Chunkyun Youn

An efficient load balancing algorithm for cluster system

Load balancing is one of the best efficient methods for performance improvement of cluster system. Recently, WLC algorithm is used for the load balancing of cluster system. But, the algorithm also has load imbalance between servers, because it uses inaccurate static load status of servers. In this paper, I suggest a more efficient dynamic load balancing algorithm base on various load status information of servers by real time. It shows that load imbalance phenomenon is improved greatly and response time is also improved compare with WLC algorithm.

A Case Study for the Application of Storage Tiering Based on ILM through Data Value Analysis

In the recent, due to explosion of Digital Universe, the performance of computer and storage system is reducing. Therefore, the upgrade and capacity expansion needs is growing. Countermeasure for this problem is required fundamental and long-term solutions rather than piecemeal expansion. In this paper, we establish a data management policy for an enterprise through the operational status of storage system and the analysis of data value of it, and implement ILM-based tiered storage system on the basis of these. The results of this study shows the overall throughput was improved about 21 % compared to the existing system, it is very effective to maintain continuous quality and reduce operating costs in the long term aspect.

A study for decrease of SNMP messages through an efficient processing of trend analysis information

Network traffic demand is increasing explosively because of various smart equipment and services on smart era. It causes traffic overload for wireless and wired network. Network management system is very important to control the explosion of data traffic. It uses SNMP to communicate with various network resources for management functions, and creates lots of network management traffic. Those are can be serious traffic congestion on a network. I propose an improving function of SNMP to minimize unnecessary network management traffic between manager and agent for collecting the Trend Analysis Information which is mainly used to monitor and accumulate for a specific time period. The results of test show it has compatibility with the existing SNMP and greatly decreases the amount of network traffic and response time.

Performance improvement of cluster system by server status information

There is a physical and logical method for performance improvement of cluster systems. Efficient load balancing of cluster systems is the best logical method. Recently, the WLC (Weighted Least Connection) algorithm was used for load balancing of cluster systems. But, the algorithm also has load imbalance between servers because it uses an inaccurate load status of servers. In this paper, the author suggested a more efficient load balancing algorithm based on various load states of servers in real time. The author implemented a prototype and tested its performance. The test result shows that the load imbalance phenomenon is improved greatly and response time is also improved compared with the WLC algorithm.

The design of a dynamic efficient load balancing algorithm on distributed networks

In order to maintain load balancing in a distributed network, each node should obtain workload information from all the nodes in the network. To accomplish this, this processing requires O(v2) communication complexity, where v is the number of nodes. First, we present a new synchronous dynamic distributed load balancing algorithm on a (v,k+1,1)-configured network applying a symmetric balanced incomplete block design, where v=k2+k+1. Our algorithm designs a special adjacency matrix and then transforms it to (v,k+1,1)-configured network for an efficient communication. It requires only

A parallel routing algorithm on 2-circulant networks employing the hamiltonian circuit latin square

O(v \sqrt v)

Extension of SNMP function for improvement of network performance

communication complexity and each node receives workload information from all the nodes without redundancy since each link has the same amount of traffic for transferring workload information. Later, this algorithm is reconstructed on distributed networks, where v is an arbitrary number of nodes and is analyzed in terms of efficiency of load balancing.

Application of the hamiltonian circuit latin square to the parallel routing algorithm on 2-circulant networks

Double-loop and 2-circulant networks are widely used in the design and implementation of local area networks and parallel processing architectures. In this paper, we investigate the routing of a message on circulant networks, that is a key to the performance of this network. We would like to transmit 2k packets from a source node to a destination node simultaneously along paths on G(n; ±s1,±s2,...,±sk), where the ith packet will traverse along the ith path (1≤ i ≤2k). In oder for all packets to arrive at the destination node quickly and securely, the ith path must be node-disjoint from all other paths. For construction of these paths, employing the Hamiltonian Circuit Latin Square(HCLS) we present O(n2) parallel routing algorithm on circulant networks.

A Design of Protocol for Credit Card Transaction on PDA Using ECC

A manager requests a MIB value for a desired object to an agent by management policy defined in SNMP, and then it responds to the manager. So, it causes a lot of network traffic between them. Specially, repetitious occurrence of sending-receiving information is very inefficient for a same object when a trend analysis of traffic is performed. In this paper, an efficient SNMP is proposed to add new PDUs into the existing SNMP in order to accept time function. Utilizing this PDU, it minimizes unnecessary sending-receiving message and collects information for trend management of network efficiently. This proposed SNMP is tested for compatibility with the existing SNMP and decreases amount of network traffic largely.

The Design of an Efficient SNMP with Low Load of Network Traffic

Double-loop and 2-circulant networks are widely used in the design and implementation of local area networks and parallel processing architectures. In this paper, we investigate the routing of a message on circulant networks, that is a key to the performance of this network. We would like to transmit 2k packets from a source node to a destination node simultaneously along paths on G(n; ±s1,±s2, ...,±sk), where the ith packet will traverse along the ith path (1≤ i ≤2k). In oder for all packets to arrive at the destination node quickly and securely, the ith path must be node-disjoint from all other paths. For construction of these paths, employing the Hamiltonian Circuit Latin Square(HCLS), a special class of (n × n) matrices, we present O(n2) parallel routing algorithm on circulant networks.