Data Center Networks Research Articles

An Adaptable and Agnostic Flow Scheduling Approach for Data Center Networks

Cloud applications have reshaped the model of services and infrastructure of the Internet. Search engines, social networks, content delivery and retail and e-commerce sites belong to this group of applications. An important element in the architecture of data centers where these applications run is the communication infrastructure, commonly known as data center networks (DCNs). A critical challenge DCNs have to address is the processing of the traffic of cloud applications, which due to its properties is essentially different to the traffic of other Internet applications. In order to improve the responsiveness and throughput of applications, DCNs should be able to prioritize short flows (a few kB) over long flows (several MB). However, given the time and space variations the traffic presents, the information about flow sizes is not available in advance in order to plan the flow scheduling. There has been a wealth of solutions developed in this space, and prior work includes flow scheduling mechanisms optimizing for a specific workload but fall short when workloads are not known in advance, or comprise a collection of applications changing dynamically. In this paper, we present an adaptable mechanism called Adaptable Workload-Agnostic Flow Scheduling (AWAFS). It is an adaptable approach that can adjust in an agnostic way the scheduling configuration of DCN forwarding devices. This agnostic adjustment contributes to reduce the Flow Completion Time (FCT) of those short flows, representing around 85% of the traffic handled by cloud applications. AWAFS operates by observing the traffic and detecting statistical properties that provide a hint to adapt the scheduling parameters. Our evaluation results based on simulation show that AWAFS can reduce the average FCT of short flows between 16.9% and 45.2% when compared to the best existing agnostic non-adaptable solution, without inducing starvation on long flows. Indeed, it can provide improvements as high as 39% for long flows. Additionally, AWAFS can improve the FCT for short flows in scenarios with high heterogeneity in the traffic present in the network, with a reduction up to 5% for the average FCT and 15% for the tail FCT.

The LCNetWork: An electronic representation of the mRNA-lncRNA-miRNA regulatory network underlying mechanisms of non-small cell lung cancer in humans, and its explorative analysis

Advancement in genomics technologies have made it possible to identify the genes and their interaction/regulation involved in NSCLC, but the interaction information are scattered over the literature. Thus, there is a need of assembling all the available interaction/regulation information in a single platform which will provide a complete view of NSCLC mechanisms. Further, analysis of the mechanisms underlying NSCLC in humans would benefit substantially from easy access to an electronic network. We, therefore, used manual literature curation and integrated all the existing knowledge of NSCLC biomarkers (mRNA, lncRNA and miRNA) into a single conceptual platform represented through a biological network, termed the LCNetWork which represents 345 genes (195 mRNA, 46 lncRNA and 104 miRNA) and 500 direct interactions that are crucial to the regulation of NSCLC in humans. Furthermore, through exploratory data analysis, we have reported four mRNAs (PLK1, ZNF300, NKX2–1, and EGR1), one lncRNA (UCA1) and five miRNAs (MIR133B, MIR326, MIR429, MIR451A, and MIR944) and MIR193A/UCA1/EGFR axis crucial to NSCLC mechanisms. The GO results suggested their role in post-transcriptional gene silencing and RNA polymerase II activities as causes leading to cancer metastasis. The LCNetWork provides up-to-date knowledge of the genes and their interaction/regulation information in NSCLC and is capable of revealing multiple cancer-gene landscapes. Additionally, the LCNetWork has been provided in the Network Data Exchange portal as an electronic circuit for growth by community-level effort.

Named data network dynamic cache placement strategy based on programmable data plane

Named data network dynamic cache placement strategy based on programmable data plane

Coarse-Grained Load Balancing with Traffic-Aware Marking in Data Center Networks

In the data center environment, meeting the dissimilar requirements of transmission performance for long and short data flows is crucial for guaranteeing the data center service quality. It is well known that optimizing the network transmission performance is the key. Abundant research studies have reported that designing an effective load-balancing scheme can boost the network performance by enhancing the path utilization of multirooted data center networks. Unfortunately, the existing data center load-balancing schemes fail to provide satisfying flow-level transmission performance since they choose to ignore the constant changing path status and blindly assign paths to data flows regardless of their different performance requirements. In order to solve these issues, we propose a data center load-balancing scheme called TAM to meet the performance requirements of long and short flows simultaneously. In detail, TAM leverages the traffic-aware ECN marking mechanism to force long flows to proactively maintain the switch queue length at a low level and release bandwidth to short flows when they compete for the bottleneck link. On the contrary, TAM carries out the coarse-grained routing or rerouting for short and long flows, respectively, in real time by perceiving the path status. In this way, the short flows achieve low delay transmission while the long flows obtain high throughput. The simulation results based on NS2 tests show that TAM achieves up to 60% lower FCTs for short flows and a 40% improvement in goodput for long flows.

