• Title/Summary/Keyword: Quality Design Simulation

Search Result 873, Processing Time 0.025 seconds

Modified Deep Reinforcement Learning Agent for Dynamic Resource Placement in IoT Network Slicing

  • Ros, Seyha;Tam, Prohim;Kim, Seokhoon
    • Journal of Internet Computing and Services
    • /
    • v.23 no.5
    • /
    • pp.17-23
    • /
    • 2022
  • Network slicing is a promising paradigm and significant evolution for adjusting the heterogeneous services based on different requirements by placing dynamic virtual network functions (VNF) forwarding graph (VNFFG) and orchestrating service function chaining (SFC) based on criticalities of Quality of Service (QoS) classes. In system architecture, software-defined networks (SDN), network functions virtualization (NFV), and edge computing are used to provide resourceful data view, configurable virtual resources, and control interfaces for developing the modified deep reinforcement learning agent (MDRL-A). In this paper, task requests, tolerable delays, and required resources are differentiated for input state observations to identify the non-critical/critical classes, since each user equipment can execute different QoS application services. We design intelligent slicing for handing the cross-domain resource with MDRL-A in solving network problems and eliminating resource usage. The agent interacts with controllers and orchestrators to manage the flow rule installation and physical resource allocation in NFV infrastructure (NFVI) with the proposed formulation of completion time and criticality criteria. Simulation is conducted in SDN/NFV environment and capturing the QoS performances between conventional and MDRL-A approaches.

Traffic Forecast Assisted Adaptive VNF Dynamic Scaling

  • Qiu, Hang;Tang, Hongbo;Zhao, Yu;You, Wei;Ji, Xinsheng
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.16 no.11
    • /
    • pp.3584-3602
    • /
    • 2022
  • NFV realizes flexible and rapid software deployment and management of network functions in the cloud network, and provides network services in the form of chained virtual network functions (VNFs). However, using VNFs to provide quality guaranteed services is still a challenge because of the inherent difficulty in intelligently scaling VNFs to handle traffic fluctuations. Most existing works scale VNFs with fixed-capacity instances, that is they take instances of the same size and determine a suitable deployment location without considering the cloud network resource distribution. This paper proposes a traffic forecasted assisted proactive VNF scaling approach, and it adopts the instance capacity adaptive to the node resource. We first model the VNF scaling as integer quadratic programming and then propose a proactive adaptive VNF scaling (PAVS) approach. The approach employs an efficient traffic forecasting method based on LSTM to predict the upcoming traffic demands. With the obtained traffic demands, we design a resource-aware new VNF instance deployment algorithm to scale out under-provisioning VNFs and a redundant VNF instance management mechanism to scale in over-provisioning VNFs. Trace-driven simulation demonstrates that our proposed approach can respond to traffic fluctuation in advance and reduce the total cost significantly.

Exploring modern machine learning methods to improve causal-effect estimation

  • Kim, Yeji;Choi, Taehwa;Choi, Sangbum
    • Communications for Statistical Applications and Methods
    • /
    • v.29 no.2
    • /
    • pp.177-191
    • /
    • 2022
  • This paper addresses the use of machine learning methods for causal estimation of treatment effects from observational data. Even though conducting randomized experimental trials is a gold standard to reveal potential causal relationships, observational study is another rich source for investigation of exposure effects, for example, in the research of comparative effectiveness and safety of treatments, where the causal effect can be identified if covariates contain all confounding variables. In this context, statistical regression models for the expected outcome and the probability of treatment are often imposed, which can be combined in a clever way to yield more efficient and robust causal estimators. Recently, targeted maximum likelihood estimation and causal random forest is proposed and extensively studied for the use of data-adaptive regression in estimation of causal inference parameters. Machine learning methods are a natural choice in these settings to improve the quality of the final estimate of the treatment effect. We explore how we can adapt the design and training of several machine learning algorithms for causal inference and study their finite-sample performance through simulation experiments under various scenarios. Application to the percutaneous coronary intervention (PCI) data shows that these adaptations can improve simple linear regression-based methods.

