Traffic Localization Research Articles

Elastically accelerating lookup on virtual SDN flow tables for software-defined cloud gateways

In recent years, Software-Defined Networking has been gradually applied to cloud gateways to provide efficient, reliable and flexible data transmission services for various large-scale cloud platforms. However, massive concurrent accessing produces huge network traffic from tenants to cloud platforms, which aggregates at cloud gateways and brings serious performance bottlenecks regarding packet classification. To solve this problem, this paper proposes an elastically accelerated lookup method of virtual SDN flow tables for software-defined cloud gateways. The method caches active exact flows in virtue of network traffic locality, enabling most packets to directly hit the cache and bypass tuple space search, which significantly accelerates flow table lookup. Focusing on network traffic jitters, the cache adaptively adjusts its capacity according to the dynamic changes of the number of active exact flows to maintain high cache hit rates, aiming to achieve elastic acceleration of flow table lookup. Furthermore, we theoretically derive the performance metrics of our proposed method such as cache hit rates, cache yield rates and average search length, based on the Zipf distribution model of network traffic. Eventually, we evaluate the performance of our proposed elastically accelerated lookup method by experiments with real network traffic traces. Experimental results indicate that our proposed method outperforms existing cache-accelerated methods with stable cache hit rates around 80% and the speedup of average search length up to 2.84 even under network traffic jitters.

A Hybrid Selection Strategy Based on Traffic Analysis for Improving Performance in Networks on Chip

Networks on chip (NoCs) are an idea for implementing multiprocessor systems that have been able to handle the communication between processing cores, inspired by computer networks. Efficient nonstop routing is one of the most significant applications of NOC. In fact, there are different routes to reach from one node to another node in these networks; therefore, there should be a function that can help to build the best route to reach the destination. In the current study, a new hybrid algorithm scored regional congestion-aware and neighbors-on-path (ScRN) is introduced to choose better output channel and thus improve NOC performance. Having utilized the ScRN algorithm, first an analyzer is used to inspect the traffic packets, and then the NoC traffic locality or nonlocality is determined based on the number of the hops. Finally, if the traffic is local, a scoring technique will choose better output channel; however, if the traffic is nonlocal, the best output channel will be chosen based on a particular parameter introduced here as well as the system status using NoP or RCA selection functions. In the end, via Nirgam simulation, the proposed approach was assessed in traffic scenarios through various selection functions. The simulation results showed that the solution was more successful in terms of delay time, throughput, and energy consumption in comparison to other solutions. It showed a reduction of 38% in packet latency, and the throughput increased by 20%. By considering these two parameters, energy consumption decreased by 10% on average.

Pedestrian fatality risk as a function of tram impact speed

Abstract The objective of the presented research-work was to develop a model to describe the risk of fatal accident involving tram and pedestrian. This study extends research concerning relationships between the “impact speed” and probability of pedestrian death in case of tram accident. Over 400 “tram-pedestrian” accidents were analyzed. Logistic regression analysis was used in these studies. The main objective of the research is to compare the risk of fatal accidents when pedestrians are struck by passenger cars and trams. GPS system from trams is used to analyze correlation between the tram speed and different conditions along the public transport stop areas (e.g. traffic signals, priority, and platforms localization). The results show that the fatal risk of hitting pedestrians by a tram running at a speed of 50 km/h is two and a half times greater than that by a car. Research clearly proves that comparing to car impact speed, there is much higher probability of death when pedestrian is hit by a tram running at a speed of 30 km/h – almost 40% (compared to 5% when hit by car). There are even cases of deaths with a very low speed of tram (5–10 km/h).

