demands for various data-hungry and delay-sensitive applications.
One of the main issues in Vehicular Ad-hoc NETworks (VANETs) is providing a reliable and efficient routing in urban scenarios with regard to the high vehicle mobility and presence of radio obstacle. In this paper, we propose a Position-Based routing protocol using Learning Automata (PBLA). In addition, PBLA uses the traffic information for enhancing learning. As we know, a main characteristic of learning is increasing performance over time. We exploit this characteristic to decreasing use of traffic information. Initially, PBLA make effort to finding best and shortest path to mobile destinatio…
A dynamic routing policy, referred to as Heat-Diffusion (HD), is developed for multihop uniclass wireless networks subject to random traffic, time-varying topology and inter-channel interference.The policy uses only current condition of queue occupancies and channel states, with requiring no knowledge of traffic and topology.Besides throughput optimality, HD minimizes an average quadratic routing cost defined by endowing each channel with a time-varying cost factor. Further, HD minimizes average network delay in the class of routing policies that base decisions only on current condition of tra…
This paper introduces NeuRoute, a dynamic routing framework for Software Defined Networks (SDN) entirely based on machine learning, specifically, Neural Networks. Current SDN/OpenFlow controllers use a default routing based on Dijkstra algorithm for shortest paths, and provide APIs to develop custom routing applications. NeuRoute is a controller-agnostic dynamic routing framework that (i) predicts traffic matrix in real time, (ii) uses a neural network to learn traffic characteristics and (iii) generates forwarding rules accordingly to optimize the network throughput. NeuRoute achieves the sam…
Due to the enormous variety of application scenarios and ubiquity,Internet of Things (IoT) brought a new perspective of applications for the current and future Internet. The Wireless Sensor Networks provide key devices for developing the IoT communication paradigm, such as the sensors collecting various kind of information and the routing and MAC protocols. However, this type of network has strong power consumption and transmission capacity restrictions (low speed wireless links and subject to interference). In this context, it is necessary to develop solutions that enable a more efficient com…
We show that the capacity of a complex network that models a city street grid to support congested traffic can be optimized by using routes that collectively minimize the maximum ratio of betweenness to capacity in any link. Networks with a heterogeneous distribution of link capacities and with a heterogeneous transport load are considered. We find that overall traffic congestion and average travel times can be significantly reduced by a judicious use of slower, smaller capacity links.
With the introduction of the smart grid, Advanced Metering Infrastructure (AMI) has become a main component in the present power system. The effective implementation of AMI depends widely on its communication infrastructure and protocols providing trustworthy two-way communications. In this paper we study two routing protocols philosophies for low power and lossy networks (LLNs) and their application for a smart metering scenario. This study purposes a detailed evaluation of two routing protocols proposed by IETF the proactive candidate namely RPL (IPv6 Routing Protocol for Low-Power and Lossy…
A Mobile Ad hoc Network (MANET) is a group of mobile nodes that can be set up randomly and formed without the need of any existing network infrastructure or centralized administration. In this network the mobile devices are dependent on battery power, it is important to minimize their energy consumption. Also storage capacity and power are severely limited. In situations such as emergency rescue, military actions, and scientific field missions, energy conservation plays an even more important role which is critical to the success of the tasks performed by the network. Therefore, energy conserv…
This paper introduces a traffic engineering routing algorithm that aims to accept as many routing demands as possible on the condition that a certain amount of bandwidth resource is reserved for each accepted demand. The novel idea is to select routes based on not only network states but also information derived from routing data such as probabilities of the ingress egress pairs and usage frequencies of the links. Experiments with respect to acceptance ratio and computation time have been conducted against various test sets. Results indicate that the proposed algorithm has better performance t…
In this paper, we design a greedy routing on networks of mobile agents. In the greedy routing algorithm, every time step a packet in agent $i$ is delivered to the agent $j$ whose distance from the destination is shortest among searched neighbors of agent $i$. Based on the greedy routing, we study the traffic dynamics and traffic-driven epidemic spreading on networks of mobile agents. We find that the transportation capacity of networks and the epidemic threshold increase as the communication radius increases. For moderate moving speed, the transportation capacity of networks is the highest and…
The Jellyfish network has recently be proposed as an alternate to the fat-tree network as the interconnect for data centers and high performance computing clusters. Jellyfish adopts a random regular graph as its topology and has been showed to be more cost-effective than fat-trees. Effective routing on Jellyfish is challenging. It is known that shortest path routing and equal-cost multi-path routing (ECMP) do not work well on Jellyfish. Existing schemes use variations of k-shortest path routing (KSP). In this work, we study two routing components for Jellyfish: path selection that decides the …
Rising energy consumption of IT infrastructure concerns have spurred the development of more power efficient networking equipment and algorithms. When \emph{old} equipment just drew an almost constant amount of power regardless of the traffic load, there were some efforts to minimize the total energy usage by modifying routing decisions to aggregate traffic in a minimal set of links, creating the opportunity to power off some unused equipment during low traffic periods. New equipment, with power profile functions depending on the offered load, presents new challenges for optimal routing. The g…
Hebrew University of Jerusalem（希伯来大学）；Microsoft Research（微软研究院）；Technion（以色列理工学院）
Routing is, arguably, the most fundamental task in computer networking, and the most extensively studied one. A key challenge for routing in real-world environments is the need to contend with uncertainty about future traffic demands. We present a new approach to routing under demand uncertainty: tackling this challenge as stochastic optimization, and employing deep learning to learn complex patterns in traffic demands. We show that our method provably converges to the global optimum in well-studied theoretical models of multicommodity flow. We exemplify the practical usefulness of our approac…
Maximum throughput requires path diversity enabled by bifurcating traffic at different network nodes. In this work, we consider a network where traffic bifurcation is allowed only at a subset of nodes called \emph{routers}, while the rest nodes (called \emph{forwarders}) cannot bifurcate traffic and hence only forward packets on specified paths. This implements an overlay network of routers where each overlay link corresponds to a path in the physical network. We study dynamic routing implemented at the overlay. We develop a queue-based policy, which is shown to be maximally stable (throughput…
An increasing number of countries are passing laws that facilitate the mass surveillance of Internet traffic. In response, governments and citizens are increasingly paying attention to the countries that their Internet traffic traverses. In some cases, countries are taking extreme steps, such as building new Internet Exchange Points (IXPs), which allow networks to interconnect directly, and encouraging local interconnection to keep local traffic local. We find that although many of these efforts are extensive, they are often futile, due to the inherent lack of hosting and route diversity for m…
In queueing networks, it is well known that the throughput-optimal backpressure routing algorithm results in poor delay performance for light and moderate traffic loads. To improve delay performance, state-of-the-art backpressure routing algorithm (called BPmin [1]) exploits queue length information to direct packets to less congested routes to their destinations. However, BPmin algorithm estimates route congestion based on unrealistic assumption that every node in the network knows real-time global queue length information of all other nodes. In this paper, we propose multi-agent Q-learning a…
Despite the large effort devoted to cybersecurity research over the last decades, cyber intrusions and attacks are still increasing. With respect to routing networks, route hijacking has highlighted the need to reexamine the existing protocols that govern traffic routing. In particular, our pri- mary question is how the topology of a network affects the susceptibility of a routing protocol to endogenous route misdirection. In this paper we define and analyze an abstract model of traffic interception (i.e. eavesdropping) in distance-vector routing networks. Specifically, we study al- gorithms t…
