• Journal of Web Engineering
• /
• v.21 no.1
• /
• pp.27-52
• /
• 2021

With recent increases in the number of network-connected devices, the number of edge computing services that provide similar functions has increased. Therefore, it is important to recommend an optimal edge computing service, based on quality-of-service (QoS). However, in the real world, there is a cold-start problem in QoS data: highly sparse invocation. Therefore, it is difficult to recommend a suitable service to the user. Deep learning techniques were applied to address this problem, or context information was used to extract deep features between users and services. However, edge computing environment has not been considered in previous studies. Our goal is to predict the QoS values in real edge computing environments with improved accuracy. To this end, we propose a GAIN-QoS technique. It clusters services based on their location information, calculates the distance between services and users in each cluster, and brings the QoS values of users within a certain distance. We apply a Generative Adversarial Imputation Nets (GAIN) model and perform QoS prediction based on this reconstructed user service invocation matrix. When the density is low, GAIN-QoS shows superior performance to other techniques. In addition, the distance between the service and user slightly affects performance. Thus, compared to other methods, the proposed method can significantly improve the accuracy of QoS prediction for edge computing, which suffers from cold-start problem.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.8
• /
• pp.30-38
• /
• 1999

On providing MPEG-2 video service through the ATM network, it is necessary for network provider to have the ATM QoS objectives in order to guarantee quality of service required by end users at the application layer. In this paper, the degradation of QoS caused by cell losses at application layer is assessed quantitatively by GIQ model considering AAL layer and is evaluated qualitatively by MOS from the viewpoint of the end users in order to analyze the relation between CLR and QoS of MPEG-2 video. From the simulation and empirical results, we know that CLR and $GIQ_{mean}$ for guaranteeing QoS of MOS grade 5(Excellent) are $CLR{\le}4{\times}10^7$ & $GIQ_{mean}{\ge}99.4%$ and those for guaranteeing QoS of MOS grade 4(Good) are $CLR{\le}2{\times}10^6$ & $GIQ_{mean}{\ge}99.705%$.

• Journal of Korea Multimedia Society
• /
• v.9 no.1
• /
• pp.73-88
• /
• 2006

With the development of Next Generation convergence Network, the current Internet needs a new network architecture and new session establishment methods, which can support various applications requiring differentiated traffic processing and high quality of service instead of the conventional best-effort service. It is expected that, in next generation network based on All-IP. SIP will play an important role in the session establishment between the end to end user terminals. In this paper, we propose a new network architecture that can provide quality of service based on SIP using the QoS enabled SIP servers and policy servers, and we also propose a new session establishment method that apply the user's demands participating the session establishment when setting up the session using the SIP. Through simulations under various environments, we show the parameter ranges in terms of server capacity and the number of users in access networks to achieve reasonable delay bounds.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.117-118
• /
• 2006

Recently, the fusion of communication and broadcasting surfaces streaming service such as IPTV with killer application of BcN. In this paper, Premium IP multicast is called as transport service technology that transfer streaming service such as IPTV through integrated, controllable, maintainable network in order to guarantee end-to-end QoS to predefined person. It capacitates billing of multicast service instead of network operator guarantees high quality QoS to subscriber. So, network operators are able to create benefits and find benefit models. The other side, subscribers can use various high quality streaming services.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.5 no.6
• /
• pp.1104-1109
• /
• 2001

In this paper, we describe a method for real-time transmitting video streams based on RTP. In order to guarantee synchronous video streams, we propose a method to grasp network situations by analyzing end-to-end network traffic. In addition, we present an algorithm for satisfying QoS requirements of real-time multimedia transmission and maintaining continuity of transmission. It describes a buffering method for overcoming bandwidth limitations and an analyzing method based on RTCP for grasping network traffic situation to resolve the problem of real-time transmission of video streams.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2001.10a
• /
• pp.169-172
• /
• 2001

In this paper, we describe a method for real-time transmitting video streams based on RTP In order to guarantee synchronous video streams, we propose a method to grasp network situations by analyzing end-to-end network traffic. In addition, we present an algorithm for satisfying QoS requirements of real-time multimedia transmission and maintaining continuity of transmission. It describes a buffering method for overcoming bandwidth limitations and an analyzing method based on RTCP for grasping network traffic situation to resolve the problem of real-time transmission of video streams.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.6
• /
• pp.672-686
• /
• 2002