An Adaptive Throughput-First Packet Scheduling Algorithm for DPDK-Based Packet Processing Systems

The continuous increase in network traffic has sharply increased the demand for high-performance packet processing systems. For a high-performance packet processing system based on multi-core processors, the packet scheduling algorithm is critical because of the significant role it plays in load distribution, which is related to system throughput, attracting intensive research attention. However, it is not an easy task since the canonical flow-level packet scheduling algorithm is vulnerable to traffic locality, while the packet-level packet scheduling algorithm fails to maintain cache affinity. In this paper, we propose an adaptive throughput-first packet scheduling algorithm for DPDK-based packet processing systems. Combined with the feature of DPDK burst-oriented packet receiving and transmitting, we propose using Subflow as the scheduling unit and the adjustment unit making the proposed algorithm not only maintain the advantages of flow-level packet scheduling algorithms when the adjustment does not happen but also avoid packet loss as much as possible when the target core may be overloaded Experimental results show that the proposed method outperforms Round-Robin, HRW (High Random Weight), and CRC32 on system throughput and packet loss rate.

Too Close for Comfort: Morasses of (Anti-) Censorship in the Era of CDNs

Abstract Recent research claims that “powerful” nation-states may be hegemonic over significant web traffic of “underserved” nations (e.g., Brazil and India). Such traffic may be surveilled when transiting (or ending in) these powerful nations. On the other hand, content distribution networks (CDNs) are designed to bring web content closer to end-users. Thus it is natural to ask whether CDNs have led to the localization of Internet traffic within the country’s boundary, challenging the notion of nation-state hegemony. Further, such traffic localization may inadvertently enhance a country’s ability to coerce content providers to censor (or monitor) access within its boundary. On top of that, the obvious solution, i.e., anti-censorship approaches, may sadly face a new dilemma. Traditional ones, relying on proxies, are easily discoverable. Whereas newer ones (e.g., Decoy Routing, Cache-Browser, Domain Fronting and CovertCast etc.) might not work as they require accessing web content hosted outside the censors’ boundary. We thus quantitatively analyzed the impact of web content localization on various anti-censorship systems. Such analysis requires geolocating the websites. Thus we adapted a multilateration method, Constraint Based Geolocation (CBG), with additional heuristics. We call it as Region Specific CBG (R-CBG). In more than 89% cases, R-CBG correctly classifies hosts as inside (or outside) w.r.t. a nation. Our empirical study, involving five countries, shows that the majority (61%−92%) of popular country-specific websites are hosted within a client’s own country. Further, additional heuristics classify the majority of them to be on CDNs.

On-Board Video-Evaluation Algorithm of Transverse Safety Clearance for Ahead Road-Vehicle

<p class="0abstract">Traffic flows are becoming more intense over time as a result of global automobilization. Road transport specialists are developing and analyzing different approaches to control traffic, to design and to build new highways. Decreasing total amount of accidents and congestion avoidance on a road are the main goals of this research. General traffic flow features and car localization are the most important types of data to be obtained, processed and analyzed in modern conditions as cars are highly maneuverable. Proper usage of this data allows building new high-quality traffic control systems taking in account all of its significant features. We have developed a system for video-processing from camera fixed on car torpedo. Research presented in this paper suggests an algorithm of transverse safety clearance evaluation by analyzing a video from vehicle on-board camera.</p>

PipeCache: High Hit Rate Rule-Caching Scheme Based on Multi-Stage Cache Tables

OpenFlow switches hardware cannot store all the OpenFlow rules due to a limited resource. The rule-caching scheme is one of the best solutions to solve the hardware size limitation. In OpenFlow switches, Multiple Flow Tables (MFTs) provide more flexible flow control than a single table. Exact match and wildcard match are two typical matching methods. The exact match applies to a single flow table and multiple flow tables, but the performance is low under frequently changing traffic. Many commodity switches use Ternary Content Addressable Memory (TCAM) to support fast wildcard lookups. Earlier works on wildcard-match rule-caching focus on the dependency problem caused by the overlaps of match fields. Their designs cannot handle the rule-caching problem of MFTs because they are based on a single flow table, instead of the widely used MFTs structure. So, we propose a new design named PipeCache that solves the problem of MFTs rule-caching scheme based on wildcard-match. In our design, we logically split the TCAM resources, and assign them to each flow table according to the size of each flow table. Each flow table will cache the selected rules into their assigned TCAM resources and be updated in time by our algorithms to make the most use of the limited TCAM resources. We compare our structure with the exact-match scheme and the wildcard-match scheme based on a single flow table under different cache sizes and traffic localities. Experiment results show that our design PipeCache improves cache hit rate by up to 18.2% compared to the exact-match scheme and by up to 21.2% compared to the wildcard-match scheme based on a single flow table.

