• Journal of KIISE:Computer Systems and Theory
• /
• v.30 no.5_6
• /
• pp.307-318
• /
• 2003

In this paper, we design and construct a TMO object group that provides the guaranteed real-time services in the distributed object computing environments, and verify execution power of its model for the correct distributed real-time services. The TMO object group we suggested is based on TINA's object group concept. This model consists of TMO objects having real-time properties and some components that support the object management service and the real-time scheduling service in the TMO object group. Also TMO objects can be duplicated or non-duplicated on distributed systems. Our model can execute the guaranteed distributed real-time service on COTS middlewares without restricting the specially ORB or the of operating system. For achieving goals of our model. we defined the concepts of the TMO object and the structure of the TMO object group. Also we designed and implemented the functions and interactions of components in the object group. The TMO object group includes the Dynamic Binder object and the Scheduler object for supporting the object management service and the real-time scheduling service, respectively The Dynamic Binder object supports the dynamic binding service that selects the appropriate one out of the duplicated TMO objects for the clients'request. And the Scheduler object supports the real-time scheduling service that determines the priority of tasks executed by an arbitrary TMO object for the clients'service requests. And then, in order to verify the executions of our model, we implemented the Dynamic Binder object and the Scheduler object adopting the binding priority algorithm for the dynamic binding service and the EDF algorithm for the real-time scheduling service from extending the existing known algorithms. Finally, from the numerical analyzed results we are shown, we verified whether our TMO object group model could support dynamic binding service for duplicated or non-duplicated TMO objects, also real-time scheduling service for an arbitrary TMO object requested from clients.

• ETRI Journal
• /
• v.24 no.4
• /
• pp.311-322
• /
• 2002

Presently, optical burst switching (OBS) technology is under study as a promising solution for the backbone of the optical Internet in the near future because OBS eliminates the optical buffer problem at the switching node with the help of no optical/electro/optical conversion and guarantees class of service without any buffering. To implement the OBS network, there are a lot of challenging issues to be solved. The edge router, burst offset time management, and burst assembly mechanism are critical issues. In addition, the core router needs data burst and control header packet scheduling, a protection and restoration mechanism, and a contention resolution scheme. In this paper, we focus on the burst assembly mechanism. We present a novel data burst generation algorithm that uses hysteresis characteristics in the queueing model for the ingress edge node in optical burst switching networks. Simulation with Poisson and self-similar traffic models shows that this algorithm adaptively changes the data burst size according to the offered load and offers high average data burst utilization with a lower timer operation. It also reduces the possibility of a continuous blocking problem in the bandwidth reservation request, limits the maximum queueing delay, and minimizes the required burst size by lifting up data burst utilization for bursty input IP traffic.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.11
• /
• pp.11-19
• /
• 1994

Turnaround time of a job performing frequent disk I/O operations is greatly affected by I/O bottleneck which incurs due to the large gap in the speeds of I/O devices and the CPU. This paper proposes to employ a Write Dedicated Buffer(WDB) in disk arrays to improve the response time for read requests and analyzes the scheduling policies and the efficiency of the WDB. Through a series of simulations we show that, among the three policies examined, the partial stripe join(PSJ) policy is the most effective in terms of response time for both read and write requests and that, especially when using a WDB on declustered arrays, improvement of response time for read requests becomes greater as the request rate increases.

• Journal of Korean Institute of Industrial Engineers
• /
• v.34 no.1
• /
• pp.108-121
• /
• 2008

Dispatching rule for parallel machines with multi product is proposed in this paper, In current market,customer's request for higher quality is increasing, In accordance with such demand, manufacturers are focusingon improving the quality of the products. Such shift in production objective is risky. The possibility ofneglecting another important factor in customer satisfaction increases, namely due dates. From the aspect ofimproving quality, frequency of product assignment to limited number of high performance machines willincrease. This will lead to increased waiting time which can incur delays, In the case of due date orientedproduct dispatch, Products are assigned to machines without consideration for quality. Overall deterioration ofproduct quality is inevitable, In addition, Poor products will undergo rework process which can increase delays.The objective of this research is dispatching products to minimize due date delays while improving overallquality. Quality index is introduced to provide means of standardizing product quality. The index is used toassure predetermined quality level while minimizing product delays when dispatching products. Qualitystandardization method and dispatching algorithm is presented. And performance evaluation is performed withcomparison to various dispatching methods.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.7 no.5
• /
• pp.8-13
• /
• 1997

In multi-server environment there are many servers which are able to process job requests. So we bave to design a mechanism that selects appropriate servers for processing each job request while maximizing server throughput and minimizing average response time of requests. Conventional methods ac~ opt the load of each server as criteria of server selection. that is, they select a server whose load is not bigger than the others. In this work we propose an approach that uses the degree of server performance, server load and the estimated service time of requested job as guidelines of server selection. We incorporate fuzzification techniques and expert knowledge in this approach. Comparing the performances c~f our approach to that of conventional one, experiments show that the proposed approach provides better performances.

