• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.37 no.6
• /
• pp.381-381
• /
• 2000

In this paper, we propose a real-time bandwidth allocation scheme of multiplexed VBR MPEG video sequences over ATM network. In order to real time processing, multiplexed source is estimated by linear-prediction per measurement period. If the result CLR value were not sufficient, we proposed a overallocation method and a reallocation one to guarantee QoS. We used two kinds of sources, one is random multiplexed source made of foot different video sources, the other is the one considered the arrange of I frame in the sequence. With those sources, we analyzed the linear prediction, compared overallocation with reallocation method. As a result, in both schemes, the objected CLR value is achieved, the sufficient value COR under 10% when mp is over 1.8 sec, the utilization is over 0.9. Especially, the COR value of the reallocation scheme is better at the same condition.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.37 no.6
• /
• pp.21-27
• /
• 2000

In this paper, we propose a real-time bandwidth allocation scheme of multiplexed VBR MPEG video sequences over ATM network. In order to real time processing, multiplexed source is estimated by linear-prediction per measurement period. If the result CLR value were not sufficient, we proposed a overallocation method and a reallocation one to guarantee QoS. We used two kinds of sources, one is random multiplexed source made of foot different video sources, the other is the one considered the arrange of I frame in the sequence. With those sources, we analyzed the linear prediction, compared overallocation with reallocation method. As a result, in both schemes, the objected CLR value is achieved, the sufficient value COR under 10% when mp is over 1.8 sec, the utilization is over 0.9. Especially, the COR value of the reallocation scheme is better at the same condition.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04d
• /
• pp.572-574
• /
• 2003

웹 서버 클러스터의 성능 개선을 위한 연구가 다양한 분야에서 이루어졌지만 로그 파일 분석과 같은 방식으로 접속 빈도를 통한 실시간 동적 자원 재분배에 관한 연구에만 대부분 초점을 맞추었다. 본 논문에서는 시구간별 접속 패턴 분석 결과를 기반으로 패턴을 예측하여 자원을 동적으로 재분배하는 메커니즘을 제안한다. 제안한 메커니즘은 불필요한 자원 낭비를 감소시켜 효율적인 자원 재분배를 통해 클러스터의 성능을 향상시킨다. 또한 시구간별 접속 패턴의 유사성을 증명한다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.3
• /
• pp.593-603
• /
• 1997

Connection admission decision in ATM networks requires decision made in real time using fast algorithm. It is difficult to construct a model of the multiplexed traffic and thus, approximation of the traffic load is necessary. In this paper, we propose a measurement-based dynamic CAC(Connection admission Control) in ATM(Asynchronous Transfer Mode) networks, which observes current traffic by the moving window and set the window size to the value which is computed from the measured cell loss amount. It is based on the measurements of the traffic load over an admission period that is load enough to reflect the current traffic behavior instead of analytic modeling. And, the dynamic reallocation of bandwidth for each class leads to effective bandwidth utilization. The performance of proposed method is analyzed through computer simulation. The performance of proposed method is analyzed by using SIMAN simulation package and FORTRAN language. As can be seen in the simulation result, cell loss performance and bandwidth utilization have been increased.

• Journal of Broadcast Engineering
• /
• v.15 no.3
• /
• pp.407-413
• /
• 2010

In DCA (Dynamic Channel Allocation) scheme of uplink cellular system appling a frequency reuse factor of one, when a new call requests a channel, the new call will be blocked if its SINR (Carrier to Noise and Interference Ratio) is less than the required SINR or there is no available channel. The additional channel allocation for the blocked new call can be performed with channel borrowing in the adjacent cells. The channel borrowing causes the CCI (Co-Channel Interference), thus the SINR of the existing calls is deteriorated and the channel reallocation for the existing calls is required. As a result, the channel borrowing leads to a complex calculation so that it is a NP-hard problem. Therefore, to overcome the problem, we propose a novel Group Search-based DCA scheme which decreases the number of the blocked new calls and then reduces the number of the channel reallocation by the channel borrowing for the blocked new calls. The proposed scheme searches the all channels in a group of the adjacent cells and home cell at the same time in order to minimizes the number of the blocked new calls. The simulation results show that proposed Group Search-based DCA scheme provides better new call blocking probability and system throughput than the existing Single Search-based DCA scheme which searches only the channels in home cell.

