• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.12
• /
• pp.4776-4798
• /
• 2015

The location selection of virtual machines in distributed cloud is difficult because of the physical resource distribution, allocation of multi-dimensional resources, and resource unit cost. In this study, we propose a multi-object virtual machine location selection algorithm (MOVMLSA) based on group information, doubly linked list structure and genetic algorithm. On the basis of the collaboration of multi-dimensional resources, a fitness function is designed using fuzzy logic control parameters, which can be used to optimize search space solutions. In the location selection process, an orderly information code based on group and resource information can be generated by adopting the memory mechanism of biological immune systems. This approach, along with the dominant elite strategy, enables the updating of the population. The tournament selection method is used to optimize the operator mechanisms of the single-point crossover and X-point mutation during the population selection. Such a method can be used to obtain an optimal solution for the rapid location selection of virtual machines. Experimental results show that the proposed algorithm is effective in reducing the number of used physical machines and in improving the resource utilization of physical machines. The algorithm improves the utilization degree of multi-dimensional resource synergy and reduces the comprehensive unit cost of resources.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38B no.7
• /
• pp.512-518
• /
• 2013

A resource allocation algorithm has a high impact on user satisfaction as well as the ability to accommodate and process services in a distributed cloud computing. In other words, service rejections, which occur when datacenters have no enough resources, degrade the user satisfaction level. Therefore, in this paper, we propose a resource allocation algorithm considering the cloud domain's remaining resources to minimize the number of service rejections. The resource allocation rate based on Q-Learning increases when the remaining resources are sufficient to allocate the maximum allocation rate otherwise and avoids the service rejection. To demonstrate, We compare the proposed algorithm with two previous works and show that the proposed algorithm has the smaller number of the service rejections.

• Journal of the Society of Disaster Information
• /
• v.10 no.2
• /
• pp.304-311
• /
• 2014

Disaster Resources are the resources used in the disaster fields such as fire, typhoon, flood, collapse, flood damage, distress, relief, sanitary, explosion and so forth. The resources are distributed by the several institutes including governmental agencies, public institution, and private sectors. When the large scale disaster is occurred, many kinds of the disaster resources are needed. But it is not easy to know where institutes has the needed resources, because the resource management systems are all distributed in the each institute. To integrate or connect the resource data among the systems, it need the several kinds of coordinations such as terms, classification, and resource exchange protocols. In this paper, we propose the standard specifications and how to connect and exchange the data among the systems.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.7
• /
• pp.205-216
• /
• 2022

One of the many tools used for distributed deep learning training is Kubeflow, which runs on Kubernetes, a container orchestration tool. TensorFlow jobs can be managed using the existing operator provided by Kubeflow. However, when considering the distributed deep learning training jobs based on the parameter server architecture, the scheduling policy used by the existing operator does not consider the task affinity of the distributed training job and does not provide the ability to dynamically allocate or release resources. This can lead to long job completion time and low resource utilization rate. Therefore, in this paper we proposes a new operator that efficiently schedules distributed deep learning training jobs to minimize the job completion time and increase resource utilization rate. We implemented the new operator by modifying the existing operator and conducted experiments to evaluate its performance. The experiment results showed that our scheduling policy improved the average job completion time reduction rate of up to 84% and average CPU utilization increase rate of up to 92%.

• The Journal of Society for e-Business Studies
• /
• v.1 no.1
• /
• pp.227-247
• /
• 1996

Presented in this paper is a control model for developing virtual factory simulator, which is being operated under the distributed environment. The control model consists of production activity plan and information flows. To incorporate elements of the characteristics of the distributed control system, we suggested a collaboration model. This model is working under the client/server architecture, and also designed for cooperative-distributed shop control(CDSC) system in order to exploit several advantages of client/server architecture. Collaboration among each agent(or client) is done through negotiation and task sharing. Based on a contract net model, the CDSC system has three kinds of agents-order agent, resource agent, and communication forwarding agent. Each agent performs shop scheduling and control through negotiation on contract net. No node in CDSC system can have authority over other node. A bidding scheme is employed far negotiation between order agent and resource agents. The CDSC system can support re-negotiation among resource agents and an algorithm for re-negotiation is also developed. Experimental results are shown to advocate the effectiveness of the CDSC system for CIM environments.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.10
• /
• pp.3771-3788
• /
• 2015

