• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.9
• /
• pp.585-591
• /
• 2006

Generalized Processor Sharing(GPS) model provides instantaneous fair services to currently backlogged sessions. Since this fair service distributes server capacity to backlogged sessions in proportion to their weights, the fairness is only valid between the sessions serviced at the same time. From the long time view, however, this fair service provides different server capacity with one session or another, even if these sessions have the same weights. This paper proposes a cumulative fair service(CFS) model to provide fair server capacity to all sessions in the long time view. This model provides fair service in session Viewpoint because it distributes server capacity in proportion to the weights of sessions. The model and an algorithm referencing that model are analyzed for their properties and performances. Performance evaluations verify that the proposed algorithm provides proportional service capacity to sessions in the long time view.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.4C
• /
• pp.343-355
• /
• 2003

Fair bandwidth allocations at routers protect adaptive flows from non-adaptive ones and may simplify end-to end congestion control. However, traditional fair bandwidth allocation mechanisms, like Weighted Fair Queueing and Flow Random Early Drop, maintain state, manage buffera and perform packet scheduling on a per-flow basis. These mechanisms are more complex and less scalable than simple FIFO queueing when they are used in the interi or of a high-speed network. Recently, to overcome the implementation complexity problem and address the scalability and robustness, several fair bandwidth allocation mechanisms without per-flow state in the interior routers are proposed. Core-Stateless Fair Queueing and Rainbow Fair Queuing are approximates fair queueing in the core-stateless networks. In this paper, we proposed simple Layered Fair Queueing (SLFQ), another core-stateless mechanism to approximate fair bandwidth allocation without per-flow state. SLFQ use simple layered scheme for packet labeling and has simpler packet dropping algorithm than other core-stateless fair bandwidth allocation mechanisms. We presente simulations and evaluated the performance of SLFQ in comparison to other schemes. We also discussed other are as to which SLFQ is applicable.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.47 no.2
• /
• pp.40-46
• /
• 2010

Multi-user MIMO (Multiple-Input Multiple-Output) systems require collaborative PF schedulers to improve the performance of the log sum of average transmission rates. While the performance of single cell based conventional PF schedulers has been evaluated over various channel conditions, scheduling algorithms by multiple base stations which select multiple users over a given time frame and their performance require further investigations. In this paper, we apply a collaborative PF scheduler to the distributed multi-user MIMO system, which assigns radio resources to multiple users by exchanging user channel information from base stations located in three adjacent sectors. We further evaluate its performance in terms of the log sum of average transmission rates. The performance is compared to that of the full-search collaborative PF scheduler which searches over all possible combinations of user groups, and that of a parallel PF scheduler that determines users without channel information exchange among base stations. We show the log sum of average transmission rates of the collaborative PF scheduler outperforms that of the parallel PF scheduler in low percentile region. In addition, the collaborative PF scheduler exhibits a negligible performance degradation when compared to the full-search collaborative PF scheduler while a significant reduction of the computational complexity is achievable at the same time.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.7
• /
• pp.370-379
• /
• 2006

Computational grid provides the environment which integrates v 따 ious computing resources. Grid environment is more complex and various than traditional computing environment, and consists of various resources where various software packages are installed in different platforms. For more efficient usage of computational grid, therefore, some kind of integration is required to manage grid resources more effectively. In this paper, a global scheduler is suggested, which integrates grid resources at meta level with applying various scheduling policies. The global scheduler consists of a mechanical part and three policies. The mechanical part mainly search user queues and resource queues to select appropriate job and computing resource. An algorithm for the mechanical part is defined and optimized. Three policies are user selecting policy, resource selecting policy, and executing policy. These can be defined newly and replaced with new one freely while operation of computational grid is temporarily holding. User selecting policy, for example, can be defined to select a certain user with higher priority than other users, resource selecting policy is for selecting the computing resource which is matched well with user's requirements, and executing policy is to overcome communication overheads on grid middleware. Finally, various algorithms for user selecting policy are defined only in terms of user fairness, and their performances are compared.

• The KIPS Transactions:PartC
• /
• v.15C no.4
• /
• pp.281-288
• /
• 2008

Recently, the advance of multimedia hardware has fostered the development of wireless multimedia sensor network which is able to ubiquitously obtain multimedia content such as image or audio from the environment. The multimedia data which has several characteristics such as large size and correlation between the data requires reliability in transmission. However, the existing solution which take the focus on the efficiency of network mainly, is not appropriate to transmit the multimedia data. In the paper, we proposes a reliable asynchronous image transfer protocol, RAIT. RAIT applies double sliding window method in node-to-node image tansfer to prevent the packet loss caused by network congestion. The double sliding window consists of one sliding window for the receiving queue, which is used for prevention of packet loss caused by communication failure between nodes and the other sliding window for the sending queue which prevents the packet loss caused by network congestion. the routing node prevents the packet loss and guarantees the fairness between the nodes by scheduling the packets based on the image non-preemptively. The RAIT implements the double sliding window method by cross layer design between RAIT layer, routing layer, and queue layer. The experiment shows that RAIT guarantees the reliability of image transmission compared with the existing protocol.