• 정보과학회 논문지
• /
• 제43권2호
• /
• pp.152-162
• /
• 2016

비 휘발성 메모리를 할당받아 사용하기 위해서는 비 휘발성 메모리 전용의 가비지 수집 기법이 필수적이다. 본 논문에서는 이를 위해 비 휘발성 메모리 할당 정보 관리용 메타데이터를 설계하였고 이를 Allocation Tree라고 명명하였다. 이 메타데이터는 검색 속도의 향상을 위해 트리 자료구조를 이용하여 구성되었고, 하나의 노드 안에는 할당 메모리 시작 주소와 저장소 ID 정보가 키-밸류 형태로 저장된다. 비 휘발성 메모리 공간이 부족하여 가용 공간이 70% 이하로 떨어지면 가비지 수집기가 작동되어 가비지 수집을 수행하게 되고 Allocation Tree와 사용자 데이터를 비교하여 가비지를 판정한다. 본 연구에서는 이 알고리즘을 Persistent Heap기반의 메모리 할당 플랫폼인 'HEAPO'에서 구현하여 정상적으로 동작함을 증명하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -1
• /
• pp.58-61
• /
• 2002

In this paper, we present a new generalized k-Tree-based (CU/PE) allocation model to perform dynamic resource (CU/PE) allocation/deallocation decision for the reconfigurable MSIMD/MIMD multi-dimensional (k-D) mesh-connected architectures. Those reconfigurable multi-SIMD/MIMD systems allow dynamic modes of executing tasks, which are SIMD and MIMD. The MIMD task requires only the free sub-system; however the SIMD task needs not only the free sub-system but also the corresponding free CU. In our new k-Tree-based (CU/PE) allocation model, we introduce two best-fit heuristics for the CU allocation decision: 1) the CU depth first search (CU-DFS) in O(kN$_{f}$ ) time and 2) the CU adjacent search (CU-AS) in O(k2$^{k}$ ) time. By the simulation study, the system performance of these two CU allocation strategies was also investigated. Our simulation results showed that the CU-AS and CU-DFS strategies performed the same system performance when applied for the reconfigurable MSIMD/MIMD 2-D and 3-D mesh-connected architectures.

• The Korean Journal of Ecology
• /
• 제6권4호
• /
• pp.1-9
• /
• 1983

The observation of branching pattern on Magnolia denudata Desr. was performed from July 1982 to September 1983 and then computer simulation was carried out. Tree crown pattern depends on not genetic factors but also environmental factors and the determination of branchin pattern which characterized it appears to properly explain the relationships such as branching pattern and allocation of materials through the analysis of influence branches under several assumptions. Now that computer simulated simulated pattern was considered as the accumulation of two factors which controled the growth, it was represented as the stimulated tree which differs in branching rate that described allocation of material necessary for the growth of each branch. There was a tendency of allocation ratio of nutrients, i.e. subbranch to main branch to decrease by the passage of year. Under assumption that branch was branched when accumulated material reached 1, it was possible to represent the allocation of nutrients are residual $nutrient{\times}\frac{1}{1+F};in main; branch, ; residual; nutrient{\times}\frac{F}{1+F}$ in subbranch, A(iA, iC)+$F^(iA-1)$ in current twig. Like this, the basic minute difference of the allocation of nutrients according to the branch resulted in complicated patterns in the tree crown.

• 전자공학회논문지B
• /
• 제30B권4호
• /
• pp.27-36
• /
• 1993

This paper proposes a shortest path allocation algorithm over the processors on the hypercube system based on the message passing techniques with the optimized module allocation. On multiprocessor systems, how to divide one task into multiple tasks efficiently is an important issue due to the hardness of the life cycle estimation of each process. To solve the life cycle discrepancies, the appropriate task assignment to each processor and the flexible communications among the processors are indispensible. With the concurrent program execution on hypercube systems, each process communicaties to others with the method of message passing. And, each processor has its own memory. The proposed algorithm generates a callable tree out of the module, assigns the weight factors, constructs the allocation graph, finds the shortest path allocation tree, and maps them with hypercube.

• 대한산업공학회지
• /
• 제42권2호
• /
• pp.151-164
• /
• 2016

In this paper, we deal with a risk analysis for an IPS (Integrated power system) and propose a simulation model combining the fault tree and event tree in order to estimate the system availability and risk level, together. Firstly, the basic information such as operational scenarios, physical structure, safety systems is explained in order to make the fault tree and event tree of the IPS. Next, we propose a discrete-event simulation model using a next-event time advance technique to advance the simulation time. Also the state transition and activity diagrams are explained to represent the relationship between the objects. By numerical examples, the redundancy allocation is considered in order to decrease the risk level of the IPS.

