Scalability Properties Research Articles

Optimal coordinated control of a vehicular platoon by taking into account the individual vehicle dynamics

In most of the previous studies about vehicular platooning control, the individual vehicle in a platoon is simply viewed as a lumped-mass point without considering the vehicle inherent dynamics. From this point, a novel optimal coordinated platooning control (OCPC) scheme is proposed in this work. In detail, not only the relative motions between adjacent vehicles but also the individual vehicle dynamics (wheel rotational dynamics) are taken into account. The OCPC controller is designed as a linear quadratic regulator to force the platooning following control and individual vehicle dynamics control automatically to reach a tradeoff. The string stability and scalability property of the platoon with the proposed OCPC scheme are analysed theoretically. Numerical simulations on a nonlinear six-vehicle platoon model have been conducted and superior platooning following performance can be achieved by the proposed control scheme in both high and low adhesion road conditions.

Виртуальный Эрудит для решения задачи о рюкзаке: обучение автоматическому распределению ресурсов

This article presents the application of Virtual Savant to solve resource allocation problems, a widely-studied area with several real-world applications. Virtual Savant is a novel soft computing method that uses machine learning techniques to compute solutions to a given optimization problem. Virtual Savant aims at learning how to solve a given problem from the solutions computed by a reference algorithm, and its design allows taking advantage of modern parallel computing infrastructures. The proposed approach is evaluated to solve the Knapsack Problem, which models different variant of resource allocation problems, considering a set of instances with varying size and difficulty. The experimental analysis is performed on an Intel Xeon Phi many-core server. Results indicate that Virtual Savant is able to compute accurate solutions while showing good scalability properties when increasing the number of computing resources used.

Design and Deployment of an Open Management and Orchestration Platform for Multi-Site NFV Experimentation

Management and orchestration of virtual resources and functions, commonly referred to as MANO, are key functionalities of NFV environments. This article describes the design and deployment of the NFV MANO platform of 5TONIC, the open research and innovation laboratory on 5G technologies founded by Telefonica and IMDEA Networks. This NFV MANO platform provides 5TONIC trials and experiments with access to a functional production-like NFV environment, enabling experimentation with novel NFV products and services. As a relevant feature, the platform is capable of incorporating external sites to complement the portfolio of software and hardware resources that can be made available for experimentation activities. The 5TONIC MANO platform has been designed and built using open source technologies. The research carried out during its design and deployment has resulted in a contribution already made to its upstream projects regarding the automated configuration of virtualized network functions. Finally, we explore the scalability properties of the 5TONIC MANO platform, and we experimentally validate its functional capacity to orchestrate multi-site experiments.

An anatomy for neural search engines

In this work, we explore the application of modern deep learning techniques to build a neural model centric search engine. We conduct an in-depth discussion under several quantitative and qualitative criteria, comparing the trade-offs of adopting the proposed neural architecture against the successful and mature traditional information retrieval techniques. We show that a full neural architecture, which employs neural models both in the retrieval and ranking phases, offers good scalability, predictability and evolution properties, and discuss under which conditions one can achieve state-of-the-art results. We conclude that deep learning centric systems still require significant more effort to implement and deploy and demand more computational resources, but this work, together with several others in the research community, sheds a light into that path.

SDN Architecture and Southbound APIs for IPv6 Segment Routing Enabled Wide Area Networks

The SRv6 architecture (Segment Routing based on IPv6 data plane) is a promising solution to support services like Traffic Engineering, Service Function Chaining and Virtual Private Networks in IPv6 backbones and datacenters. The SRv6 architecture has interesting scalability properties as it reduces the amount of state information that needs to be configured in the nodes to support the network services. In this paper, we describe the advantages of complementing the SRv6 technology with an SDN based approach in backbone networks. We discuss the architecture of a SRv6 enabled network based on Linux nodes. In addition, we present the design and implementation of the Southbound API between the SDN controller and the SRv6 device. We have defined a data-model and four different implementations of the API, respectively based on gRPC, REST, NETCONF and remote Command Line Interface (CLI). Since it is important to support both the development and testing aspects we have realized an Intent based emulation system to build realistic and reproducible experiments. This collection of tools automate most of the configuration aspects relieving the experimenter from a significant effort. Finally, we have realized an evaluation of some performance aspects of our architecture and of the different variants of the Southbound APIs and we have analyzed the effects of the configuration updates in the SRv6 enabled nodes.

