Showing papers on "Database-centric architecture published in 2020"
TL;DR: An urban Internet of Things architecture, grounded in big data patterns and focused on the needs of cities and their key stakeholders, is proposed and key data processing components vital to provide high-quality IoT data streams in a near-real-time manner are defined.
Abstract: In this work, we describe an urban Internet of Things (IoT) architecture, grounded in big data patterns and focused on the needs of cities and their key stakeholders. First, the architecture of the dedicated platform USE4IoT (Urban Service Environment for the Internet of Things), which gathers and processes urban big data and extends the Lambda architecture, is proposed. We describe how the platform was used to make IoT an enabling technology for intelligent transport planning. Moreover, key data processing components vital to provide high-quality IoT data streams in a near-real-time manner are defined. Furthermore, tests showing how the IoT platform described in this study provides a low-latency analytical environment for smart cities are included.
11 citations
Posted Content•
TL;DR: How a database OS (DBOS) can improve the programmability and performance of many of today's most important applications is discussed and a plan for the development of a DBOS proof of concept is proposed.
Abstract: Current operating systems are complex systems that were designed before today's computing environments. This makes it difficult for them to meet the scalability, heterogeneity, availability, and security challenges in current cloud and parallel computing environments. To address these problems, we propose a radically new OS design based on data-centric architecture: all operating system state should be represented uniformly as database tables, and operations on this state should be made via queries from otherwise stateless tasks. This design makes it easy to scale and evolve the OS without whole-system refactoring, inspect and debug system state, upgrade components without downtime, manage decisions using machine learning, and implement sophisticated security features. We discuss how a database OS (DBOS) can improve the programmability and performance of many of today's most important applications and propose a plan for the development of a DBOS proof of concept.
10 citations
Posted Content•
TL;DR: Evaluations on a set of HPC and data-driven applications across different domains show that ARENA can provide better parallel scalability with reduced data movement, offering ideal architectural support for future high-performance parallel computing and data analytics systems.
Abstract: The next generation HPC and data centers are likely to be reconfigurable and data-centric due to the trend of hardware specialization and the emergence of data-driven applications. In this paper, we propose ARENA -- an asynchronous reconfigurable accelerator ring architecture as a potential scenario on how the future HPC and data centers will be like. Despite using the coarse-grained reconfigurable arrays (CGRAs) as the substrate platform, our key contribution is not only the CGRA-cluster design itself, but also the ensemble of a new architecture and programming model that enables asynchronous tasking across a cluster of reconfigurable nodes, so as to bring specialized computation to the data rather than the reverse. We presume distributed data storage without asserting any prior knowledge on the data distribution. Hardware specialization occurs at runtime when a task finds the majority of data it requires are available at the present node. In other words, we dynamically generate specialized CGRA accelerators where the data reside. The asynchronous tasking for bringing computation to data is achieved by circulating the task token, which describes the data-flow graphs to be executed for a task, among the CGRA cluster connected by a fast ring network. Evaluations on a set of HPC and data-driven applications across different domains show that ARENA can provide better parallel scalability with reduced data movement (53.9%). Compared with contemporary compute-centric parallel models, ARENA can bring on average 4.37x speedup. The synthesized CGRAs and their task-dispatchers only occupy 2.93mm^2 chip area under 45nm process technology and can run at 800MHz with on average 759.8mW power consumption. ARENA also supports the concurrent execution of multi-applications, offering ideal architectural support for future high-performance parallel computing and data analytics systems.
3 citations
TL;DR: This work presents a meta-modelling framework for estimating the energy consumption of individual cells in a network and provides a simple, scalable, and efficient way to estimate the energy usage of a distributed system.
Abstract: Building an open global sensing layer is critical for the Internet of Things (IoT). In this article, we present a Sensory Data-Centric Networking (SDCN) architecture for inter-networking two main networked sensing systems in IoT—wireless sensor networks and mobile sensing networks. Specifically, the proposed SDCN is a systematic solution including NDNs for sensor nodes in the Zigbee network, NDNm for mobilephones in the Wi-Fi network, and NDNg for gateways. Considering the sensing requirement of IoT, we first design a novel Spatio-Temporal 16 Tree (ST16T) naming scheme associated with the scope-matching method. Based on the naming scheme, we further propose the related discovery methods, network switching mechanism, forwarding, and routing strategies according to the features of large-scale sensing and resource-constrained environment. A proof-of-concept prototype is implemented and further is deployed on our campus (BUPT) and the Great Wall (Shaanxi, China) for Environment Monitoring Project. Several experiments are conducted on the deployed platform. The experimental results show that SDCN outperforms the state-of-the-arts and gains a great performance improvement in terms of energy consumption, data collection efficiency, memory footprint, and time delay.