Flexspander: augmenting expander networks in high-performance systems with optical bandwidth steering

Communication efficiency is one of the deciding factors in determining many of today’s high-performance computing (HPC) applications. Traditionally, HPC systems have been on static network topologies, making them inflexible to the variety of skewed traffic demands that may arise due to the spatial locality inherent in many applications. To handle traffic locality, researchers have proposed integrating optical circuit switches (OCSs) into the network architecture, which reconfigures the network topology to alter and dynamically adapt to the predicted traffic. In this paper, we present a novel reconfigurable network topology called Flexspander. Beyond offering a flexible interconnect, Flexspander also offers full flexibility in terms of construction and can be built with any arbitrary combination of commercial electrical packet switches and OCSs. We evaluate Flexspander performance through extensive simulations with multiple network traces, and our results show improved performance for Flexspander over currently proposed static and reconfigurable topologies in terms of the flow completion time.

Toward a High-Performance and Low-Loss Clos–Benes-Based Optical Network-on-Chip Architecture

As chip multiprocessors (CMPs) keep growing in capability, on-chip communication efficiency is crucial to the overall performance. However, on-chip networks based on electronic switches suffer from excessive power consumption and limited performance. In order to take advantages of optical interconnect, we propose an optimized design toward a high-performance and low-loss Clos–Benes-based hierarchical optical network-on-chip (NoC) for large-scale CMPs. We propose several key techniques, including a loss-aware adaptive (LAA) routing for intraswitch Benes network, a priority-based round-Robin virtual output queue selection and a $Q$ -learning-based heuristic routing for interswitch Clos network, and a local transfer link (LTL) technique to improve the traffic locality. A case study on a 256-core CMP under uniform traffic shows that the network throughput is increased by 346.7%, 61%, and 12.9%, respectively, than the mesh, fattree, and the traditional generic Clos–Benes optical NoC. On average of a set of real applications, the application end-to-end delay is reduced by 47.6%, 28.2%, and 19.4%, respectively, than the mesh, fattree, and the traditional generic Clos–Benes network. Meanwhile, the average optical power loss is decreased by 11.8% and 49.9%, respectively, as compared to the mesh and fattree. As compared to a baseline Clos–Benes network, the use of LAA routing together with the LTL could reduce the average optical power loss by 28.4%.

Fast key-frame image retrieval of intelligent city security video based on deep feature coding in high concurrent network environment

Aiming at the problems faced by the connection management module in single packet processing in intelligent city security video retrieval, we firstly propose the traffic locality quantization index based on the traffic characteristics of the backbone link to quantitatively analyze the traffic locality characteristics in the backbone link. And then, a key-frame abstraction and retrieval of videos based on deep learning is proposed to improve the efficiency and accuracy of video retrieval, where an adaptive key-frame selection algorithm is designed and the existing convolutional neural network framework is used to extract the features of key-frames, and unsupervised, semi-supervised and supervised retraining models are designed to improve the effectiveness of the feature extraction of the convolutional neural network and the accuracy of the video retrieval. Experimental results based on the public video datasets show that our proposed key-frame image retrieval model realizes a good precision for key-frame representation, and achieves high accuracy and efficiency for video retrieval.

