1,721,097 research outputs found
(INVITED)Chemical sensors based on long period fiber gratings: A review
Get PDFFiber optic devices are being increasingly employed in the fields of chemical and environmental sensing due to their important features, such as high accuracy, small size, chemical inertness, remote operation and multiplexing capabilities. In this work, a thorough review about the design, fabrication and characterization of fiber optic chemical sensors based on long period grating (LPG) technology is reported. The emphasis is placed on transducer designs and features as well as the techniques to enhance the sensitivity. Subsequently, coating materials to be deposited around the grating region, providing a selective response to the target analytes are described in detail. Finally, the different applications are reviewed, mainly related to the monitoring of environmental parameters, volatile organic compounds, hazardous gases, heavy metal ions, corrosion, marine salinity and food quality. The aim of this work is to deliver a comprehensive analysis regarding the state-of-the-art solutions about LPG-based chemical sensors and to summarize the current shortcomings and upcoming research paths
Optimizing Live Migration of Multiple Virtual Machines
No full textThe Cloud computing paradigm is enabling innovative and disruptive services by allowing enterprises to lease computing, storage and network resources from physical infrastructure owners. This shift in infrastructure management responsibility has brought new revenue models and new challenges to Cloud providers. One of those challenges is to efficiently migrate multiple virtual machines (VMs) within the hosting infrastructure with minimum service interruptions. In this paper we first present a live-migration performance testing, captured on a production-level Linux-based virtualization platform, that motivates the need for a better multi-VM migration strategy. We then propose a geometric programming model whose goal is to optimize the bit rate allocation for the live-migration of multiple VMs and minimize the total migration time, defined as a tradeoff cost function between user-perceived downtime and resource utilization time. By solving our geometric program we gained qualitative and quantitative insights on the design of more efficient solutions for multi-VM live migrations. We found that merely few transferring rounds of dirty memory pages are enough to significantly lower the total migration time. We also demonstrated that, under realistic settings, the proposed method converges sharply to an optimal bit rate assignment, making our approach a viable solution for improving current live-migration implementations
A Network Management Protocol for Sonification of Software-Defined Infrastructures
No full textNetwork management traffic is usually carried in-band with the data plane traffic on a logically separate plane. For example, separate service queues and/or VLANs may be reserved for reliable and timely delivery of management messages. This approach has roots in history but carries a fundamental problem: fate sharing between the data plane traffic and management traffic. Failure in data plane networks often cuts off management traffic to the exact network regions at fault, making it impossible to achieve important and relevant management tasks, such as diagnostics and recovery. In this paper, we propose a network management protocol that enables programmability of out-of-channel management applications to combat the fate-sharing problem in Software-Defined Infrastructures. To test our approach and our implementation we used acoustics, a fairly unexplored physical layer for the control and management plane. We then use the notion of sonification to implement a few representative applications such as k-superseeder detection and TraceSound, a sonified version of traceroute, for out-of-channel network verification and debugging. While scaling acoustics could be an insurmountable challenge, our tests show how our protocol brings about a sound software-defined approach that can be expanded to other (combinations of) frequencies and even multiple physical channels
Integrating Piece and Peer Selection in Content Distribution Networks
No full textContent Distribution Networks (CDNs) could benefit from peer-to-peer (P2P) network techniques to improve content delivery time by leveraging the upload capacity of the entire network. In most available solutions, peers first select a set of partners, and later select the pieces of content to exchange. It is fundamental instead that both peer and piece selection algorithms are performed in a consistent and integrated way. To this aim, we propose a content distribution protocol that unifies piece and peer selection in a single algorithm which optimizes the swarming effects. Our approach leverages Flajolet-Martin sketches, a technique based on Bloom filters, to estimate the number of distinct pieces in the CDN, and then adopts a fractional knapsack problem approach to effectively utilize the entire upload capacity of each peer. We tested our solution with both simulations and Planetlab experiments, showing how the piece estimation at every peer is a good approximation of the global rarest piece across the network, and not just across the first hop neighborhood. Moreover, we show how our solution improves the average downloading time by up to 20%. If we consider only the fastest 50% of peers, the downloading time is improved by 100%. Furthermore, our solution decreases the average first content uploading time by 80% with respect to standard P2P protocols which use a local rarest first piece selection, and tit-for-tat as peer selection algorithm