S/W Development of Flying Qualities Evaluation in Virtual Flight Test using MATLAB GUI (GUI 기반 가상모의시험 비행성 평가 S/W 개발)

  • Cho, Seung-Gyu;Rhee, Ihn-Seok;Kim, Byoung-Soo
    • Journal of the Korean Society for Aeronautical & Space Sciences
    • /
    • v.41 no.1
    • /
    • pp.61-69
    • /
    • 2013
  • In an evaluation process of aircraft flying qualities, a clear and concise application interface is important since an evaluation process requires numerous repeated evaluation. This flight evaluation program have implemented efficient flight evaluation user interface along with changed trim condition interface and composed of comprehensive evaluation interface have mounted all automated FQ evaluation modules that was selected to be compose of 14 items in respect of an unmanned fixed-wing aircraft. Accordingly when it is necessary to design the flight control system as well as to develop a FQ considered aircraft, this S/W can be utilized as a tool that is a useful test evaluation S/W with scalability and enable to reduce the time and the cost of verification and evaluation process.

QoS Enhancement Based on Link Quality in Tactical Data Link of KVMF (KVMF 전술네트워크에서 링크 품질에 기반한 QoS 향상 방안)

  • Kwon, Koo-Hyung;Jeong, Hyun-Sook;Lim, Won-Gi;Yoon, Young-Deuk;Kim, Sang-Soo;Lee, Sang-Jin
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.39C no.2
    • /
    • pp.139-150
    • /
    • 2014
  • This paper suggests an algorithm to improve QoS by using DTR bit employed in the MIL-STD-188-220 protocol, when there is a multi-path between source and destination in the environment of KVMF tactical network supporting NCW. The MIL-STD-188-220 protocol can evaluate the link quality relatively but it cannot support optimal path selection for QoS. In order to solve this problem, we design an algorithm for selecting path using topology table which reflects measured DTR of path after the completion of transmission. The performance of the proposed algorithm has been evaluated by OPNET simulator. As a result of the simulation, it is found that QoS of proposed algorithm is enhanced higher than that of the MIL-STD-188-220 in the aggravated communication environment.

Comparative Study of PI, Fuzzy and Fuzzy tuned PI Controllers for Single-Phase AC-DC Three-Level Converter

  • Gnanavadivel, J;Senthil Kumar, N;Yogalakshmi, P
    • Journal of Electrical Engineering and Technology
    • /
    • v.12 no.1
    • /
    • pp.78-90
    • /
    • 2017
  • This paper presents the design of closed loop controllers operating a single-phase AC-DC three-level converter for improving power quality at AC mains. Closed loop inhibits outer voltage controller and inner current controller. Simulations of three level converter with three different voltage and current controller combinations such as PI-Hysteresis, Fuzzy-Hysteresis and Fuzzy tuned PI-Hysteresis are carried out in MATLAB/Simulink. Performance parameters such as input power factor and source current total harmonic distortion (THD) are considered for comparison of the three controller combinations. The fuzzy-tuned PI voltage controller with hysteresis current controller combination provides a better result, with a source-current THD of 0.93% and unity power factor without any source side filter for the three level converter. For load variations of 25% to 100%, a THD of less than 5% is obtained with a maximum value of only 1.67%. Finally, the fuzzy-tuned PI voltage with hysteresis controller combination is implemented in a Xilinx Spartan-6 XC6SLX25 FPGA board for experimental validation of power quality enhancement. A prototype 100 W, 0-24-48 V as output converter is considered for the testing of controller performance. A source-current THD of 1.351% is obtained in the experimental study with a power factor near unity. For load variations of 25% to 100%, the THD is found to be less than 5%, with a maximum value of only 2.698% in the experimental setup which matches with the simulation results.