AN OPEN SOURCE WEB-GIS BASED PRECISE SATELLITE TRACKING AND VISUALISATION TOOL USING TWO LINE ELEMENT DATA

Abstract. Accurate monitoring of satellites plays a pivotal role in analysing critical mission specific parameters for estimating orbital position uncertainties. An appropriate database management system (DBMS) at the software end, could prove its potential as a convenient solution over the existing file based two line element (TLE) data structure. The current web-based satellite tracking systems, such as n2yo, satview, and satflare, are unable to provide location-based satellite monitoring. Moreover, the users need to zoom into the displayed world map for obtaining information of the satellites that are currently over the respective area. Also, satellite searching is a cumbersome task in these web-based systems. In this research work, a systematic approach has been utilised to develop a generic open-source Web-GIS based tool for addressing the aforementioned issues. This tool incorporates a PostgreSQL database for storing the parsed TLE data which are freely available on the CelesTrak (NORAD) repository. Our choice of selecting PostgreSQL as a backend DB is primarily due to its open source and scalable properties compared to other resource intensive databases. Using suitable python libraries (e.g. Skyfield and Orbit-Predictor), the position and velocity at any point of time can be accurately estimated. For this purpose, the tool has been tested on several cities for displaying location-based satellite tracking that includes different types of space-objects.

Low-voltage electric-double-layer MoS2 transistor gated via water solution

Two-dimensional (2D) molybdenum disulfide (MoS2) has attracted growing interests due to its intriguing electrical, optical, and scalable properties. Exploring 2D MoS2-based electronic devices which are compatible with the biological systems are of great significance. Herein, a proof-of-concept water-gated multilayer MoS2 transistor is successfully demonstrated by using a side-gated device architecture. Electric-double-layer (EDL) effect is observed in such water-gated multilayer MoS2 transistor. The device exhibits a good performance with a high current on/off ratio of 4 × 103, a small subthreshold swing of 0.27 V/dec, and a low operation voltage of ∼1.5 V, respectively. Furthermore, an ion-contributed quasi-EDL model can be further confirmed by the frequency-dependent capacitance and phase angle measurements. Such merits of water-containing systems coupled with MoS2 opens new opportunities to harness the excellent physical and electrical properties of 2D MoS2 for the potential bioelectronic devices integrated in biological systems for monitoring, diagnostic, and medical applications.

Design of a machine tool control system for function reconfiguration and reuse in network environment

Abstract Computer numerical control (CNC) systems are becoming multi-functional as the requirements for manufacturing quality, efficiency and product diversity are becoming more rigorous. The reconfigurability and scalability property of CNC are important for reducing manufacturing costs and functional redundancy and shortening manufacturing time. However, in current CNC systems, functions are closely coupled in a real-time operation environment. This has been a main obstacle for implementing a scalable and reconfigurable CNC system. This paper proposes a new type of CNC system named invisible numerical control (INC) system to simplify CNC architecture and improve CNC architecture reconfigurability and function reusability. INC system consists of three sub-systems, namely project center, motor controller and mobile terminal. The functions of the sub-systems are machine control instructions generation, execution of machine control instructions and process control respectively. The sub-systems are organized in loosely coupled manner. This is enabled by current computer/information resources and technologies such as high speed data transmission, large capacity and high speed storage, standard communication protocols and compiled operation of machining programs. By configuring different functions in project center, it can generates uniform machine control instructions for multiple and different types of machine tools. Therefore, reconfigurability and function reusability are achieved. This paper illustrates the functions, architecture and information model of INC and builds an INC prototype. Case studies show that by using current off-the-shelf hardware, INC can be implemented to undertake different manufacturing tasks.