• KIPS Transactions on Computer and Communication Systems
• /
• v.8 no.10
• /
• pp.239-244
• /
• 2019

In recent mobile environments, query processing costs have been rapidly increasing as users request large amounts of queries. In addition, the server's performance is increasing for many users to handle high-capacity queries, but the workload is increasing continuously. To solve these problems, we use the wireless broadcasting environment. However, in a existing wireless broadcasting environment, servers have a problem sending all the objects they manage to their clients. Therefore, we propose a new R-Bcast combining the advantages of demand-based and wireless broadcasting. R-Bcast is a technique that protects query information and reduces query processing time. Experiments have proved that R-Bcast is superior to conventional techniques.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.48 no.7
• /
• pp.48-56
• /
• 2011

Recently, new storage device SSD(Solid State Disk) based on NAND flash memory is gradually replacing HDD(Hard Disk Drive) in mobile device and thus a variety of research efforts are going on to find the cost-effective ways of performance improvement. By increasing the NAND flash channels in order to enhance the bandwidth through parallel processing, DRAM buffer which acts as a buffer cache between host(PC) and NAND flash has become the bottleneck point. To resolve this problem, this paper proposes an efficient low-cost scheme to increase SSD performance by improving DRAM buffer bandwidth through scheduling techniques which utilize DRAM multi-banks. When both host and NAND flash multi-channels request access to DRAM buffer concurrently, the proposed technique checks their destination and then schedules appropriately considering properties of DRAMs. It can reduce overheads of bank active time and row latency significantly and thus optimizes DRAM buffer bandwidth utilization. The result reveals that the proposed technique improves the SSD performance by 47.4% in read and 47.7% in write operation respectively compared to conventional methods with negligible changes and increases in the hardware.

• Journal of Digital Convergence
• /
• v.18 no.10
• /
• pp.225-232
• /
• 2020

The underlaying communication scheme in 5G cellular network is a very promising resource sharing scheme, and it is an effective scheme for improving service performance of 5G and reducing communication load between a cellular link and a device to device (D2D) link. This paper proposes the algorithm to minimize the resource interference that occurs when performing 5G-based multi-class service on gNB(gNodeB) and the cooperative priority-based resource allocation scheduling scheme (CPRAS) to maximize 5G communication service according to the analyzed control conditions of interference. The proposed CPRAS optimizes communication resources for each device, and it optimizes resource allocation according to the service request required for 5G communication and the current state of the network. In addition, the proposed scheme provides a function to guarantee giga-class service by minimizing resource interference between a cellular link and a D2D link in gNB. The simulation results show that the proposed scheme is better system performance than the Pure cellular and Force cellular schemes. In particular, the higher the priority and the higher the cooperative relationship between UE(User Equipment), the proposed scheme shows the more effective control of the resource interference.

• The KIPS Transactions:PartA
• /
• v.11A no.5
• /
• pp.355-364
• /
• 2004

These days, various clustering technologies have been adopted to construct web sites. High performance hardware switches have good performance, but have disadvantage of high cost for constructing small and middle-sized web sites. Now a days, many sites have been constructed with the LVS (Linux Virtual Server), which is free of charge and has good performance. Having a centralized load balancing with one front-end, the LVS causes a bottleneck when it receives all at once. In the paper, we suggest a way to remove the LVS bottleneck by providing multiple front-ends. In this architecture, all of cluster nodes act as both a front-end and a back-end. When the load of a node receiving requests is not large enough, the node responds to the client directly. When the load of a node is large enough, the node send the request to a node which is selected by a scheduling algorithm. The scheduling algorithm is discussed to balance loads between servers. While single front-end cluster raises the throughput curvedly, the multiple front-end cluster raises the throughput linearly.

• The KIPS Transactions:PartC
• /
• v.14C no.4
• /
• pp.349-358
• /
• 2007

Ethernet Passive Optical Network(EPON), which is one of PON technologies for realizing FTTx(Fiber-To-The-Curb/Home/Office), can cost-effectively construct optical access networks. In addition, EPON can provide high transmission rate up to 10Gbps and it is compatible with existing customer devices equipped with Ethernet card. To effectively control frame transmission from ONUs to OLT EPON can use Multi-Point Control Protocol(MPCP) with additional control functions in addition to Media Access Control(MAC) protocol function. For EPON, many researches on intra- and inter-ONU scheduling algorithms have been performed. Among the inter-ONU scheduling algorithms, IPS(Interleaved Polling with Stop) based on polling scheme is efficient because OLT assigns available time portion to each ONU given the request information from all ONUs. Since the IPS needs an idle time period on uplink between two consecutive frame transmission periods, it wastes time without frame transmissions. In this paper, we propose a dynamic bandwidth allocation algorithm to increase the channel utilization on uplink and evaluate its performance using simulations. The simulation results show that the proposed Two-phase Cycle Danamic Bandwidth Allocation(TCDBA) algorithm improves the throughput about 15%, compared with the IPS and Fast Gate Dynamic Bandwidth Allocation(FGDBA). Also, the average transmission time of the proposed algorithm is lower than those of other schemes.