GeoMig: Online multiple VM live migration
No full textThe Cloud computing paradigm enables innovative and disruptive services by allowing enterprises to lease computing, storage and network resources from physical infrastructure owners, to offer a persistently available service. This shift in infrastructure management responsibility has brought new revenue models and new challenges to Cloud providers. One of those challenges is to efficiently migrate multiple virtual machines (VMs) within the hosting infrastructure, since these migrations are often required to be "live", i.e., without noticeable service interruptions. In this paper we propose a geometric programming model and an online multi-VM live migration algorithm based on such model. The goal of the geometric program is to minimize the total migration time via optimal bit-rate assignments. By solving our geometric program we gained qualitative and quantitative insights into the design of efficient solutions for multi-VM live migrations. We found that transferring merely a few rounds of dirty memory pages are enough to significantly lower the total migration time. We also demonstrated that, under realistic settings, the proposed method converges sharply to an optimal bit-rate assignment, making our approach a viable solution for improving current live-migration implementations
NAIL: A Network Management Architecture for Deploying Intent into Programmable Switches
Get PDFProgrammable switches allow network operators to implement their customized network behavior. Despite its benefits, data-plane programmability has many practical challenges, including the ability to transfer intended behaviors on forwarding devices. Languages, such as P4 represent a low level of abstraction, and corresponding programs are cumbersome to manage and configure for DevOps engineers, presenting a barrier to adoption. To facilitate such adoption, we propose NAIL, an architecture that allows network engineers to articulate desired network behaviors at a higher, more expressive layer and then translate such behaviors into executable code using a transpiler that acts as a network intent translator. NAIL can detect and properly instruct the network devices affected by the intent. Then, it offers continuous monitoring functionality to verify whether the intent is met. We demonstrate the effectiveness of our solutions with some use cases, showing the fast reaction to updates and the applicability of supplied intent
Routing with ART: Adaptive Routing for P4 Switches With In-Network Decision Trees
Get PDFRecent advances in Machine Learning (ML) brought several advantages also within computer network management. For programmable data planes, however, it is more challenging to benefit from these advantages, given their limited resource capabilities colliding with the complexity of ML models. In this paper, we propose ART, an attempt to simplify ML-based solutions for routing, so that they can "fit", i.e., be executed, on P4 switches. To provide such model simplification, ART relies on efficient knowledge distillation techniques, converting, in particular, Deep Reinforcement Learning (DRL) models into a simpler Decision Tree (DT). Our evaluation results validate the accuracy of the extracted model and the application of the model logic directly into switches with little impact, paving the way for a more reactive data plane programmability via machine learning integration
Enabling Lightweight Federated Learning in NextG Wireless Networks
No full textNextG wireless will heavily rely on Federated Learning (FL) applications to learn context-aware AI solutions from the massive amount of generated data. Ensuring the reliability of wireless links for such applications is paramount, especially for FL where packet loss can severely hamper performance and efficiency. Traditional approaches fall short under the high packet loss characteristics of wireless networks. This demo shows how the integration of Fountain Codes (FC) into the FL process can bring notable improvements in packet transmission efficiency, especially under high packet loss conditions
Experimental Study of the Refractive Index Sensitivity in Arc-induced Long Period Gratings
No full textThis paper presents an experimental study of the sensitivity characteristics to the surrounding refractive index (SRI) in arc-induced long period gratings (LPGs), in order to outline their dependence over the fabrication parameters. Several LPGs were fabricated, with spectral features that are appealing for chemical sensing applications, e.g., negligible power losses, bands depth greater than 20 dB, and total length smaller than 35 mm. In addition, low spatial periods Λ, which are close to the limit of the arc-based fabrication technique, were selected in order to excite high-order cladding modes. In particular, the period was chosen in range 350-500 μm to focus attention on the same cladding modes for the gratings under investigation. Accordingly, a wide experimental analysis was then carried out to investigate the dependence of the sensitivity to SRI changes on the period in order to derive design criteria for LPG fabrication. In the wavelength range 1100-1700 nm and taking into consideration the attenuation bands related to the LP05 and LP06 cladding modes, an SRI sensitivity enhancement up to one order of magnitude can be achieved by proper selection of the grating period
- …
