• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.8
• /
• pp.2774-2796
• /
• 2015

Quality-of-service (QoS) provisioning for a cognitive mesh network (CMN) with heterogeneous services has become a challenging area of research in recent days. Considering both real-time (RT) and non-real-time (NRT) traffic in a multihop CMN, [1] studied cross-layer resource management, including joint access control, route selection, and resource allocation. Due to the complexity of the formulated resource allocation problems, which are mixed-integer non-linear programming, a low-complexity yet efficient algorithm was proposed there to approximately solve the formulated optimization problems. In contrast, in this work, we present an application of genetic algorithm (GA) to re-address the hard resource allocation problems studied in [1]. Novel initialization, selection, crossover, and mutation operations are designed such that solutions with enough randomness can be generated and converge with as less number of attempts as possible, thus improving the efficiency of the algorithm effectively. Simulation results show the effectiveness of the newly proposed GA-based algorithm. Furthermore, by comparing the performance of the newly proposed algorithm with the one proposed in [1], more insights have been obtained in terms of the tradeoff among QoS provisioning for RT traffic, throughput maximization for NRT traffic, and time complexity of an algorithm for resource allocation in a multihop network such as CMN.

• Journal of Internet Computing and Services
• /
• v.15 no.3
• /
• pp.1-10
• /
• 2014

The cloud computing paradigm introduced pay-per-use models in which IT services can be created and scaled on-demand. However, service providers are still concerned about the constraints imposed by their physical infrastructures. In order to keep the required QoS and achieve the goal of upholding the SLA, virtualized resources must be efficiently consolidated to maximize system throughput while keeping energy consumption at a minimum. Using ANN, we propose a predictive SLA-aware approach for consolidating virtualized resources in a cloud environment. To maintain the QoS and to establish an optimal trade-off between performance and energy efficiency, the server's utilization threshold dynamically adapts to the physical machine's resource consumption. Furthermore, resource-intensive VMs are prevented from getting underprovisioned by assigning them to hosts that are both capable and reputable. To verify the performance of our proposed approach, we compare it with non-optimized conventional approaches as well as with other previously proposed techniques in a heterogeneous cloud environment setup.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.11a
• /
• pp.41-44
• /
• 2014

최근 클라우드 컴퓨팅에 관련된 기술이 각광을 받으면서, 기존에 인터넷을 통해 제공되던 다양한 서비스들이 클라우드 컴퓨팅 플랫폼 환경으로 이동하고 있다. 이를 통해 사용자들에게는 좀 더 편리하고 유연한 서비스를 제공하고 서비스 제공자들에게는 기존 관리 비용의 절감을 할 수 있게 되었다. 하지만 현재 폭발적인 수요의 증가로 인해, 기존의 자원 활용도의 극대화를 목적으로 고안된 자원 분배 기법들에 대한 여러 한계점이 나타나게 되었다. 본 논문에서는 이러한 문제점들을 해결하고자 클라우드 컴퓨팅 환경에서 Qos를 기반으로 사용자나 서비스 제공자의 비용적인 측면을 고려한 자원분배를 통해 서비스를 제공시 사용자 요구를 만족시키고 동시에 서비스 공급자에게는 비용 효율적인 프로비저닝(Provisioning)기법을 제안하고자 한다. 실험 결과 기존의 자원 활용도에 중점을 둔 기법보다 사용자 요청에 대한 응답 속도가 8.35% 향상되었으며, 컴퓨터 자원 유지 관련 비용면에서도 기존 대비 11.31% 절감 효과를 가져오는 것을 확인 할 수 있었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.7
• /
• pp.2530-2547
• /
• 2015

In the recent years, femtocell technology has received a considerable attention due to the ability to provide an efficient indoor wireless coverage as well as enhanced capacity. However, under the spectrum sharing between femtocell user equipment (FUEs) and the owner of spectrum macrocell user equipment (MUEs), both may experience higher uplink interference to each other. This paper proposes a novel distributed power control algorithm for the interference management in two-tier femtocell networks. Due to the assignment of licensed radio frequency to the outdoor macrocell users, the access priority of MUEs should be higher than FUEs. In addition, the quality of service (QoS) of MUEs that is expressed in the target signal-to-interference-plus-noise ratio (SINR) must always be achieved. On the other hand, we consider an efficient QoS provisioning cost function for the low-tier FUEs. The proposed algorithm requires only local information and converges even in cases where the frontiers of available power serve the target SINRs impossible. The advantage of the algorithm is the ability to implement in a distributed manner. Simulation results show that the proposed algorithm based on our cost function provides effective resource allocation and substantial power saving as compared to the traditional algorithms.

