• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.5
• /
• pp.465-470
• /
• 2012

This paper proposes a distributed autonomous control method of swarm robot behavior strategy based on artificial immune system and an optimization strategy for artificial immune system. The behavior strategies of swarm robot in the system are depend on the task distribution in environment and we have to consider the dynamics of the system environment. In this paper, the behavior strategies divided into dispersion and aggregation. For applying to artificial immune system, an individual of swarm is regarded as a B-cell, each task distribution in environment as an antigen, a behavior strategy as an antibody and control parameter as a T-cell respectively. The executing process of proposed method is as follows: When the environmental condition changes, the agent selects an appropriate behavior strategy. And its behavior strategy is stimulated and suppressed by other agent using communication. Finally much stimulated strategy is adopted as a swarm behavior strategy. In order to decide more accurately select the behavior strategy, the optimized parameter learning procedure that is represented by stimulus function of antigen to antibody in artificial immune system is required. In this paper, particle swarm optimization algorithm is applied to this learning procedure. The proposed method shows more adaptive and robustness results than the existing system at the viewpoint that the swarm robots learning and adaptation degree associated with the changing of tasks.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.1
• /
• pp.135-145
• /
• 2010

Efficient Directed Acyclic Graph(DAG) scheduling is critical for achieving high performance in Distributed Heterogeneous computing System(DHCS). In this paper, we present a new high-performance scheduling algorithm, called the LCFT(Levelized Critical First Task) algorithm, for DHCS. The LCFT algorithm is a list-based scheduling that uses a new attribute to efficiently select tasks for scheduling in DHCS. The complexity of LCFT is $O(\upsilon+e)(p+log\;\upsilon)$. The performance of the algorithm has been observed by its application to some practical DAGs, and by comparing it with other existing scheduling algorithms such as PETS, HPS, HCPT and GCA in terms of the schedule length and SpeedUp. The comparison studies show that LCFT significantly outperforms PETS, HPS, HCPT and GCA in schedule length, SpeedUp.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.10a
• /
• pp.723-724
• /
• 2017

Recently, researches are being conducted to build a smart environment using various sensors and devices and to provide customized services to users through inter object communication. However, the existing system utilizes a centralized method of transmitting measured sensor data in real time to the server and processing it in batches and As the system is expanded, there is a problem that a high-end server must be configured. In this paper, we design a Resource Allocation Algorithm for IoT distributed processing environment to solve these problems. The resources required for the device to operate are transferred to the server and the server allocates resources in comparison to the task in progress. Therefore, it is expected that the data throughput of the server will be reduced and various devices can be configured in a server having a low specification.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.747-752
• /
• 2004

Researches about scheduling of the distributed real-time systems have been proposed. However, they have some weak points, not scheduling both sporadic and periodic tasks and messages or being unable to guaranteeing the end-to-end constraints due to omitting precedence relations between sporadic tasks. So this paper proposes a new scheduling method for distributed real-time systems consisting of sporadic and periodic tasks with precedence relations and sporadic and periodic messages, guaranteeing end-to-end constraints. The proposed method is based on a binary search-based period assignment algorithm, an end-to-end laxity-based priority assignment algorithm, and three kinds of schedulability analysis, node, network, and end-to-end schedulability analysis. In addition, this paper describes the application model of sporadic tasks with precedence constraints in a distributed real-time system, shows that existing scheduling methods such as Rate Monotonic (RM) scheduling are not proper to be applied to the system having sporadic tasks with precedence constraints, and proposes an end-to-end laxity-based priority assignment algorithm.

• Proceedings of the Korea Contents Association Conference
• /
• 2007.11a
• /
• pp.611-614
• /
• 2007

The IEEE 802.11 Task Group E has worked to enhance the legacy 802.11 MAC to expand support for applications with QoS requirements. EDCF(Enhanced Distributed Coordination Function) of IEEE 802.11e is enhanced from DCF(Distributed Coordination Function) of 802.11 and It has differential AC(Access Category). In this paper, we change parameters(AIFS, CWmax) and make an analysis of network performance. We use NS-2 to verify change of network performance.