• Journal of KIISE:Software and Applications
• /
• v.41 no.8
• /
• pp.569-579
• /
• 2014

In a tactical-edge environment, where multiple weapon resources are coordinated together via services, it is essential to make an efficient binding between an abstract service and a resource that are needed to execute composite services for accomplishing a given mission. However, the tactical network that is used in military operation has low bandwidth and a high rate of packet loss. Therefore, communication overhead between services must be minimized to execute composite services in a stable manner in the tactical network. In addition, a tactical-edge environment changes dynamically, and it affects the connectivity and bandwidth of the tactical network. To deal with these characteristics of the tactical network we propose two service-resource reallocation methods which minimize the communication overhead between service gateways and effectively manage neutralization of gateways during distributed service coordination. We compared the effectiveness of these two - methods in terms of total communication overhead between service gateways and resource-allocation similarity between the initial resource allocation and the reallocation result.

• Journal of information and communication convergence engineering
• /
• v.1 no.3
• /
• pp.109-114
• /
• 2003

There is an emergence of Internet applications that have real-time requirements. These applications require IP to support guaranteed capacity, higher priority and lower packet loss rate. To address this, the Internet Engineering Task Force (IETF) is developing a set of protocols and standards for Integrated Services on the Internet. Using RSVP and policies to manage the allocation of network resources in order to provide different levels of service is a topic of great interest to service providers. Currently, it is not possible to dynamically reallocate resources during an application's session. This paper discusses how policies in conjunction with new service class can provide a more enhanced network resource allocation by allowing for this dynamic reallocation.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.21 no.5
• /
• pp.113-120
• /
• 2013

This paper presents a mathematical model to determine the optimal length of static messages that can achieve more efficient use of a FlexRay network. In order to determine the optimal length of static message, the proposed model evaluates the given set of messages with respect to a network utilization index, which is defined in this work. The efficient use of a FlexRay network is achieved by reallocating any static message whose length is equal or greater than the resulting value to the dynamic segment. The effectiveness of the proposed method is investigated by applying to the SAE benchmark data.

• Journal of KIISE:Information Networking
• /
• v.32 no.4
• /
• pp.471-482
• /
• 2005

The high-speed network permits Grid computing to handle large problem of management areas and share various computational resources. As there are many resources and changes of them in Grid computing, the resources should be detected effectively and matched correctly with tasks to provide high performance. In this paper, we propose a mechanism that maximizes the performance of Grid computing systems. According to a priority, grade and site of heterogeneous resources, we assign tasks to those resources. Initially, a volunteer's priority and ranking are determined by static information like as CPU speed, RAM size, storage size and network bandwidth. And then, the rank of resources is decided by considering dynamic information such as correctness, response time, and error rate. We find that overall Grid system performance is improved and high correctness using resource reallocation mechanism is achieved.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.3
• /
• pp.896-915
• /
• 2023

The network function virtualization (NFV) uses virtualization technology to separate software from hardware. One of the most important challenges of NFV is the resource management of virtual network functions (VNFs). According to the dynamic nature of NFV, the resource allocation of VNFs must be changed to adapt to the variations of incoming network traffic. However, the significant delay may be happened because of the reallocation of resources. In order to balance the performance between delay and quality of service, this paper firstly made a compromise between VNF migration and energy consumption. Then, the long short-term memory (LSTM) was utilized to forecast network traffic. Also, the asymmetric loss function for LSTM (LO-LSTM) was proposed to increase the predicted value to a certain extent. Finally, an experiment was conducted to evaluate the performance of LO-LSTM. The results demonstrated that the proposed LO-LSTM can not only reduce migration times, but also make the energy consumption increment within an acceptable range.