Reliable Ge2Sb2Te5‐Integrated High‐Density Nanoscale Conductive Bridge Random Access Memory using Facile Nitrogen‐Doping Strategy

AbstractConductive bridge random access memory (CBRAM) is a possible replacement for static field‐programmable gate arrays (FPGAs) based on random‐access memory. Ge2Sb2Te5 (GST) is used in CBRAMs as a solid electrolyte due to its high diffusion properties of active ions and scalability to obtain high‐density memory devices. Here, the trade‐off between high memory window and uniformity of CBRAM based on GST is solved by introducing N atoms into the SE. Nitrogen‐incorporated GST film (N‐GST) is proposed as a replacement for the current GST‐based CBRAMs with improved performance and better opportunities for conventional FPGA technologies. A bidirectional polarity‐dependent characteristic with high ION/IOFF ratio and satisfactory operation voltage is achieved by using N‐GST thin film in a programmable metallization cell (PMC). Integration of N atoms in the GST‐based PMC with a simple structure of Ag/ N‐GST /Pt increases the resistance ratio more than 100 times compared to an undoped one. Consistent data retention is attained in both resistance states for ≥3.5 × 104 s at temperature up to 85 °C.

SUPG stabilization for the nonconforming virtual element method for advection–diffusion–reaction equations

We present the design, convergence analysis and numerical investigations of the nonconforming virtual element method with Streamline Upwind/Petrov–Galerkin (VEM-SUPG) stabilization for the numerical resolution of convection–diffusion–reaction problems in the convective-dominated regime.According to the virtual discretization approach, the bilinear form is split as the sum of a consistency and a stability term. The consistency term is given by substituting the functions of the virtual space and their gradients with their polynomial projection in each term of the bilinear form (including the SUPG stabilization term). Polynomial projections can be computed exactly from the degrees of freedom. The stability term is also built from the degrees of freedom by ensuring the correct scalability properties with respect to the mesh size and the equation coefficients.The nonconforming formulation relaxes the continuity conditions at cell interfaces and a weaker regularity condition is considered involving polynomial moments of the solution jumps at cell interface. Optimal convergence properties of the method are proved in a suitable norm, which includes contribution from the advective stabilization terms. Experimental results confirm the theoretical convergence rates.

Game-Theoretic Scalable Offloading for Video Streaming Services over LTE and WiFi Networks

This paper presents a game-theoretic scalable offloading system that provides seamless video streaming services by effectively offloading parts of video traffic in all video streaming services to a WiFi network to alleviate cellular network congestion. The system also consolidates multiple physical paths in a cost-effective manner. In the proposed system, the fountain encoding symbols of compressed video data are transmitted through long term evolution (LTE) and WiFi networks concurrently to flexibly control the amount of video traffic through the WiFi network as well as mitigate video quality degradation caused by wireless channel errors. Furthermore, the progressive second price auction mechanism is employed to allocate the limited LTE resources to multiple user equipment in order to maximize social welfare while converging to the ε-Nash equilibrium. Specifically, we design an application-centric resource valuation that explicitly considers both the realistic wireless network conditions and characteristics of video streaming services. In addition, the scalability and convergence properties of the proposed system are verified both theoretically and experimentally. The proposed system is implemented using network simulator 3. Simulation results are provided to demonstrate the performance improvement of the proposed system.

Hybrid lattice Boltzmann-direct simulation Monte Carlo approach for flows in three-dimensional geometries

We present the results of a comparative study performed with three numerical methods applied to a flow in a three-dimensional geometry characterized by weak compressibility and large rarefaction effects. The employed methods, all based on the kinetic theory of gases, are the Lattice Boltzmann Method (LBM) in a regularized formulation, the Direct Simulation Monte Carlo (DSMC) approach and a hybrid method coupling the LBM and the DSMC recently developed by Di Staso et al., in this contribution extended to the case of simulations involving many particles and three-dimensional geometries. Owing to the common kinetic nature shared by the employed methods and to their implementation in a single code infrastructure, a detailed comparison of the results can be performed on a quantitative ground. The numerical results permit to determine, for the studied flow problem, the range of applicability in terms of a geometry-based Knudsen number for the present LBM formulation. The need to employ the hybrid method is justified by the very large computational cost of the DSMC simulation. Limitations of the current hybrid method formulation in treating thermal and large compressibility effects are underlined and possible strategies to overcome them are delineated. Finally, good scalability properties of the parallel algorithms, as well as the large computational cost reduction guaranteed by the hybrid method, while providing an accurate solution, are demonstrated.