• Journal of Advanced Navigation Technology
• /
• v.17 no.4
• /
• pp.435-441
• /
• 2013

This paper proposes a neural net based-predictive connection admission control (CAC) scheme for multiclass users in wireless cognitive radio networks. We classifies cognitive users(cu) into real and non real time services, and then permit only real time services to reserve the demanded resource for spectrum handoff in guard channel for provisioning the desired QoS. Neural net is employed to predict primary user's arrival on time and demanded channels. Resource scheduling scheme is based on $C_IA$(cognitive user I complete access) shown in this paper. For keeping primary users from interference, the CAC is performed on only cognitive user not primary user. Simulation results show that our schemes can guarantee the desired QoS by cognitive real time services.

• Journal of Korea Multimedia Society
• /
• v.11 no.10
• /
• pp.1446-1459
• /
• 2008

In an infrastructure-based wireless network, an access point is used for all communications among mobile devices. However, when a mobile device moves into a dead Bone, a connectivity disruption between the mobile device and the access point occurs. Such connectivity disruption consequently leads to another connectivity disruption between the mobile device moving toward the dead zone and other wireless-enabled devices located within the area of the infrastructure-based wireless network. To cope with the connectivity disruption in the infrastructure-based wireless network the ad hoc network that dynamically forms a network without any preexisting communication infrastructure needs to be set up to provide seamless connections among mobile devices. In this paper, we propose the DNSQ-MAC (Dynamic Network State aware QoS-Medium Access Control) technique that meets the deadlines of MAC frames forwarded over hop-by-hop multipaths and guarantees the QoS performance of an ad hoc-based wireless network. Mobile devices incorporating the DNSQ-MAC technique are capable of adjusting to the new dynamic network status in order to enhance the QoS performance in the ad hoc-based wireless network. A case study which exploits the Qualnet simulator shows that the proposed DNSQ-MAC technique can guarantee the deadlines of MAC frames forwarded over hop-by-hop multipaths and enhance the QoS performance of various routing protocols and packet schedulers running on the network layer above the MAC layer.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.5
• /
• pp.1567-1587
• /
• 2014

Virtual Machine (VM) resource management is crucial to satisfy the Quality of Service (QoS) demands of various multimedia services in a media cloud platform. To this end, this paper presents a VM resource allocation model that dynamically and optimally utilizes VM resources to satisfy QoS requirements of media-rich cloud services or applications. It additionally maintains high system utilization by avoiding the over-provisioning of VM resources to services or applications. The objective is to 1) minimize the number of physical machines for cost reduction and energy saving; 2) control the processing delay of media services to improve response time; and 3) achieve load balancing or overall utilization of physical resources. The proposed VM allocation is mapped into the multidimensional bin-packing problem, which is NP-complete. To solve this problem, we have designed a Mixed Integer Linear Programming (MILP) model, as well as heuristics for quantitatively optimizing the VM allocation. The simulation results show that our scheme outperforms the existing VM allocation schemes in a media cloud environment, in terms of cost reduction, response time reduction and QoS guarantee.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.6 no.1
• /
• pp.41-47
• /
• 2002

Path setup considering QoS is one of the main problems to solve in Internet traffic engineering. In network restoration that is one of the traffic engineering components, to establish a backup path or backup path for a working path to be protected is the main task. The backup path should have enough bandwidth to guarantee the working paths. Thus this work requires the QoS routing solution that is to set up a backup path as well as a working path at the same time provisioning enough bandwidth. In this paper, we propose an algorithm to setup a backup path that shares the bandwidth of other backup paths whose working path does not pass along the same link with the working path we are considering. In this way we can reduce much bandwidth consumption caused by setting up backup paths. We also analyze the disjoint path computation algorithms. Finally we show simulation results how the algorithm can reduce the bandwidth consumption and how it will affect blocking when we setup paths.

• Proceedings of the IEEK Conference
• /
• 2000.07a
• /
• pp.529-532
• /
• 2000

This paper addresses how to be connected with end-to-end shortcut using ATM Switched Virtual Connection (SVC) in ATM-based Multi-Protocol Label Switching (MPLS) Networks. Without additionally existing ATM Ships-in-the-Night (SIN) mode, when the stream is continuously transmitted at the same destination with the lapse of determined aging time, the connection is changed with end-to-end shortcut connection using ATM signaling. An ATM direct short circuit is performed an IP and ATM effective integration. An ATM shortcut has a number of advantages, like higher throughput, shorter end-to-end delay, reduced router load, better utilization of L2 Quality of Service (QoS) capabilities, and route optimization. In particular between other MPLS domains, this can be efficiently improved the performance of networks.

• Journal of The Institute of Information and Telecommunication Facilities Engineering
• /
• v.2 no.3
• /
• pp.9-16
• /
• 2003

In this paper, we propose the burst error reduction (BER) algorithm for VoIP service in the wireless LAN network. In end point device, this BER algorithm can be achieved packet loss bounded QoS provisioning using interleaving in buffering and FEC (Forward Error Correction) through transmitting voice packet. BER algorithm can reduced the voice packet loss rate 5.5%-60% in VoIP network using wireless LAN.