Data Center Traffic Prediction Algorithms and Resource Scheduling.

This paper uses intelligent methods such as a time recurrent neural network to predict network traffic, mainly to solve the problems of resource imbalance and demand differentiation under the current 5G cloud-network collaborative architecture. An improved tree species optimization algorithm is proposed to optimize the initial network data, and the LSTM model is used to predict the data center traffic to obtain better network traffic prediction accuracy, take corresponding measures, and finally build a scheduling algorithm that integrates business cooperative caching and load balancing based on traffic prediction to reduce the peak pressure of the 5G data center network.

A Low-Overhead and High-Precision Attack Traceback Scheme with Combination Bloom Filters

Distributed denial of service attacks seriously threatens the availability of highly resilient software-defined networking systems, such as data center networks. A traceback scheme is an effective means of mitigating attacks by identifying the location of the attacker and the attacking path. However, traditional traceback schemes suffer from low traceability success rates, high packet header overheads, and high communication traffic overheads, in addition to the fact that logically centralized traceability schemes make the control plane a prime target for attacks. To overcome the above challenges, we propose the low-overhead and high-precision traceback scheme, which is divided into two stages: packet marking and path reconstruction. The first stage of the traceback scheme utilizes programmable switches in the data plane to selectively mark the actual physical path information that the packet was forwarded on. The marking method is adaptive to the path length, which utilizes a combined Bloom filter so that the packet length does not grow with the length of the attacking path. The proposed probabilistic packet marking algorithm effectively reduces the number of packets collected to reconstruct the attacking path. The second stage of the traceback scheme utilizes the distributed victim host to reconstruct the attacking path without the controller and locate the source of the attacker. Theoretical analysis and experimental results show that the proposed scheme ensures the high accuracy of tracing and minimizes the traffic overhead and storage overhead required for the traceback process.

Link-aware distributed steiner sub-tree scheme for all-optical multicasting in elastic optical datacenter networks

The distributed sub-tree (DST) scheme in the elastic optical datacenter network (EODN) can use multiple datacenters (DCs) to jointly serve a multicast request. By allocating some suitable DCs to the multicast request, the route length can be reduced, thereby reducing resource consumption and decreasing blocking probability. However, DST scheme also has a defect that, all source nodes of multicast requests are hosted in the DCs, which leads to that links connecting the DCs nodes have higher usage than other links, and the resulting network bottleneck makes the network performance declines sharply. In this paper, we propose a link-aware cost calculation (LA-CC) formula and a link-aware distributed steiner sub-tree (LA-DSST) algorithm to make the usage of all links as balanced as possible, thus reducing the blocking probability caused by network bottlenecks. Simulation results show that our proposed algorithm significantly improves performance with the lowest blocking probability compared to existing well-performing algorithms.

Prospects and challenges of optical switching technologies for intra data center networks

This paper explores how optical switching technologies can innovate future intra data center networks. The effectiveness of applying large-port-count optical switches is clarified by comparing the available scales and performances of electrical and optical switching networks. The two core technologies needed to make it happen are presented: large-port-count optical switches that have pay-as-you-grow scalability and a simple and fast switch control procedure. Different from the present multi-tier electrical switch network, single-tier large-port-count optical switches and their parallel configurations are shown to greatly simplify the network. Their combination offers low blocking rates and low latency even though the connection set-up is performed in a completely distributed and asynchronous manner where network wide synchronization and routing control are unneeded. The design and performance verification of our control network are detailed, and experiments on a control network emulation based on field programmable gate arrays are presented. The connection set-up latency of around 20 µs is verified within a floor (200 m) using our recently developed silicon photonic switch and tunable filter devices. The devices rely on the thermo-optic effect, but if we apply the electro-optic effect and adopt a simplified connection set-up procedure, the set-up latency is reduced to around 7 µs. The direction discussed here will pave the way for achieving bandwidth abundant and energy efficient data center networks in the future.