2 citations
18 Jul 2020
TL;DR: This work proposes an ICN planning service with specific consideration of interoperability across PID schemas in the Cloud environment, and proposes an effective translation between the different naming schemas among PIDs and NDN.
Abstract: Data infrastructures manage the life cycle of digital assets and allow users to efficiently discover them. To improve the Findability, Accessibility, Interoperability and Re-usability (FAIRness) of digital assets, a data infrastructure needs to provide digital assets with not only rich meta information and semantics contexts information but also globally resolvable identifiers. The Persistent Identifiers (PIDs), like Digital Object Identifier (DOI) are often used by data publishers and infrastructures. The traditional IP network and client-server model can potentially cause congestion and delays when many consumers simultaneously access data. In contrast, Information Centric Networking (ICN) technologies such as Named Data Networking (NDN) adopt a data centric approach where digital data objects, once requested, may be stored on intermediate hops in the network. Consecutive requests for that unique digital object are then made available by these intermediate hops (caching). This approach distributes traffic load more efficient and reliable compared to host-to-host connection oriented techniques, and demonstrates attractive opportunities for sharing digital objects across distributed networks. However, such an approach also faces several challenges. It requires not only an effective translation between the different naming schemas among PIDs and NDN, in particular for supporting PIDs from different publishers or repositories. Moreover, the planning and configuration of an ICN environment for distributed infrastructures are lacking an automated solution. To bridge the gap, we propose an ICN planning service with specific consideration of interoperability across PID schemas in the Cloud environment.
1 citations
01 Jan 2020
TL;DR: This paper review about memristor In-Memory computing capabilities, and its potency in Combinational logic and propose an architecture that suits for real-time Image processing applications.
Abstract: CMOS technology and its sustainable scaling have been the facilitators for the design and modeling of computers that have been inciting a wider range of applications. A broad dependence on technology, voluminous data, and rising processing needs have imposed the technology-computer architecture duos to suffer from serious hardships that hinder transistor utilization and advertise the need for new devices. This stimulates novel architectures equidistant to novel technologies. With zillion advantages like tiny size, high power tolerance, remembering capacity, huge retention, high persistence, low reads and writes, 3D design ability, tight fit with portable devices, made memristor a breakthrough technology for all ongoing data-centric applications. This paper review about memristor In-Memory computing capabilities, and its potency in Combinational logic and propose an architecture that suits for real-time Image processing applications.
1 citations
01 Jan 2020
TL;DR: This chapter concentrates on the elements of a data-centric architecture that must support data safety requirements associated with critical control points, and the concept of an architecture having Transformation-Abstraction-Product elements is introduced.
Abstract: This chapter concentrates on the elements of a data-centric architecture. The selected architecture must support data safety requirements associated with critical control points. The concept of an architecture having Transformation-Abstraction-Product elements is introduced. The architecture must facilitate the correct container incorporating correct data. It must also ensure data diversity requirements. Different architectural models, such as multi-tier and cloud, are explored in a data-centric context. The use of TAPs and data paths requires strong interface agreements to be in place, and this element of a data-centric architecture is considered in some detail. The highest level of architectural abstraction employed is that of a metamodel architecture.
01 Jan 2020
TL;DR: This chapter describes the data analytics framework that has been designed and developed in the ENVRIplus project to be suitable for serving the needs of researchers in several domains including environmental sciences, open and extensible both with respect to the algorithms and methods it enables and the computing platforms it relies on to execute them.
Abstract: The development of data processing and analytics tools is heavily driven by applications, which results in a great variety of software solutions, which often address specific needs. It is difficult to imagine a single solution that is universally suitable for all (or even most) application scenarios and contexts. This chapter describes the data analytics framework that has been designed and developed in the ENVRIplus project to be (a) suitable for serving the needs of researchers in several domains including environmental sciences, (b) open and extensible both with respect to the algorithms and methods it enables and the computing platforms it relies on to execute those algorithms and methods, and (c) open-science-friendly, i.e. it is capable of incorporating every algorithm and method integrated into the data processing framework as well as any computation resulting from the exploitation of integrated algorithms into a “research object” catering for citation, reproducibility, repeatability and provenance.