• Journal of KIISE:Computer Systems and Theory
• /
• v.34 no.2
• /
• pp.49-56
• /
• 2007

MEMS-based storage is being developed as a new storage media. Due to its attractive features such as high-bandwidth, low-power consumption, high-density, and low cost, MEMS storage is anticipated to be used for a wide range of applications from storage for small handhold devices to high capacity mass storage servers. However, MEMS storage has vastly different physical characteristics compared to a traditional disk. First, MEMS storage has thousands of heads that can be activated simultaneously. Second, the media of MEMS storage is a square structure which is different from the platter structure of disks. This paper presents a new request scheduling algorithm for MEMS storage that makes use of the aforementioned characteristics. This new algorithm considers the parallelism of MEMS storage as well as the seek time of requests on the two dimensional square structure. We then extend this algorithm to consider the aging factor so that starvation resistance is improved. Simulation studies show that the proposed algorithms improve the performance of MEMS storage by up to 39.2% in terms of the average response time and 62.4% in terms of starvation resistance compared to the widely acknowledged SPTF (Shortest Positioning Time First) algorithm.

• Journal of KIISE:Information Networking
• /
• v.37 no.1
• /
• pp.42-49
• /
• 2010

Because sensor nodes operate with the limited power based on battery which cannot be easily replaced, energy efficiency is a fundamental issue pervading the design of communication protocols developed for wireless sensor networks. In wireless networks, energy efficient MAC protocols can usually be described as being either a contention-based protocol or a schedule-based protocol. It is suitable to use combination of both contention-based protocol and schedule-based protocol, because the strengths and weaknesses of these protocols are contrary to each other. In this paper, in order to minimize energy consumption of sensor nodes and maximize network lifetime, we propose a new MAC protocol called "Tiered-MAC" The Tiered-MAC uses a schedule-based TDMA inside maximum transmission range of sink node and a contention-based CSMA otherwise. Therefore, by efficiently managing the congested traffic area, the Tiered-MAC reduces the unnecessary energy consumption. Based on the ns-2 simulation result, we prove that the Tiered-MAC improves the energy-efficiency of sensor network nodes.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.7
• /
• pp.429-439
• /
• 2006

A desktop grid, which is a computing grid composed of idle computing resources in a large network of desktop computers, is a promising platform for compute-intensive distributed computing applications. However, due to reliability and unpredictability of computing resources, effective scheduling of parallel computing applications on such a platform is a difficult problem. This paper proposes a new scheduling method aimed at reducing the total execution time of a parallel application on a desktop grid. The proposed method is based on utilizing the histories of execution behavior of individual computing nodes in the scheduling algorithm. In order to test out the feasibility of this idea, execution trace data were collected from a set of 40 desktop workstations over a period of seven weeks. Then, based on this data, the execution of several representative parallel applications were simulated using trace-driven simulation. The simulation results showed that the proposed method improves the execution time of the target applications significantly when compared to previous desktop grid scheduling methods. In addition, there were fewer instances of application suspension and failure.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.1B
• /
• pp.20-26
• /
• 2010

The downlink scheduling algorithm has a great impact on the performance of mobile telecommunication system. In proportional fairness (PF) scheduling algorithm, the resource is allocated proportionally to the quality of wireless channel. Thus, PF has difficulty in servicing the users having more downlink traffic. One can allocate the resource proportionally to the accumulated queue length. However, this leads to system throughput degradation since the users having low channel quality get more and more resource allocated due to accumulation property of queue. In this paper, we propose a new downlink scheduling algorithm, which extends PF algorithm by incorporating downlink traffic arrival rate. The proposed algorithm can effectively cope with users having more downlink traffic, and maintain high system throughput by eliminating accumulation effect in the algorithm. With computer simulations, it is verified that the proposed algorithm performs better than existing algorithms.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.6B
• /
• pp.377-386
• /
• 2005

Recently, to increase throughput per hour on real-time disk scheduling, a lot of algorithms that apply SCAN technique to EDF(Earliest Deadline First) that is representative real-time disk scheduling algorithm are studied. However, existing disk scheduling algorithms have several limitations because they consider continuous I/O requests when create SCAN group. Also, because SCAN technique was fixed direction, the existing algorithms have shortcoming that there are a lot of time damages. This paper proposes a new real-time disk scheduling algorithm based on the insertion technique and the two-way SCAN technique to solve the problems of the exiting real-time disk scheduling algorithms in hard real-time system. The simulation result shows that, when using our techniques, the disk throughput and the number of serviceable I/O requests are enhanced.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.1
• /
• pp.1-9
• /
• 2024

