The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Neste artigo, propomos um método para alocação automática de recursos virtuais usando um esquema baseado em classificação multi-alvo (MTCAS). Em nosso método, um Provedor de Infraestrutura (InP) agrupa seus recursos de CPU, memória, armazenamento e largura de banda como Elementos de Rede (NEs) e os categoriza em vários tipos de acordo com sua função, capacidades, localização, consumo de energia, preço, etc. MTCAS é usado pelo InP para alocar de forma otimizada um conjunto de NEs para um Operador de Rede Virtual (VNO). Esses NEs estarão sujeitos a algumas restrições, como evitar a superalocação de recursos e a satisfação de múltiplas métricas de Qualidade de Serviço (QoS). A fim de obter uma precisão de previsão comparável ou superior usando menos tempo de treinamento do que os algoritmos de classificação multialvo (MTC) baseados em conjunto disponíveis, propomos um algoritmo de conjunto baseado em votação majoritária (MVEN) para MTCAS. Avaliamos numericamente o desempenho do MTCAS usando o MVEN e algoritmos MTC disponíveis com conjuntos de dados de treinamento sintéticos. Os resultados indicam que o algoritmo MVEN requer 70% menos tempo de treinamento, mas atinge a mesma precisão que os algoritmos MTC baseados em conjuntos relacionados. Os resultados também demonstram que aumentar a quantidade de dados de treinamento aumenta a eficácia do MTCAS, reduzindo assim a alocação de CPU e memória em cerca de 33% e 51%, respectivamente.
Abu Hena Al MUKTADIR
National Institute of Information and Communications Technology (NICT)
Takaya MIYAZAWA
National Institute of Information and Communications Technology (NICT)
Pedro MARTINEZ-JULIA
National Institute of Information and Communications Technology (NICT)
Hiroaki HARAI
National Institute of Information and Communications Technology (NICT)
Ved P. KAFLE
National Institute of Information and Communications Technology (NICT)
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Abu Hena Al MUKTADIR, Takaya MIYAZAWA, Pedro MARTINEZ-JULIA, Hiroaki HARAI, Ved P. KAFLE, "Multi-Target Classification Based Automatic Virtual Resource Allocation Scheme" in IEICE TRANSACTIONS on Information,
vol. E102-D, no. 5, pp. 898-909, May 2019, doi: 10.1587/transinf.2018NTP0016.
Abstract: In this paper, we propose a method for automatic virtual resource allocation by using a multi-target classification-based scheme (MTCAS). In our method, an Infrastructure Provider (InP) bundles its CPU, memory, storage, and bandwidth resources as Network Elements (NEs) and categorizes them into several types in accordance to their function, capabilities, location, energy consumption, price, etc. MTCAS is used by the InP to optimally allocate a set of NEs to a Virtual Network Operator (VNO). Such NEs will be subject to some constraints, such as the avoidance of resource over-allocation and the satisfaction of multiple Quality of Service (QoS) metrics. In order to achieve a comparable or higher prediction accuracy by using less training time than the available ensemble-based multi-target classification (MTC) algorithms, we propose a majority-voting based ensemble algorithm (MVEN) for MTCAS. We numerically evaluate the performance of MTCAS by using the MVEN and available MTC algorithms with synthetic training datasets. The results indicate that the MVEN algorithm requires 70% less training time but achieves the same accuracy as the related ensemble based MTC algorithms. The results also demonstrate that increasing the amount of training data increases the efficacy ofMTCAS, thus reducing CPU and memory allocation by about 33% and 51%, respectively.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2018NTP0016/_p
Copiar
@ARTICLE{e102-d_5_898,
author={Abu Hena Al MUKTADIR, Takaya MIYAZAWA, Pedro MARTINEZ-JULIA, Hiroaki HARAI, Ved P. KAFLE, },
journal={IEICE TRANSACTIONS on Information},
title={Multi-Target Classification Based Automatic Virtual Resource Allocation Scheme},
year={2019},
volume={E102-D},
number={5},
pages={898-909},
abstract={In this paper, we propose a method for automatic virtual resource allocation by using a multi-target classification-based scheme (MTCAS). In our method, an Infrastructure Provider (InP) bundles its CPU, memory, storage, and bandwidth resources as Network Elements (NEs) and categorizes them into several types in accordance to their function, capabilities, location, energy consumption, price, etc. MTCAS is used by the InP to optimally allocate a set of NEs to a Virtual Network Operator (VNO). Such NEs will be subject to some constraints, such as the avoidance of resource over-allocation and the satisfaction of multiple Quality of Service (QoS) metrics. In order to achieve a comparable or higher prediction accuracy by using less training time than the available ensemble-based multi-target classification (MTC) algorithms, we propose a majority-voting based ensemble algorithm (MVEN) for MTCAS. We numerically evaluate the performance of MTCAS by using the MVEN and available MTC algorithms with synthetic training datasets. The results indicate that the MVEN algorithm requires 70% less training time but achieves the same accuracy as the related ensemble based MTC algorithms. The results also demonstrate that increasing the amount of training data increases the efficacy ofMTCAS, thus reducing CPU and memory allocation by about 33% and 51%, respectively.},
keywords={},
doi={10.1587/transinf.2018NTP0016},
ISSN={1745-1361},
month={May},}
Copiar
TY - JOUR
TI - Multi-Target Classification Based Automatic Virtual Resource Allocation Scheme
T2 - IEICE TRANSACTIONS on Information
SP - 898
EP - 909
AU - Abu Hena Al MUKTADIR
AU - Takaya MIYAZAWA
AU - Pedro MARTINEZ-JULIA
AU - Hiroaki HARAI
AU - Ved P. KAFLE
PY - 2019
DO - 10.1587/transinf.2018NTP0016
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2019
AB - In this paper, we propose a method for automatic virtual resource allocation by using a multi-target classification-based scheme (MTCAS). In our method, an Infrastructure Provider (InP) bundles its CPU, memory, storage, and bandwidth resources as Network Elements (NEs) and categorizes them into several types in accordance to their function, capabilities, location, energy consumption, price, etc. MTCAS is used by the InP to optimally allocate a set of NEs to a Virtual Network Operator (VNO). Such NEs will be subject to some constraints, such as the avoidance of resource over-allocation and the satisfaction of multiple Quality of Service (QoS) metrics. In order to achieve a comparable or higher prediction accuracy by using less training time than the available ensemble-based multi-target classification (MTC) algorithms, we propose a majority-voting based ensemble algorithm (MVEN) for MTCAS. We numerically evaluate the performance of MTCAS by using the MVEN and available MTC algorithms with synthetic training datasets. The results indicate that the MVEN algorithm requires 70% less training time but achieves the same accuracy as the related ensemble based MTC algorithms. The results also demonstrate that increasing the amount of training data increases the efficacy ofMTCAS, thus reducing CPU and memory allocation by about 33% and 51%, respectively.
ER -