Distributed IoT monitoring model using multi-core sensing function integration

Agricultural IoT technology realizes the technology of precise, intelligent, and scientific management of agricultural production. Accurate perception and efficient transmission of farmland data is the basis for precision and smart agriculture. Based on the consideration of WSN distributed monitoring sensor nodes, this paper designs a multi-core sensing agricultural Internet of Things monitoring system based on the low efficiency of existing single-core computing and the inability to adapt to massive sensing data node operations. Multi-core data fusion was simulated and analyzed. Firstly, a method for constructing key value subspaces based on logical landmarks is proposed. The node set maintained by the subspace adds local physical location features to coordinate node discovery and routing. Compared with the traditional key value space, the subspace has a higher system priority, which makes the route local priority, thus realizing traffic localization. The simulation results show that the distributed agricultural network data aggregation algorithm based on multi-core perception can significantly reduce the energy consumption of sensor nodes in WSN, prolong the service life of WSN, and greatly improve the computational efficiency and data accuracy.

Empirical Performance Models of MAC Protocols for Cooperative Platooning Applications

Vehicular ad-hoc networks (VANET) enable vehicles to exchange information on traffic conditions, dynamic status and localization, to enhance road safety and transportation efficiency. A typical VANET application is platooning, which can take advantage of exchanging information on speed, heading and position to allow shorter inter-vehicle distances without compromising safety. However, the platooning performance depends drastically on the quality of the communication channel, which in turn is highly influenced by the medium access control protocol (MAC). Currently, VANETs use the IEEE 802.11p MAC, which follows a carrier sense multiple access with collision avoidance (CSMA/CA) policy that is prone to collisions and degrades significantly with network load. This has led to recent proposals for a time-division multiple access (TDMA)-based MAC that synchronize vehicles’ beacons to prevent or reduce collisions. In this paper, we take CSMA/CA and two TDMA-based overlay protocols, i.e., deployed over CSMA/CA, namely PLEXE-slotted and RA-TDMAp, and carry out extensive simulations with varying platoon sizes, number of occupied lanes and transmit power to deduce empirical models that provide estimates of average number of collisions per second and average busy time ratio. In particular, we show that these estimates can be obtained from observing the number of radio-frequency (RF) neighbours, i.e., number of distinct sources of the packets received by each vehicle per time unit. These estimates can enhance the online adaptation of distributed applications, particularly platooning control, to varying conditions of the communication channel.

A system for profiling the IXPs in a region and monitoring their growth: Spotlight at the internet frontier

SummaryThis work aims at designing and implementing a system able to profile and help manage the set of Internet eXchange Points (IXPs) in an Internet region. As part of the Internet Society's strategy to help monitor and understand the evolution of IXPs in a particular region, a route‐collector data analyzer tool was developed before being deployed and tested in AfriNIC. In fact, traffic localization efforts in the African peering ecosystem would be more sustained, and their efficacy assessed if they were supported by a platform, which evaluates and reports in real time about their impact on the Internet. We, thus, built the “African” Route‐collectors Data Analyzer (ARDA), an open source web platform for analyzing publicly available routing information collected since 2005, by local route‐collectors. ARDA evaluates predefined metrics that picture the status of the interconnection at local, national, and regional levels. It shows that a small proportion of AfriNIC ASes (roughly 17%) are peering in the region. Through them, 58% of all African networks are visible at one IXP or more. These have been static from April to September 2017, and even February 2018, underlining the need for increased efforts to improve local interconnectivity. We show how ARDA can help detect the impact of policies on the growth of local IXPs or continually provide the community with up‐to‐date empirical data on the evolution of the IXP substrate. Given its features, this tool will be a helpful compass for stakeholders in the quest for better traffic localization and new interconnection opportunities in the targeted region.