Space Propulsion Technology for Small Spacecraft

As small satellites become more popular and capable, strategies to provide in-space propulsion increase in importance. Applications range from orbital changes and maintenance, attitude control and desaturation of reaction wheels to drag compensation and de-orbit at spacecraft end-of-life. Space propulsion can be enabled by chemical or electric means, each having different performance and scalability properties. The purpose of this review is to describe the working principles of space propulsion technologies proposed so far for small spacecraft. Given the size, mass, power, and operational constraints of small satellites, not all types of propulsion can be used and very few have seen actual implementation in space. Emphasis is given in those strategies that have the potential of miniaturization to be used in all classes of vehicles, down to the popular 1-L, 1-kg CubeSats and smaller.

A distributed command governor based on graph colorability theory

SummaryIn this paper, a distributed command governor (CG) strategy is introduced that, by the use of graph colorability theory, improves the scalability property and the performance of recently introduced distributed noncooperative sequential CG strategies. The latter are characterized by the fact that only 1 agent at a decision time is allowed to update its command, whereas all the others keep applying their previously computed commands. The scalability of these early CG distributed schemes and their performance are limited because the structure of the constraints is not taken into account in their implementation. Here, by exploiting the idea that agents that are not directly coupled by the constraints can simultaneously update their control actions, the agents in the network are grouped into particular subsets (turns). At each time instant, on the basis of a round‐robin policy, all agents belonging to a turn are allowed to update simultaneously their commands, whereas agents in other turns keep applying their previous commands. Then, a turn‐based distributed CG strategy is proposed and its main properties are analyzed. Graph colorability theory is used to determine the minimal number of turns and to distribute each agent in at least a turn. A novel graph colorability problem that allows one to maximize the frequency at which agents can update their commands is proposed and discussed. A final example is presented to illustrate the effectiveness of the proposed strategy.

Preferred search over encrypted data

Cloud computing provides elastic data storage and processing services. Although existing research has proposed preferred search on the plaintext files and encrypted search, no method has been proposed that integrates the two techniques to efficiently conduct preferred and privacy-preserving search over large datasets in the cloud. In this paper, we propose a scheme for preferred search over encrypted data (PSED) that can take users’ search preferences into the search over encrypted data. In the search process, we ensure the confidentiality of not only keywords but also quantified preferences associated with them. PSED constructs its encrypted search index using Lagrange coefficients and employs secure inner-product calculation for both search and relevance measurement. The dynamic and scalable property of cloud computing is also considered in PSED. A series of experiments have been conducted to demonstrate the efficiency of the proposed scheme when deploying it in real-world scenarios.

Cluster Frameworks for Efficient Scheduling and Resource Allocation in Data Center Networks: A Survey

Data centers are widely used for big data analytics, which often involve data-parallel jobs, including query and web service. Meanwhile, cluster frameworks are rapidly developed for data-intensive applications in data center networks (DCNs). To promote the performance of these frameworks, many efforts have been paid to improve scheduling strategies and resource allocation algorithms. With the deployment of geo-distributed data centers and data-intensive applications, the optimization in DCNs regains pervasive attention in both industry and academia. Many solutions, such as the coflow-aware scheduling and speculative execution, have been proposed to meet various requirements. Therefore, we present a solid starting ground and comprehensive overview in this area to help readers quickly understand state-of-the-art technologies and research progress. We observe that algorithms in cluster frameworks are implemented with different guidelines and can be classified according to scheduling granularity, controller management, and prior-knowledge requirement. In addition, mechanisms for conquering crucial challenges in DCNs are discussed, including providing low latency and minimizing job completion time. Moreover, we analyze desirable properties of fault tolerance and scalability to illuminate the design principles of distributed systems. We hope that this paper will shed light on this promising land and serve as a guide for further researches.

