Monolithic Cloud Research Articles

Serverless Empowered Video Analytics for Ubiquitous Networked Cameras

Ubiquitous deployment of networked cameras has boosted the prevalence of video analytics. Leveraging machines to automatically analyze captured videos has become the driving force behind a variety of contemporary applications. However, it is known to be resource-hungry with highly dynamic demands, which mismatches the existing monolithic cloud service deployment with coarse-grained resource allocation. Recent advances in serverless computing, which offers ultra-fast and fine-grained autoscaling, would become a game-changer. This article closely examines the potential and challenges of serverless computing in building modern video analytics applications. We accordingly present an integrated framework with geo-distributed resources, and identify the critical design issues toward its implementation. We further discuss a series of promising research directions in this field.

The Gaia-ESO Survey and CSI 2264: Substructures, disks, and sequential star formation in the young open cluster NGC 2264

Context. Reconstructing the structure and history of young clusters is pivotal to understanding the mechanisms and timescales of early stellar evolution and planet formation. Recent studies suggest that star clusters often exhibit a hierarchical structure, possibly resulting from several star formation episodes occurring sequentially rather than a monolithic cloud collapse. Aims. We aim to explore the structure of the open cluster and star-forming region NGC 2264 (~3 Myr), which is one of the youngest, richest and most accessible star clusters in the local spiral arm of our Galaxy; we link the spatial distribution of cluster members to other stellar properties such as age and evolutionary stage to probe the star formation history within the region. Methods. We combined spectroscopic data obtained as part of the Gaia-ESO Survey (GES) with multi-wavelength photometric data from the Coordinated Synoptic Investigation of NGC 2264 (CSI 2264) campaign. We examined a sample of 655 cluster members, with masses between 0.2 and 1.8 M⊙ and including both disk-bearing and disk-free young stars. We used Teff estimates from GES and g,r,i photometry from CSI 2264 to derive individual extinction and stellar parameters. Results. We find a significant age spread of 4–5 Myr among cluster members. Disk-bearing objects are statistically associated with younger isochronal ages than disk-free sources. The cluster has a hierarchical structure, with two main blocks along its latitudinal extension. The northern half develops around the O-type binary star S Mon; the southern half, close to the tip of the Cone Nebula, contains the most embedded regions of NGC 2264, populated mainly by objects with disks and ongoing accretion. The median ages of objects at different locations within the cluster, and the spatial distribution of disked and non-disked sources, suggest that star formation began in the north of the cluster, over 5 Myr ago, and was ignited in its southern region a few Myr later. Star formation is likely still ongoing in the most embedded regions of the cluster, while the outer regions host a widespread population of more evolved objects; these may be the result of an earlier star formation episode followed by outward migration on timescales of a few Myr. We find a detectable lag between the typical age of disk-bearing objects and that of accreting objects in the inner regions of NGC 2264: the first tend to be older than the second, but younger than disk-free sources at similar locations within the cluster. This supports earlier findings that the characteristic timescales of disk accretion are shorter than those of disk dispersal, and smaller than the average age of NGC 2264 (i.e., ≲3 Myr). At the same time, we note that disks in the north of the cluster tend to be shorter-lived (~2.5 Myr) than elsewhere; this may reflect the impact of massive stars within the region (notably S Mon), that trigger rapid disk dispersal. Conclusions. Our results, consistent with earlier studies on NGC 2264 and other young clusters, support the idea of a star formation process that takes place sequentially over a prolonged span in a given region. A complete understanding of the dynamics of formation and evolution of star clusters requires accurate astrometric and kinematic characterization of its population; significant advance in this field is foreseen in the upcoming years thanks to the ongoing Gaia mission, coupled with extensive ground-based surveys like GES.

Outlook on moving of computing services towards the data sources

The internet of things (IoT) is potentially interconnecting unprecedented amounts of raw data, opening countless possibilities by two main logical layers: become data into information, then turn information into knowledge. The former is about filtering the significance in the appropriate format, while the latter provides emerging categories of the whole domain. This path of the data is a bottom-up flow. On the other hand, the path of the process is a top-down flow, starting at the strategic level of business and scientific institutions. Today, the path of the process treasures a sizeable amount of well-known methods, architectures and technologies: the so called Big Data. On the top, Big Data analytics aims variable association (e-commerce), data mining (predictive behaviour) or clustering (marketing segmentation). Digging the Big Data architecture there are a myriad of enabling technologies for data taking, storage and management. However the strategic aim is to enhance knowledge with the appropriate information, which does need of data, but not vice versa. In the way, the magnitude of upcoming data from the IoT will disrupt the data centres. To cope with the extreme scale is a matter of moving the computing services towards the data sources. This paper explores the possibilities of providing many of the IoT services which are currently hosted in monolithic cloud centres, moving these computing services into nano data centres (NaDa). Particularly, data-information processes, which usually are performing at sub-problem domains. NaDa distributes computing power over the already present machines of the IP provides, like gateways or wireless routers to overcome latency, storage cost and alleviate transmissions. Large scale questionnaires have been taken for 300 IT professionals to validate the points of view for IoT adoption. Considering IoT is by definition connected to the Internet, NaDa may be used to implement the logical low layer architecture of the services. Obviously, such distributed NaDa send results on a logical high layer in charge of the information-knowledge turn. This layer requires the whole picture of the domain to enable those processes of Big Data analytics on the top.