CoMap: An efficient virtual network re-mapping strategy based on coalitional matching theory

Virtualization of resources has been adopted in different environments such as wireless sensor networks (WSN), 5G networks, Fog computing, Internet of Things (IoT), and traditional data center (DC) networks. In DC networks, virtualized resources are provisioned as virtual networks (VNs), which comprise multiple communicating virtual machines (VMs) and virtual links (VLs) capturing their communication dependencies. However these virtual components, i.e., VMs and VLs, often experience fluctuating resource demands and require dynamic re-embedding as part of the management activities undertaken by the service providers (SPs). This paper focuses on addressing the issue of resource re-embedding via solution components (SCs), where a SC comprises a VM and its attached VLs, with either the VM and/or at least one of the VLs facing resource expansion. In fact, the resource provisioning problem for VNs is proven to be NP -Hard. Further, the requirement of distributed allocation of VMs of the VNs across the servers to avoid single point failure and enhance the survivability adds to the existing complexity. We propose a framework called CoMap that aims to generate an efficient relocation plan in polynomial time for VNs to reduce the re-embedding costs and improve the utilization of DC servers. The overall problem is modeled as a one-to-many matching game with coalition formation at the servers. Simulation results confirm a 32% average reduction in re-embedding cost and a 69% improvement in the average server utilization compared to the baseline algorithms.

Congestion Control for Cross-Datacenter Networks

Geographically distributed applications hosted on cloud are becoming prevalent. They run on <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">cross-datacenter network</i> that consists of multiple data center networks (DCNs) connected by a wide area network (WAN). Such a cross-DC network poses significant challenges in transport design because the DCN and WAN segments have vastly distinct characteristics ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e.g.</i> , buffer depths, RTTs). In this paper, we find that existing DCN or WAN transport reacting to ECN or delay alone do not (and cannot be extended to) work well for such an environment. The key reason is that neither of the signals, by itself only, can simultaneously capture the location and degree of congestion, mainly due to the discrepancies between DCN and WAN. Motivated by this, we present the design and implementation of GEMINI that strategically integrates both ECN and delay signals for cross-DC congestion control. To achieve low latency, GEMINI bounds the inter-DC latency with delay signal and prevents the intra-DC packet loss with ECN. To maintain high throughput, GEMINI modulates the window dynamics and maintains low buffer occupancy utilizing both congestion signals. GEMINI is implemented in Linux kernel and evaluated by extensive testbed experiments. Results show that GEMINI achieves up to 53%, 31%, 76% and 2% reduction of small flow average completion times, and up to 34%, 39%, 9% and 58% reduction of large flow average completion times compared to TCP Cubic, DCTCP, BBR and TCP Vegas.

The impact of channel model on the performance of distance-based schemes in vehicular named data networks

&lt;span lang="EN-US"&gt;Distance-based schemes present one of the methods to avoid the broadcast problem in vehicular named data networks. However, such schemes overlook the most factor in performance evaluation which is the variation in received signal strength caused by the propagation model choice. Thus, they are evaluated under one propagation model while neglecting the effect of the others. This paper evaluates the impact of the propagation variation model over three distance-based schemes, namely rapid named data networking (RNDN), enhanced vehicle on named data networking (EVNDN) and opportunistic interest forwarding protocol (OIFP). Simulation experiments are performed over three propagation models. Simulation results show that Nakagami significantly degrades network performance. However, it has a noticeable positive effect over higher distance resulting in a higher interest satisfaction ratio as compared to the other models. The RNDN exhibits a higher number of retransmissions across the Nakagami. In contrast, a higher number of retransmissions is exhibited by EVNDN when compared to the other schemes over the Friis and random. The OIFP show a higher interest satisfaction ratio when compared to EVNDN and RNDN under all models. OIFP shows robustness towards the adverse fading effects resulting from the Nakagami and exhibits lower end to end delays.&lt;/span&gt;

Performance evaluation of route optimization management of producer mobility in information-centric networking

&lt;p class="MDPI17abstract"&gt;&lt;span lang="EN-US"&gt;Named data networking (NDN) is a network service evolving the Internet's host-based packet delivery model. The idea of NDN is to use named data for routing, which specifies what they are looking for, instead of using location addresses that determine where they expect it to be provided. This architecture is expected to solve many issues that are currently faced by transmission control protocol/internet protocol (TCP/IP) architecture, such as scalability, robustness, mobility, security, and etcetera. One of the problems is about handling producer mobility. Considering the explosion growth rate of Internet connection in public transport vehicles, this is a challenge that needs to be overcome. Therefore, we have proposed a new scheme called route optimization management of producer mobility (ROM-P) with new features such as distributing anchor points and caching by using the same data name and com-paring our previous scheme, efficient producer mobility support (EPMS). This paper shows the analysis result between the ROM-P and EPMS by using simulation. All simulations were conducted using ndnSIM 2.4 NS-3 based. Throughout the simulation ROM-P shows a promising development in better performing compares to EPMS.&lt;/span&gt;&lt;/p&gt;