현재 단대단(End-to-End) 비디오 서비스의 질을 높이기 위해 많은 연구가 각 계층별로 진행되고 있다. 전송계층에서의 오류 제어(Error Control), 네트워크계층에서의 QoS (Quality of Service)모델, 표현 및 응용계층에서의 오류 강인성(Error resilience)/오류 은닉(Error concealment) 등이 연구 개발되고 있다. 그러나 계층 간의 연관성이 높은 부분에서의 통합을 통한 성능향상에 관한 연구는 그 필요성과 효율에 비해 아직도 미흡하다. 본 논문은 QoS 서비스 모델하에서의 적응적 FEC(Forward Error Correction) 적용 및 우선순위에 따른 비디오패킷(VP ,VideoPacket)을 통하여 효율적인 계층화 비디오 스트리밍을 단대단 QoS성능의 향상에 관점을 맞추어 제안한다. 제안하는 방식은 최소 화질 보장과 같은 효율에서 보다 적은 가격에서의 서비스를 제공할 수 있다. 이를 위하여 통합형 서비스(IntServ, IS, Integrated Service) 의 자원예약을 사용하는 방법과 높은 가격의 자원 예약을 사용하지 않는 차별화 서비스(DiffServ, DS, Differentiated Service)를 적용했으며 이에 보장형 서비스의 특징을 공통을 가지기 위해 계층화 FEC를 적용하였으며 적절한 가격의 조절을 위하여 비디오패킷을 통한 데이터 분할을 적용하였다. 본 논문은 또한 최종 사용자의 만족도를 PSNR(Picture Signal to Noise Ration)과 PSNR에서 표현하지 못하는 부분의 평가를 위해 손상프레임율(DFR, Damaged Frame Ratio)과 오류프레임율(EFR,Error Frame Ratio)을 제안 이를 통해 평가하고자 한다. 제안하는 방식의 실험 결과는 비디오 코딩계층과 전송 계층, 네트워크 계층의 결합된 성능이며 이는 또한 화질의 개선뿐만 아니라 사용자의 가격문제에 대하여서도 비교 분석하였다.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.15 no.1
• /
• pp.16-27
• /
• 2012

In multi-interface multi-channel(MIMC) based tactical ad hoc networks, QoS support for required operational capacity is one of the main challenging issues for multi-hop transmissions. To support QoS in such a harsh environment, we propose a novel MAC scheme to minimize multi-hop as well as per-hop delay. The current IEEE 802.11 MAC protocols should contend to reserve the channel resource at every hop by each sender. The every-hop channel contention results in a degradation of end-to-end delay for multi-hop transmissions. The basic idea of our scheme is to make a "multi-hop reservation" at the MAC layer by using the modified RTS frame. It contains additional information such as destination information, packet priority, and hop count, etc. In addition, we differentiate the contention window area according to the packet priority and the number of hops to deliver packets in the predefined allowed latency. Our scheme can minimize the multi-hop delay and support the QoS of the critical data in real time(i.e., VoIP, sensing video data, Video conference between commanders). Our simulation study and numerical analysis show that the proposed scheme outperforms the IEEE 802.11 MAC.

• The KIPS Transactions:PartB
• /
• v.8B no.5
• /
• pp.507-514
• /
• 2001

In VOD(Video-on-Demand) system, the real-time interactive service is one of the most important factor to determine the degree of QoS(Quality of Service). In this paper, we propose the head-end system consisted of switching agent and head-end node, which needs to receive the only video stream for multiple users which have requested the same video, to serve the unlimited interactive service which has no service delay and block. The unlimited VCR services can be served by storing the video stream with buffer at client and head-end node. And the proposed algorithm presents the method to enhance the efficiency by buffer, offer the true interactive VOD services to users because all of service requested by clients are processed immediately. In this paper, we implemented the VOD system which has the VCR functions without service delay and block. Simulation results indicate that the proposed algorithm has better performance in the number of service request and time interval.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.40 no.10
• /
• pp.59-66
• /
• 2003

We propose the novel optical burst switching scheme to guarantee a minimum bandwidth for multiple classes. To date, QoS studies on OBS network are capable of differentiating two classes, but have difficulties in providing a minimum bandwidth lot several classes because of lower classes' collision with the highest class bursts in the networks. To solve that problem, in our proposed scheme we assign time zones in a data channel for each class periodically, making one burst have top priority at least its zone. Also, the new burst assembling algorithm, as well as the way of managing data channel, is necessarily proposed to coordinate with the proposed OBS scheme. Through the evaluation, we show that the worst-case end-to-end delay is small enough and the received bandwidth of the lower classes is still assured regardless of the traffic load of the highest class.