Distributed Simulations of Physical Phenomena Based on Windows Machines

Simulating physical phenomena can be computationally very demanding, making the distributed approach attractive. Scientific computing and other computationally complex tasks are often performed on dedicated cluster or grid of computers usually running some distribution of Linux operating system. In this article we propose a simulation framework that can utilize general purpose computers running Windows operating system to share available computational resources. The proposed system is composed of simulation client, the network of distributors, and workers. The presented framework has architecture and design that provides a flexible and efficient system with good scalability and fault tolerance properties. The performed tests on the prototype application show that our approach is viable.

Deep Potential: A General Representation of a Many-Body Potential Energy Surface

We present a simple, yet general, end-to-end deep neural network representation of the potential energy surface for atomic and molecular systems. This methodology, which we call Deep Potential, is "first-principle" based, in the sense that no ad hoc approximations or empirical fitting functions are required. The neural network structure naturally respects the underlying symmetries of the systems. When tested on a wide variety of examples, Deep Potential is able to reproduce the original model, whether empirical or quantum mechanics based, within chemical accuracy. The computational cost of this new model is not substantially larger than that of empirical force fields. In addition, the method has promising scalability properties. This brings us one step closer to being able to carry out molecular simulations with accuracy comparable to that of quantum mechanics models and computational cost comparable to that of empirical potentials.

Analysis of a parametrically driven exchange-type gate and a two-photon excitation gate between superconducting qubits

A current bottleneck for quantum computation is the realization of high-fidelity two-qubit quantum operations between two or more quantum bits in arrays of coupled qubits. Gates based on parametrically driven tunable couplers offer a convenient method to entangle multiple qubits by selectively activating different interaction terms in the effective Hamiltonian. Here, we theoretically and experimentally study a superconducting qubit setup with two transmon qubits connected via a capacitively coupled tunable bus. We develop a time-dependent Schrieffer-Wolff transformation and derive analytic expressions for exchange-interaction gates swapping excitations between the qubits (iswap) and for two-photon gates creating and annihilating simultaneous two-qubit excitations (bswap). We find that the bswap gate is generally slower than the more commonly used iswap gate, but features favorable scalability properties with less severe frequency-crowding effects, which typically degrade the fidelity in multiqubit setups. Our theoretical results are backed by experimental measurements as well as exact numerical simulations including the effects of higher transmon levels and dissipation.

Fast multipole preconditioners for sparse matrices arising from elliptic equations

Among optimal hierarchical algorithms for the computational solution of elliptic problems, the fast multipole method (FMM) stands out for its adaptability to emerging architectures, having high arithmetic intensity, tunable accuracy, and relaxable global synchronization requirements. We demonstrate that, beyond its traditional use as a solver in problems for which explicit free-space kernel representations are available, the FMM has applicability as a preconditioner in finite domain elliptic boundary value problems, by equipping it with boundary integral capability for satisfying conditions at finite boundaries and by wrapping it in a Krylov method for extensibility to more general operators. Here, we do not discuss the well developed applications of FMM to implement matrix-vector multiplications within Krylov solvers of boundary element methods. Instead, we propose using FMM for the volume-to-volume contribution of inhomogeneous Poisson-like problems, where the boundary integral is a small part of the overall computation. Our method may be used to precondition sparse matrices arising from finite difference/element discretizations, and can handle a broader range of scientific applications. It is capable of algebraic convergence rates down to the truncation error of the discretized PDE comparable to those of multigrid methods, and it offers potentially superior multicore and distributed memory scalability properties on commodity architecture supercomputers. Compared with other methods exploiting the low-rank character of off-diagonal blocks of the dense resolvent operator, FMM-preconditioned Krylov iteration may reduce the amount of communication because it is matrix-free and exploits the tree structure of FMM. We describe our tests in reproducible detail with freely available codes and outline directions for further extensibility.