Anonymity-based intra–inter and multiple layer service dependent security-aware packet scheduling algorithm (AIIMLSDSPS)

ABSTRACTThe concept of anonymity is included for enhancing the efficiency of security aware packet scheduling by introducing, Anonymity-based Intra and inter and multiple layer service dependent security aware packet scheduling algorithm (AIIMLSDSPS). The anonymity of the source locations are often violated by the intruders through traffic analysis and RF localization techniques. The proposed fake source-location method produces the fake sources into the network in order to confuse the intruder. When the original sources send event messages with secured routing policy, the fake sources are generated dynamically. Fake sources then construct several fake paths in the network. Thus, the proposed fake source-location method minimizes the chances of intrusion and reduces the packet loss with minimal latency and reduced overhead. However, as number of fake paths and fake messages increases, energy consumption of each source is also increases.

Reshaping the African Internet: From scattered islands to a connected continent

There is an increasing awareness amongst developing regions on the importance of localizing Internet traffic in the quest for fast, affordable, and available Internet access. In this paper, we focus on Africa, where 37 IXPs are currently interconnecting local ISPs, but mostly at the country level. An option to enrich connectivity on the continent and incentivize content providers to establish presence in the region is to interconnect ISPs present at isolated IXPs by creating a distributed IXP layout spanning the continent. The goal of this paper is to investigate whether such IXP interconnection would be possible, and if successful, to estimate the best-case benefits that could be realized in terms of traffic localization and performance. Our hope is that quantitatively demonstrating the benefits will provide incentives for ISPs to intensify their peering relationships in the region. However, it is challenging to estimate this best-case scenario, due to numerous economic, political, and geographical factors influencing the region. Towards this end, we begin with a thorough analysis of the environment in Africa. We then investigate a naive approach to IXP interconnection, which shows that a theoretically optimal solution would be infeasible in practice due to the prevailing socio-economic conditions in the region. We therefore provide an innovative, realistic four-step interconnection scheme to achieve the distributed IXP layout that considers and parameterizes external socio-economic factors using publicly available datasets. We demonstrate that our constrained solution doubles the percentage of continental intra-African paths, reduces their lengths, and drastically decreases the median of their RTTs as well as RTTs to ASes hosting the top 10 global and top 10 regional Alexa websites. Our approach highlights how, given real-world constraints, a solution requires careful considerations in order to be practically realizable.

Four years tracking unrevealed topological changes in the african interdomain

Despite extensive studies on the Internet topology, little is still known about the AS level topology of the African Internet, especially when it comes to its IXP substrate. The main reason for this is the lack of vantage points that are needed to obtain the proper information. From 2013 to 2016, we enhanced the RIPE Atlas measurement infrastructure in the region to shed light on both IPv4 and IPv6 topologies interconnecting local ISPs. We increased the number of vantage points in Africa by 278.3% and carried out measurements between them at random periods. To infer results that depict the behavior of ISPs in the region, we propose reproducible traceroute data analysis techniques suitable for the treatment of any set of similar measurements. We first reveal a large variety of ISP transit habits and their dependence on socio-economic factors. We then compare QoS within African countries, European countries, and the US to find that West African networks in particular need to promote investments in fiber networks and to implement traffic engineering techniques. Our results indicate the remaining dominance of ISPs based outside Africa for the provision of intra-continental paths, but also shed light on traffic localization efforts. We map, in our traceroute data, 62.2% of the IXPs in Africa and infer their respective peers. Finally, we highlight the launch of new IXPs and quantify their impacts on end-to-end connectivity. The study clearly demonstrates that to better assess interdomain routing in a continent, it is necessary to perform measurements from a diversified range of vantage points.