This paper proposes an integration of the ED-H scheduling algorithm, known for optimal real-time scheduling, with the LoRaEnergySim simulator. This integration facilitates the simulation of interactions between real-time scheduling algorithms for tasks with time constraints in Class-A LoRaWAN Class-A devices using a super-capacitor-based energy harvesting system. The time and energy characteristics of LoRaWAN status and state transitions are extracted in a log format, and the task model is structured to suit the time-slot-based ED-H scheduling algorithm. The algorithm is extended to perform tasks while satisfying time constraints based on CPU executions. To evaluate the proposed approach, the ED-H scheduling algorithm is executed on a set of tasks with varying time and energy characteristics and CPU occupancy rates ranging from 10% to 90%, under the same conditions as the LoRaEnergySim simulation results for packet transmission and reception. The experimental results confirmed the applicability of co-simulation by demonstrating that tasks are prioritized based on urgency without depleting the supercapacitor's energy to satisfy time constraints, depending on the scheduling algorithm.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11a
• /
• pp.826-828
• /
• 2005

인텔의 IA-64 프로세서는 명령어 수준의 병렬수행을 지원하는 EPIC (Explicitly Parallel Instruction Computing) 구조를 채택하고 있으며 컴파일러가 순차적 코드에서 병렬 수행이 가능한 독립적인 명령어들을 스케줄링 하도록 되어있다. 본 논문에서는 IA-64 스케줄링을 위해 향상된 파이프라인 스케줄링 (Enhanced Pipeline Scheduling, EPS) 기법[1]을 적용한 결과를 소개한다. EPS는 루프수준의 병렬화를 위한 소프트웨어 파이프라이닝 (software pipelining)기법으로 전역 스케줄링 (global Scheduling) 기법을 기반으로 하고 있다. 우리는 IA-64 프로세서를 위한 공개소스 컴파일러인 ORC (Open Research Compiler)에 EPS를 구현하고 실제 프로세서인 Itanium에서 실험을 수행하였다. 상용 프로세서와 컴파일러에 구현과 튜닝을 하는 과정에서 얻은 경험을 소개하고 기존의 ORC 컴파일러와 비교하여 얻은 성능 향상을 보고하고 분석한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04a
• /
• pp.667-669
• /
• 2002

이 논문은 행위 합성(behavioral synthesis)에서 전력 소모 최적화를 위한 효율적인 알고리즘을 제안한다. 이전의 논문에서 전력 최적화를 위한 여러가지의 하드웨어 할당/바인딩(allocation/binding) 문제들이 네트워크 플로우 문제로 나타내어 질 수 있고, 최적으로 풀릴 수 있음이 보여졌다. 그러나, 그 연구에서는 고정된 스케줄이 가정되고 있다. 이와 관련해서 주어진 스케줄에 대한 하드웨어 할당/바인딩 문제를 위한 최적의 네트워크 플로우 결과가 주어졌을 때, 주어진 스케줄을 일부분 바꾼 것에 데란 새로운 최적의 네트워크 플로우 결과를 얻는 것이 주요 문제이다. 이 때문에 우리는 네트워크 구조와 플로우 계산간의 관계에 대한 분석으로 부터 최대 플로우 계산 단계와 최소 비용 계산 단계의 2단계 과정을 고안하였다. 실험결과를 통해 우리의 설계가 스케줄의 영향과 각 스케줄에 대한 최적의 바인딩을 이용함으로써 전력 소모와 계산 시간에서 매우 향상된 결과를 얻을 수 있음을 볼 수 있다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1999.05a
• /
• pp.208-212
• /
• 1999

실시간 스케줄가능성 분석에 대한 기존의 방법들은 프로세스의 모든 상태공간을 추적하거나 고정 우선 순위 스케줄 방법을 사용하기 때문에 시간 및 공간에 대한 복잡성이 증가된다. 본 논문에서는 프로세스 대수의 전이규칙을 이용하여 프로세스의 최소 수행시간, 주기, 마감시간, 동기화 시간을 고려하여 실시간 프로세스가 마감시간을 지키는가를 판단하고, GUI 환경을 기반으로 스케줄이 불가능한 프로세스에 대해 스케줄 가능하게 하는 회복 알고리즘을 제안하고, 이들의 상태 공간을 화면상에 표시해 주는 실시간 프로세스의 상태 분석기를 구현한다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.9A
• /
• pp.1507-1515
• /
• 2001

본 논문은 실시간 커널과 비실시간 커널의 특성을 모두 가질 수 있는 이중 실시간 커널의 설계를 위한 이중 큐 스케줄링 알고리즘을 제안한다. 본 논문에서는 제안한 실시간 커널은 실시간 제약들을 고려한 실시간 커널과 비실시간 커널의 특성을 가지도록 설계한다. 그리고 실시간 태스크 안에는 인터럽트처리를 수행하고, 비실시간 태스크는 일반적인 작업을 수행한다. 실시간 커널에는 인터럽트 처리와 실시간 태스크를 처리하도록 하였다. 비실시간 커널은 일반적인 태스크를 처리하도록 한다. 또한 실시간 커널과 비실시간 커널을 이중 큐를 통하여 태스크의 처리를 수행한다. 그리고 실시간 태스크는 고정 우선 순위기반 스케줄링인 RMS을 사용하여 실시간 태스크 스케줄링을 한다. 제안된 실시간 시스템은 RT-Linux, QNX와 인터럽트 지연, 스케줄링 정확성, 메시지 전달시간 등을 비교 분석하여 효율성을 입증한다.