A new perspective on the interstellar cloud surrounding the Sun from UV absorption line results

We offer a new, more inclusive, picture of the local interstellar medium, where it is composed of a single, monolithic cloud that surrounds the Sun in all directions. Our study of velocities based on Mg II and Fe II ultraviolet absorption lines indicates that the cloud has an average motion consistent with the velocity vector of gas impacting the heliosphere and does not behave like a rigid body: gas within the cloud is being differentially decelerated in the direction of motion, and the cloud is expanding in directions perpendicular to this flow, much like the squashing of a balloon. The outer boundary of the cloud is in average 10 pc away from us but is highly irregular, being only a few parsecs away in some directions, with possibly a few extensions up to 20 pc. Average H I volume densities vary between 0.03 and 0.1 cm3 over different sight lines. Metals appear to be significantly depleted onto grains, and there is a steady increase in this effect from the rear of the cloud to the apex of motion. There is no evidence that changes in the ionizing radiation influence the apparent abundances. Additional, secondary velocity components are detected in 60% of the sight lines. Almost all of them appear to be interior to the volume holding the gas that we identify with the main cloud. Half of the sight lines exhibit a secondary component moving at about - 7.2 km/s with respect to the main component, which may be the signature of an implosive shock propagating toward the cloud's interior.

The interstellar cloud surrounding the Sun: a new perspective

Aims: We offer a new, simpler picture of the local interstellar medium, made of a single continuous cloud enveloping the Sun. This new outlook enables the description of a diffuse cloud from within and brings to light some unexpected properties. Methods: We re-examine the kinematics and abundances of the local interstellar gas, as revealed by the published results for the ultraviolet absorption lines of MgII, FeII, and HI. Results: In contrast to previous representations, our new picture of the local interstellar medium consists of a single, monolithic cloud that surrounds the Sun in all directions and accounts for most of the matter present in the first 50 parsecs around the Sun. The cloud fills the space around us out to about 9 pc in most directions, although its boundary is very irregular with possibly a few extensions up to 20 pc. The cloud does not behave like a rigid body: gas within the cloud is being differentially decelerated in the direction of motion, and the cloud is expanding in directions perpendicular to this flow, much like a squashed balloon. Average HI volume densities inside the cloud vary between 0.03 and 0.1 cm-3 over different directions. Metals appear to be significantly depleted onto grains, and there is a steady increase in depletion from the rear of the cloud to the apex of motion. There is no evidence that changes in the ionizing radiation influence the apparent abundances. Secondary absorption components are detected in 60% of the sight lines. Almost all of them appear to be interior to the volume occupied by the main cloud. Half of the sight lines exhibit a secondary component moving at about -7.2 km/s with respect to the main component, which may be the signature of a shock propagating toward the cloud's interior.

Blueprinting the Cloud

Current cloud solutions are fraught with problems. They introduce a monolithic cloud stack that imposes vendor lock-in and don't let developers mix and match services freely from diverse cloud service tiers to configure them dynamically to address application needs. Cloud blueprinting is a novel approach that lets developers easily syndicate, configure, and deploy virtual service-based application payloads on virtual machine and resource pools in the cloud.

Hierarchical Formation of Galaxies with Dynamical Response to Supernova‐Induced Gas Removal

We reanalyze the formation and evolution of galaxies in the hierarchical clustering scenario. Using a semianalytic model (SAM) of galaxy formation described in this paper, which we hereafter call the Mitaka model, we extensively investigate the observed scaling relations of galaxies among photometric, kinematic, structural, and chemical characteristics. In such a scenario, spheroidal galaxies are assumed to be formed by a major merger and subsequent starburst, in contrast to the traditional scenario of monolithic cloud collapse. As a new ingredient of SAMs, we introduce the effects of dynamical response to supernova-induced gas removal on size and velocity dispersion, which play an important role in dwarf galaxy formation. In previous theoretical studies of dwarf galaxies based on the monolithic cloud collapse given by Yoshii & Arimoto and Dekel & Silk, the dynamical response was treated in the extremes of a purely baryonic cloud and a baryonic cloud fully supported by surrounding dark matter. To improve this simple treatment, in our previous paper we formulated the dynamical response in more realistic, intermediate situations between the above extremes. While the effects of dynamical response depend on the mass fraction of removed gas from a galaxy, the amount of the gas that remains just after major merger depends on the star formation history. A variety of star formation histories are generated through the Monte Carlo realization of merging histories of dark halos, and it is found that our SAM naturally makes a wide variety of dwarf galaxies and their dispersed characteristics as observed. It is also found that our result strongly depends on the adopted redshift dependence of thestar formation timescale, because it determines the gas fraction in high-redshift galaxies for which major mergers frequently occur. We test four star formation models. The first model has a constant timescale of star formation independent of redshift. The last model has a timescale proportional to the dynamical timescale of the galactic disk. The other models have timescales intermediates of these two. The last model fails to reproduce observations, because it predicts only a small amount of the leftover gas at major mergers, therefore giving too weak a dynamical response on size and velocity dispersion of dwarf spheroidals. The models, having a constant timescale of star formation or a timescale very weakly dependent on redshift, associated with our SAM, succeed in reproducing most observations from giant to dwarf galaxies, except that the adopted strong supernova feedback in this paper does not fully explain the color-magnitude relation under the cluster environment and the Tully-Fisher relation. A direction for overcoming this remaining problem is also discussed.