• The Journal of Society for e-Business Studies
• /
• v.2 no.1
• /
• pp.21-37
• /
• 1997

As the complexity in design and manufacturing activities of distributed virtual enterprises rapidly increases, the issue of process management becomes more critical to shorten the time-to-market, reduce the manufacturing cost and improve the product quality. This paper proposes a unified framework to manage design and manufacturing processes in a distributed environment. We present a methodology which utilizes process flow graphs to depict the hierarchical structure of workflows and process grammars to represent various design processes and design tools. To implement the proposed concept, we develop a process management system which mainly consists of a cockpit and manager programs, and we finally address a preliminary implementation procedure based on the Object Modeling Technique. Since the proposed framework can be a formal approach to the process management by providing formalism, parallelism, reusability, and flexibility, it can be effectively applied to further application domains of distributed virtual enterprises.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.7
• /
• pp.501-508
• /
• 2004

In this paper, a coordinated scheduling algorithm is proposed to reduce end-to-end delay in distributed control of systems. For the algorithm, the analysis of practical end-to-end delay in the worst case is performed priory with considering implementation of the systems. The end-to-end delay is composed of the delay caused by multi-task scheduling of operating systems, the delay caused by network communications, and the delay caused by asynchronous timing between operating systems and network communications. Through some simulation tests based on CAN(Controller Area Network), the proposed worst case end-to-end delay analysis is validated. Through the simulation tests, it is also shown that a real-time distributed control system designed to existing worst case delay cannot guarantee end-to-end time constraints. With the analysis, a coordinated scheduling algorithm is proposed here. The coordinated scheduling algorithm is focused on the reduction of the delay caused by asynchronous timing between operating systems and network communications. Online deadline assignment strategy is proposed for the scheduling. The performance enhancement of the distributed control systems by the scheduling algorithm is shown through simulation tests.

• Journal of Institute of Control, Robotics and Systems
• /
• v.11 no.2
• /
• pp.175-185
• /
• 2005

The scheduling methods of the distributed real-time systems have been proposed. However, they have some weak points. They did not schedule both sporadic and periodic tasks and messages at the same time or did not consider the end-to-end constraints such as precedence relations between sporadic tasks. This means that system scheduling must guarantee the constraints of practical systems and be applicable to them. This paper proposes a new scheduling method that can be applied to more practical model of distributed real-time systems. System model consists of sporadic and periodic tasks with precedence relations and sporadic and periodic messages and has end-to-end constraints. The proposed method is based on a binary search-based period assignment algorithm, an end-to-end laxity-based priority assignment algorithm, and three kinds of schedulability analysis, node, network, and end-to-end schedulability analysis. In addition, this paper describes the application model of sporadic tasks with precedence constraints in a distributed real-time system, shows that existing scheduling methods such as Rate Monotonic scheduling are not proper to be applied to the system having sporadic tasks with precedence constraints, and proposes an end-to-end laxity-based priority assignment algorithm.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.131-134
• /
• 2013

최근 클라우드 컴퓨팅의 발전과 상업적인 성공과 함께 클라우드 자원의 이용률을 최대로 유지하면서 에너지를 효율적으로 사용하기 위한 연구에 대한 관심이 커지고 있다. 자원의 사용률이 최대로 높아지게 되면 에너지 소비량이 급격하게 증가하여 많은 에너지를 사용하게 되므로 자원의 사용율과 에너지 사용은 트레이드오프 관계를 가지게 된다. 따라서 본 논문에서는 자원의 최대 사용 및 효율적인 에너지 사용을 위해 에너지 소비가 최적이 되는 자원 이용률의 임계값을 찾기 위한 연구를 수행하였다. 실험을 위해 자원 중 가장 많은 에너지를 소비하는 CPU를 이용하였고, 전력 측정을 위해 KEM2500 전력계와 ThrottleStop_500 프로그램을 사용하였다. 실험 결과 CPU 사용률이 약 90%일 때 에너지 사용량이 급격하게 증가하였으며, 기존의 평균 자원 이용률과 비교했을 때 12.3% 정도의 전기량이 더 소모됨을 확인하였다. 따라서 클라우드 컴퓨팅에서 CPU 자원의 이용률이 90%일 때 에너지가 최적이라고 할 수 있다.

• Journal of Platform Technology
• /
• v.11 no.4
• /
• pp.71-79
• /
• 2023

In this paper, we analyze the characteristics of machine learning workloads and, based on them, propose a distributed in-memory caching technique to improve the performance of machine learning workloads. The core of machine learning workload is model training, and model training is a computationally intensive task. Performing machine learning workloads in a Kubernetes-based cloud environment in which the computing framework and storage are separated can effectively allocate resources, but delays can occur because IO must be performed through network communication. In this paper, we propose a distributed in-memory caching technique to improve the performance of machine learning workloads performed in such an environment. In particular, we propose a new method of precaching data required for machine learning workloads into the distributed in-memory cache by considering Kubflow pipelines, a Kubernetes-based machine learning pipeline management tool.