Bandwidth Dimensioning for High-Speed Internet Access Networks (초고속인터넷 가입자망의 대역설계)

  • Lee, Tae-Joon;Lee, Hoon
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.31 no.12B
    • /
    • pp.1017-1027
    • /
    • 2006
  • Recently, Internet service providers are offering triple play service which combines voice and video services with the existing high speed Internet service under the common network infrastructure of IP protocol, so that they can create more benefit from operating a single network architecture. In line with this movement in the convergence of network and services, in this work we propose a bandwidth dimensioning method for the subscriber network of the IP network at flow level. To that purpose, let us propose a series of bandwidth dimensioning methods: bandwidth for best effort service only, bandwidth dimensioning for premium services, and bandwidth dimensioning schemes for the premium Internet services as well as the best effort service which comprise the TPS. Our link dimensioning method is based on the flow level that incorporates the flow blocking probability as a measure of grade of services(GoS), and investigates the characteristics of the proposed methods via extensive numerical experiments. After that, let us carry out a simulation experiment concerning the delay and loss performance of the packet scheduling for the premium services (QoS) using the bandwidth designed by our proposed method, via which the packet level quality of service (QoS) for the proposed link dimensioning method can be observed.

A Study to Generate a Theory of Coordination for Intelligent Agent Societies (지능형 에이전트 집단을 위한 조정 이론 생성에 관한 연구)

  • Kim, Eun-Gyung
    • The KIPS Transactions:PartB
    • /
    • v.9B no.2
    • /
    • pp.147-154
    • /
    • 2002
  • In bulding Intelligent Agent Societies (IAS), it is very important to design and implement coordination in accordance with the known requirement and anticipated working conditions. Coordination consists of a set of mechanisms necessary for the effective operation of IAS. Currently, there is little theoretical support that could help in this research is to generate an empirically-based solving systems in which all agent share an identical goal structure and fully cooperate. And we developed a simulation model called "P-System" which produces basic data to be used for statistical analysis to generate a theory of coordination. Coordination among agent in the P-System is dependent on 23 control variables calld TEs(tweakable emtities.)And the level of coordination is represennted by an independent variabe called QMC (Quality Measure Coordination) expressed in numerical terms according tn the definiion of this study. Also, we have studied how to select unbiased subset from the huge total experimental space of the P-System and how to decide the scale of the subset.

Performance Improvement and ASIC Design of OAM Function Using Special Cell Field (특별 셀 영역을 이용한 OAM 기능의 성능 향상 및 ASIC 설계)

  • Park, Hyoung-Keun;Kim, Hwan-Yong
    • Journal of the Korean Institute of Telematics and Electronics C
    • /
    • v.36C no.2
    • /
    • pp.26-36
    • /
    • 1999
  • In this paper, the novel scheme of OAM performance management function is proposed to supply the most of network resources and reliable services by processing data having various QoS(quality of service) in the view of cell loss and cell delay of ATM networks Also, the special fields of OAM cell are defined in order to improve correlate control, operation, and management technique between networks which is required to flexibility and precision control as detecting the performance information of the variable networks periodically. The proposed OAM function, the input/output function of cell, and the interface function of the accessory device which is likely to the memory/CPU are designed to ASIC. The designed chip is carried out the back-end simulation using Verilog-XL simulator of Cadence. In result, it is able to performs an accurate control in $2{\mu}s$.

  • PDF

Design and Implementation of HomePNA 2.0 MAC Controller Circuit (HomePNA 2.0 MAC Controller 회로의 설계 및 구현)

  • Kim, Jong-Won;Kim, Dae-Young
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.31 no.1A
    • /
    • pp.1-10
    • /
    • 2006
  • The Home Phoneline Networking Alliance(HomePNA) 2.0 technology can establish a home network using existing in-home phone lines, which provides a channel rate of 4-32 Mbps. HomePNA 2.0 Medium Access Control(MAC) protocol adopts an IEEE 802.3 Carrier Sense Multiple Access with Collision Detection(CSMA/CD) access method, Quality of Service(QoS) algorithm, and Distributed Fair Priority Queuing(DFPQ) collision resolution algorithm. In this paper, we describe some performance analysis results of HomePNA 2.0 MAC protocol and the requirements of HomePNA 2.0 MAC controller. Then, we propose the architecture of HomePNA 2.0 MAC controller circuit, show the simulation result of each block included in HomePNA 2.0 MAC controller, and present the HomePNA 2.0 transceiver chip that we have implemented.