An Intelligent Caching Strategy Considering Time-Space Characteristics in Vehicular Named Data Networks

In the Internet of Vehicles (IoV), the classic TCP/IP still plays an important role for data transmission, traffic control and address assignment. However, with increasing requirements on content retrieve efficiency in IoV, the drawbacks of traditional TCP/IP stacks, such as weak scalability in large networks, low efficiency in dense environment and unreliable addressing in high mobility circumstance, have incurred significant performance degradations in vehicular environments. Fortunately, the emerging Named Data Network (NDN) technology provides a good choice to address above issues in vehicular environment by proving content caching capability with introduced content store module, and boosts the research activity of Vehicular Named Data Network (VNDN) in the last few years. In this paper, to improve the service performance, e.g., reducing the delay of data acquisition, a data caching scheme is proposed by taking the spatial-temporal characteristics of data into account. At first, we divided the data in a VNDN into emergency safety message, traffic efficiency message and service message, according to the application requirements. Then, we analyze the spatial-temporal characteristics of these three message categories and design the caching strategy according to these characteristics. Experimental results from NDNSim platform show that our designed scheme has an approximately 50% performance enhancement compared with Leave Copy Everywhere (LCE), Pro(0.7), and Pro(0.2) data caching protocols in terms of average hit rate, average hop count and average cache replacement times, which verifies the reliability and effectiveness of our proposed data caching scheme.

FINT: Flexible In-band Network Telemetry method for data center network

By embedding the state data maintained by the programmable data plane into user packets, the In-band Network Telemetry (INT) can greatly improve the freshness of measured data, such as capturing the micro-bursts in data center networks. However, because the existing INT schemes use fixed telemetry tasks and metadata adding strategies, INT cannot be adjusted in time according to the network state, thus lacking flexibility. To solve the above problems, we propose a Flexible In-band Network Telemetry method FINT. With the designed triple bitmap mechanism, telemetry tasks and parameters can be set dynamically at runtime, which providing flexibility without redeployment to improve telemetry efficiency and reduce the impact of telemetry on network performance. With the designed flexible INT field structure, the types of telemetry metadata carried by user packets can be flexibly selected without significantly adding the indication field. Based on this, to meet the limitation of packet length and reduces the impact on the flow completion time, a greedy telemetry metadata selection algorithm MSG is designed to preferentially select the telemetry metadata with maximum bit-width among the remaining telemetry metadata. The experimental results show that FINT is flexible in adjusting telemetry tasks and add telemetry metadata, and effectively reduce the average flow completion time of the mice flow carrying INT data in the network without significantly increasing the bandwidth consumption.

An Efficient Location-Based Forwarding Strategy for Named Data Networking and LEO Satellite Communications

Low Earth orbit (LEO) satellite constellations are increasingly gaining attention as future global Internet providers. At the same time, named data networking (NDN) is a new data-centric architecture that has been recently proposed to replace the classic TCP/IP architecture since it is particularly well suited to the most common usage of the Internet nowadays as a content delivery network. Certainly, the use of NDN is especially convenient in highly dynamic network environments, such as those of next LEO constellations incorporating inter-satellite links (ISL). Among other native facilities, such as inbuilt security, NDN readily supports the mobility of clients, thus helping to overcome one of the main problems raised in LEO satellite networks. Moreover, thanks to a stateful forwarding plane with support for multicast transmission and inbuilt data caches, NDN is also able to provide a more efficient usage of the installed transmission capacity. In this paper, we propose a new location-based forwarding strategy for LEO satellite networks that takes advantage of the knowledge of the relative position of the satellites and the grid structure formed by the ISLs to perform the forwarding of NDN packets. So, forwarding at each node is done using only local information (node and destination locations), without the need of interchanging information between nodes, as is the case with conventional routing protocols. Using simulation, we show that the proposed forwarding strategy is a good candidate to promote the efficient and effective future use of the NDN architecture in LEO satellite networks.