This paper studies the distributed energy efficient resource management in the Internet of Things (IoT). Wireless communication networks support the IoT without limitation of distance and location, which significantly impels its development. We study the communication channel and energy management in the wireless communication network supported IoT to improve the ability of connection, communication, share and collaboration, by using the game theory and distributed learning algorithm. First, we formulate an energy efficient neighbor collaborative game model and prove that the proposed game is an exact potential game. Second, we design a distributed energy efficient channel selection learning algorithm to obtain the global optimum in a distributed manner. We prove that the proposed algorithm will asymptotically converge to the global optimum with geometric speed. Finally, we make the simulations to verify the theoretic analysis and the performance of proposed algorithm.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.9
• /
• pp.123-129
• /
• 2011

In this paper, We have proposed a new distributed conference architecture which can reduce largely SIP(Session Initiation Protocol) messages exchanged between servers and participants in distributed conference environment by using resource lists which consist of conference participants URIs. This architecture can also reduce processing time and loads of conference servers. In our proposed method, the number of SIP messages required for participating in the conference can be largely reduced, and the number of SIP messages required for subscription of conference event package and maintaining sessions can also be largely reduced by using resource lists. Therefore expandibility of the conference system increases and network traffic can be reduced by using our conference architecture. And We also have proposed in this paper a new conference information data format with some added elements that are necessary for processing resource lists. Furthermore the procedure for dynamically adding conference servers to the conference environment has been suggested, and the exchanging process of SIP messages and conference information data between conference servers and conference participants has been also suggested. The performance of our proposed system has been evaluated by experiments.

• Journal of Korea Multimedia Society
• /
• v.15 no.12
• /
• pp.1464-1474
• /
• 2012

In this paper, we propose a QoS (Quality of Service)-aware and cooperative resource reservation scheme using cross-layer link adaptation for wireless high definition video transmission through UWB (Ultra Wide Band) network with D-MAC (Distributed Medium Access Control). A wireless high definition video transmission system usually requires stable high throughput even without line-of-sight, e.g., a destination device in another room separated by a wall. Since the WiMedia D-MAC supporting DRP (Distributed Reservation Protocol) scheme causes lots of DRP resource reservation conflicts due to failure of beacon detection in wireless channel environment, overall performances of the WiMedia D-MAC can be deteriorated. And the current WiMedia MAC standard has not considered QoS provisioning even though QoS parameters such as a range of service rates are provided to each traffic stream. Therefore, we propose Relay DRP protocol with QoS-based relay node selection criterion, which makes a relay path to avoid DRP resource reservation conflicts and guarantee QoS more stably through cross-layer link adaptation of cooperative relay transmission scheme and is compliant with the current WiMedia D-MAC protocol. Simulation results demonstrate performance improvements of the proposed method for throughput and QoS provisioning.

• Journal of Communications and Networks
• /
• v.11 no.4
• /
• pp.375-383
• /
• 2009

The WiMedia alliance has specified a distributed medium access control (WiMedia MAC) protocol based on ultra wideband (UWB) for high data rate WPANs (HR-WPANs). The merits of WiMedia MAC such as distributed nature and high data rate make it a favorite candidate in HR-WPAN. Although QoS parameters such as the range of service rates are provided to a traffic stream, the WiMedia MAC is not able to use the QoS parameters and to determine or adjust a service rate using the QoS parameters for the traffic stream. In this paper, we propose a fair and adaptive resource allocation method that allocates time slots to isochronous streams according to QoS parameters and the current traffic load condition in a fully distributed manner. Although the traffic load condition changes, each device independently recognizes the changes and calculates fair and maximum allowable service rates for traffic streams. From the numerical and simulation results, it is proved that the proposed method achieves high capacity of traffic streams and fair QoS provisioning under various traffic load condition.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.3
• /
• pp.49-56
• /
• 2006

A special feature of P2P distributed system isn't always the guarantee of online status for peers. In other words we want to download the file from the peer when we use the P2P system but it sometimes caused this system to fail the download. Many studies to resolve this problem depend on re-transmission method. It caused to lower performance so we have to resolve this problem. In this study, we analysis the average usage time of P2P application user and raise the resource transmission guarantee to apply the selection criteria of resource supplier. Moreover the combinations of distributed object replication techniques, the role to enhance the data transmission opportunity of high popularity resource. will cause this search algorithm to advance.