Tracking Traffic Peaks in Mobile Networks Using Statistics of Performance Metrics

In recent years, there has been an increasing awareness to tracking traffic peaks reflecting the presence of mass events or permanent traffic hotspots. This trend is driven by dominant themes for wireless evolution towards 5G networks such as the problematic of hotspot offloading solutions, the emergence of heterogeneous networks with small cells’ deployment and the development of green networks’ concept. Actually, tracking traffic peaks with a high accuracy is of great interest to know how the congested zones can be offloaded, where small cells should be deployed and how they could be managed for sleep mode concept or even controlled according to traffic mobility if they are moving. In this paper, we propose a method for tracking peaks of traffic using performance metrics extracted from the operation and maintenance database of the network. These metrics are the timing advance, the angle of arrival, the neighboring cell level, the cell load and two mean throughputs: arithmetic (AMT) and harmonic (HMT). The combined use of these performance metrics, projected over a coverage map, yields a promising traffic localization precision even with considering imperfections of coverage prediction and mobile equipment capabilities in handling measurements. The proposed solution can be easily implemented in the network at an appreciable low cost.

Delay Insertion Based P2PTV Traffic Localization Considering Peer's Relaying Capability

Recently, P2PTV is a popular application to deliver video streaming data over Internet network. On the overlay network, P2PTV applications create the logical links between pairs of peers considering round trip time (RTT) without physical network consideration. P2PTV packets are shared over a network without localization awareness which is the serious problem for Internet Service Providers (ISPs). The delay-insertion-based traffic localization scheme was proposed for solving this problem. However, this scheme sometimes leads the newly joining peer to download streaming traffic from a local neighbor peer which has only scarce upload bandwidth. This paper proposes a novel scheme of delay-insertion-based traffic localization in which the router estimates relay capability to each relay peer candidate and leads the newly joining peer to connect to a neighbor peer with sufficient performance for relaying video data. Parameters were evaluated for the optimized condition in the relay capability estimation process. In addition, experiments conducted on a real network show that our proposed scheme can lead the newly joining peer to avoid downloading video data from insufficient relay capability peers and maintain video quality close to normal P2PTV system while efficient traffic localization in level of Autonomous System (AS) network.

P2P Traffic Optimization Based on Dynamic Network Information Aware

Peer-to-Peer (P2P) service may damage the interests of Internet Service Provider (ISP) because P2P traffic usually takes a lot of network link bandwidth and even overwhelms some network links. Aimed at the problem, mainstream solutions are usually optimizing P2P traffic through the interaction between applications and underlying network. However, current solutions still have two aspects of defects: one is that the interacted underlying network status information is immutable and can’t reflect the real-time dynamic changes because it is usually configured by ISP. The other is that some solutions may cause excessive traffic localization, which may greatly influence other services in the local network. In order to improve the above two defects and provide P2P users with better service experience, we propose an enhanced application layer traffic optimization scheme, in which more valuable network status information of underlying network is dynamically calculated and provided to P2P application. Extensive simulations demonstrate that our P2P traffic optimization scheme is superior to other solutions in terms of available bandwidth, resource transmission delay and user service experience.

LazyCtrl: A Scalable Hybrid Network Control Plane Design for Cloud Data Centers

The advent of software defined networking enables flexible, reliable and feature-rich control planes for data center networks. However, the tight coupling of centralized control and complete visibility leads to a wide range of issues among which scalability has risen to prominence due to the excessive workload on the central controller. By analyzing the traffic patterns from a couple of production data centers, we observe that data center traffic is usually highly skewed and thus edge switches can be clustered into a set of communication-intensive groups according to traffic locality. Motivated by this observation, we present LazyCtrl, a novel hybrid control plane design for data center networks where network control is carried out by distributed control mechanisms inside independent groups of switches while complemented with a global controller. LazyCtrl aims at bringing laziness to the global controller by dynamically devolving most of the control tasks to independent switch groups to process frequent intra-group events near the datapath while handling rare inter-group or other specified events by the controller. We implement LazyCtrl and build a prototype based on Open vSwitch and Floodlight. Trace-driven experiments on our prototype show that an effective switch grouping is easy to maintain in multi-tenant clouds and the central controller can be significantly shielded by staying “lazy”, with its workload reduced by up to 82 percent.