An INT‐based packet loss monitoring system for data center networks implementing Fine‐Grained Multi‐Path routing

In‐band network telemetry (INT) is a newer network measurement technology that uses normal data packets to collect network information hop‐by‐hop with low overhead. Since incomplete telemetry data seriously degrades the performance of upper‐layer network telemetry applications, it is necessary to consider the own INT packet loss. In response, LossSight, a powerful packet loss monitoring system for INT has been designed, implemented, and made available as open‐source. This letter extends the previous work by proposing, implementing, and evaluating LB‐LossSight, an improved version compatible with packet‐level load‐balancing techniques, which are currently used in modern Data Center Networks. Experimental results in a Clos network, one of the most commonly used topologies in today's data centers, confirm the high detection and localization accuracy of the implemented solution.

Double-Lead Content Search And Producer Location Prediction Scheme For Producer Mobility In Named Data Networking

Abstract In recent years, Named Data Network (NDN) has become a popular network architecture because of high resource utilization, strong security and high transmission efficiency. Meanwhile, mobile multimedia communication has become the mainstream with the popularization and application of smart terminals. Most of the research on NDN mobility is focused on consumer mobility without taking producer mobility into account. To solve the delay and high cost carried by producer moving, we propose a Double-Lead content search algorithm based on neighbor and proxy and a location prediction algorithm based on traffic features. We use a neural network model to predict a new location of producers and calculate route before switching, which can save the rerouting latency in advance when predicting accurately. In a few cases of inaccurate predictions, we select different search methods according to the distance of the producer’s movement, to complete the Double-Lead search between the producer and the consumer. Experimental results show that DLPNDN can reduce the delay and traffic overhead well in NDN when the producer moves.

SDN-Based Traffic Monitoring in Data Center Network Using Floodlight Controller

Data center networks are the backbone of IT infrastructure and cloud services. According to traffic pattern research, a small group of flows transport the vast majority of the bytes and are referred to as elephant flows. Proper management of such traffic flows can enhance overall performance and energy efficiency. Software-defined network (SDN) is a fresh networking model that provides a centralized control plane (i.e., controller). The controller can be utilized for traffic monitoring by collecting the network flows at the controller. In this research, a new mechanism has been provided to detect such flows, which requires continuous polling of all switches. The proposed method depends on passive querying so it does not require additional traffic. The result shows the successful detection of elephant flow and cheetah flow that can be rerouted to improve the quality of service (QoS).

An NDN Cache-Optimization Strategy Based on Dynamic Popularity and Replacement Value

Aiming at examining the problems of the low cache hit ratio and high-average routing hops in named data networking (NDN), this paper proposes a cache-optimization strategy based on dynamic popularity and replacement value. When the requested content arrives at the routing node, the latest popularity is calculated based on the number of requests in the current cycle and the popularity of the previous cycle. We adjust the node cache threshold according to the occupation of the node cache space and cache the content with a higher popularity than the threshold. When the cache is complete, the cache-optimization strategy considers the last request time, popularity, and transmission cost of cached content to calculate the replacement value of cached content. We move the content with the lowest replacement value out of the cache, and keep the content with a high replacement value. We deploy the proposed cache-optimization strategy by using a programmable language in a real network with programmable devices. The experimental results illustrate that the strategy proposed in this paper can effectively improve the cache hit ratio and reduce the average routing hops for user request responses compared with other traditional NDN caching strategies.

On the realization of VANET using named data networking: On improvement of VANET using NDN‐based routing, caching, and security

SummaryNamed data networking (NDN) presents a huge opportunity to tackle some of the unsolved issues of IP‐based vehicular ad hoc networks (VANET). The core characteristics of NDN such as the name‐based routing, in‐network caching, and built‐in data security provide better management of VANET proprieties (e.g., the high mobility, link intermittency, and dynamic topology). This study aims at providing a clear view of the state‐of‐the‐art on the developments in place, in order to leverage the characteristics of NDN in VANET. We resort to a systematic literature review (SLR) to perform a reproducible study, gathering the proposed solutions and summarizing the main open challenges on implementing NDN‐based VANET. There exist several related studies, but they are more focused on other topics such as forwarding. This work specifically restricts the focus on VANET improvements by NDN‐based routing (not forwarding), caching, and security. The surveyed solution herein presented is performed between 2010 and 2021. The results show that proposals on the selected topics for NDN‐based VANET are recent (mainly from 2016 to 2021). Among them, caching is the most investigated topic. Finally, the main findings and the possible roadmaps for further development are highlighted.