• Journal of Information Processing Systems
• /
• 제20권1호
• /
• pp.131-147
• /
• 2024

A routing strategy based on traffic prediction and dynamic cache allocation for satellite nodes is proposed to address the issues of high propagation delay and overall delay of inter-satellite and satellite-to-ground links in low Earth orbit (LEO) satellite systems. The spatial and temporal correlations of satellite network traffic were analyzed, and the relevant traffic through the target satellite was extracted as raw input for traffic prediction. An improved gradient boosting regression tree algorithm was used for traffic prediction. Based on the traffic prediction results, a dynamic cache allocation routing strategy is proposed. The satellite nodes periodically monitor the traffic load on inter-satellite links (ISLs) and dynamically allocate cache resources for each ISL with neighboring nodes. Simulation results demonstrate that the proposed routing strategy effectively reduces packet loss rate and average end-to-end delay and improves the distribution of services across the entire network.

• 한국정보과학회논문지:데이타베이스
• /
• 제28권4호
• /
• pp.732-741
• /
• 2001

관계형 데이타베이스 시스템에서 결합 연산자는 데이타 베이스 절의를 구성하는 연산자들 중 가장 많은 처리시간을 요구한다. 따라서 이러한 결합 연산자를 효율적으로 처리하기 위해 많은 병렬 알고리즘들이 수개되었다. 그 중 다중 해쉬 결합 질의의 처리를 위해 할당트리를 이용한 방법이 가장 우수한 것으로 알려져 와싸. 그러나 이 방법은 할당 트리의 각 노트에서 필연적인 지연이 발생되는데 이는 루플 실험단계에서 외부 릴레이션을 디스트로부터 페이지 단위로 읽는 비용과 이미 읽는 페이지에 대한 해쉬 결합 비용간의 실행시간 차이에 의해 발생하게 된다. 이는 페이지 실행시간 동기화 기법을 이용하여 할당 트라 한 노드에서의 실행시간을 줄일 수 있었다. 본 논문에서는 한 노드에서의 성능 개선 효과를 할당 트리 전체로 확장하여 전체 다중 해쉬 결합의 성능 분석을 수행하였으며 한정된 프로세서 환경 하에서 입력 릴레이션 수와 할당된 프로세서 수와의 관게에 따른 효율적인 다중 해쉬 결합 알고리즘을 제안하였다. 그리고 분석적 비용 모형을 세워 기존 방식과의 다양한 성늘 분석을 통해 비용 모형의 타당성을 입증하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제6권2호
• /
• pp.629-648
• /
• 2012

Given a video stream delivering system deployed on a multicast tree, which is embedded in a multi-channel multi-radio wireless mesh network, our problem is concerned about how to allocate interference-free channels to tree links and maximize the number of serviced mesh clients at the same time. In this paper, we propose a channel allocation heuristic algorithm based on best-first search and backtracking techniques. The experimental results show that our BFB based CA algorithm outperforms previous methods such as DFS and BFS based CA methods. This superiority is due to the backtracking technique used in BFB approach. It allows previous channel-allocated links to have feasibility to select the other eligible channels when no conflict-free channel can be found for the current link during the CA process. In addition to that, we also propose a tree refinement method to enhance the quality of channel-allocated trees by adding uncovered destinations at the cost of deletion of some covered destinations. Our aim of this refinement is to increase the number of serviced mesh clients. According to our simulation results, it is proved to be an effective method for improving multicast trees produced by BFB, BFS and DFS CA algorithms.

• 대한전자공학회논문지
• /
• 제27권4호
• /
• pp.571-579
• /
• 1990

A dynamic relocation algorithm for non-deterministic process graph in distributed computer systems is proposed. A method is represented for determining the optimal policy for processing a process tree. A general database query request is modelled by a process tree which represent a set of subprocesses together with their precedence relationship. The process allocation model is based on operating cost which is a function fo selection of site for processing operation, data reduction function and file size. By using expected values of parameters for non-deterministic process tree, the process graph and optimal policy that yield minimum operating cost are determined. As process is relocated according to threshold value and new information of parameters after the execution of low level process for non-deterministic process graph, the assigned state that approximate to optiaml solution is obtained. The proposed algorihtm is heuristic By performing algorithm for sample problems, it is shown that the proposed algorithm is good in obtaining optimal solution.

• 한국통신학회논문지
• /
• 제36권5A호
• /
• pp.502-510
• /
• 2011

본 논문에서는 트리 기반의 센서네트워크에서 전력소모의 균형을 이루기 위한 시간 슬랏을 할당하는 알고리즘을 제안한다. 트리 토폴로지를 갖는 센서네트워크에서는 낮은 트리 깊이를 갖는 노드들이 더 많은 패킷을 처리하기 때문에 더 많은 전력을 소모한다. 따라서, 네트워크 생명이 단축되는 문제가 있다. 본 논문에서 제안하는 슬랏 스케줄링 알고리즘은 각 노드에게 수신 슬랏들을 먼저 할당하고 송신 슬랏들을 할당한다. 이러한 할당 방식은 패킷 결합과 필터링을 용이하게 하기 때문에 낮은 트리 깊이에 위치한 노드들의 부하를 감소시키는 효과가 있다. 시뮬레이션을 사용하여 제안한 알고리즘을 TreeMAC 에서 제안한 프레임-슬랏 할당 알고리즘과 비교함으로써 전력소모의 균형을 이룬다는 것을 확인하였다.