Jai-Hoon Kim

Disconnected Operation Service in Mobile Grid Computing

In this paper, we discuss on the extension of grid computing systems in mobile computing environments, where mobile devices can be effectively incorporated into the grid either as service recipients or as more valuable service providers. First, based on the present grid architecture, we try to figure out what would be the newly required services in such a mobile/grid integrated architecture. There are a number of challenging issues when taking mobile environment into account, such as intermittent connectivity, device heterogeneity, and weak security. Among these issues to solve, we particularly focus on a disconnected operation problem in this paper since mobile resources are prone to frequent disconnections due to their confined communication range and device mobility. We develop a new job scheduling algorithm for mobile grid system and evaluate it by various methods such as mathematical analysis, simulation, and prototype implementation.

Dynamic Data Grid Replication Strategy Based on Internet Hierarchy

In data grid, large quantity of data files is produced and data replication is applied to reduce data access time. Efficiently utilizing grid resources becomes important research issue since available resources in grid are limited while large number of workloads and large size of data files are produced. Dynamic replication in data grid aims to reduce data access time and to utilize network and storage resources efficiently. This paper proposes a novel dynamic replication strategy, called BHR, which reduces data access time by avoiding network congestions in a data grid network. With BHR strategy, we can take benefits from ‘network-level locality’ which represents that required file is located in the site which has broad bandwidth to the site of job execution. We evaluate BHR strategy by implementing it in an OptorSim, a data grid simulator initially developed by European Data Grid Projects. The simulation results show that BHR strategy can outperform other optimization techniques in terms of data access time when hierarchy of bandwidth appears in Internet. BHR extends current site-level replica optimization study to the network-level.

A novel gradient approach for efficient data dissemination in wireless sensor networks

In a wireless sensor network, a majority of packet transmissions are delivered in the direction of a sink from scattered sensors. Thus, each sensor node can be implicitly provided with the direction in which to forward sensing data towards the sink. Most existing gradient approaches are based on this observation. However, these approaches do not consider the mobility problem. We propose a new gradient flooding protocol in which only hop count information is utilized as a cost metric for gradient forwarding and each sensor is able to self-adjust this metric with the minimum overhead whenever its movement occurs.

Real-time performance analysis for publish/subscribe systems

The publish/subscribe communication system has been a popular communication model in many areas. Especially, it is well suited for a distributed real-time system in many ways. However, the research of cost model and analysis of publish/subscribe system in a distributed real-time system have not been suggested yet. In this paper, we present our cost model for publish/subscribe system in a real-time domain, analyze its performance, and compare it with other communication models such as request/reply and polling models. Our empirical result on mobile embedded device shows accordance with cost analysis, which verifies correctness and usefulness of our cost model.

A New Directional Flooding Protocol for Wireless Sensor Networks

Flooding is commonly used both for conventional ad hoc networks and wireless sensor networks. Most of previous works on developing efficient flooding protocols are focused on making an optimal broadcast tree, with an implicit assumption that all nodes should be reachable from the source. However, this aim as well as the implied assumption may no longer be true because flooding protocols in wireless sensor networks are used to deliver the data packets towards a single or only subset of destination node(s). In this paper, we propose a new flooding protocol for utilizing directional information to achieve the efficiency in data delivery. The proposed directional flooding can lead flooded packets to flow in the ”right direction” towards their destinations, hence eliminating unnecessary packet forwarding and reducing the total energy consumption. Our simulation results show the average number of transmitted packets can be significantly reduced over the existing flooding algorithms, in which possibly all nodes are participated in a flooding process.

Enhanced Power Saving Scheme for IEEE 802.11 DCF Based Wireless Networks

Providing energy efficiency in MAC (Medium Access Control) layer, while achieving desirable throughput, is an important research issue in the area of wireless networking. A wireless LAN such as IEEE 802.11 using the Distributed Coordination Function (DCF) also provides a mechanism for power conservation which allows each node to “sleep” for some amount of periods, but also requires the nodes to wake up periodically and stay “awake” for a certain duration called the ATIMWindow. In this paper, we propose a new energy-efficient MAC protocol that allows the nodes to go to sleep early, without the need to be “on” for the whole ATIM interval, in the case they are acknowledged that no data is buffered within an ad hoc network and therefore no data transmission will be taken place.

Enhanced power saving for IEEE 802.11 WLAN with dynamic slot allocation

In the area of wireless mobile communication, minimizing energy consumption as well as maximizing data throughput in medium access control (MAC) layer is a very important research issue. The Distributed Coordination Function (DCF) of IEEE 802.11 provides the power saving mechanism (PSM) that allows nodes to remain silent in ‘doze mode’ for reducing energy consumption. However, IEEE 802.11 PSM is known to cause unnecessary energy consumption due to the problems of an overhearing, a back-off time delay and possible packet collisions. To overcome these problems, we present a new MAC protocol called ‘Slotted-PSM’ for IEEE 802.11 WLANs. In our proposed scheme, the Beyond-ATIM window is divided into a number of time slots, and any node that participates in communication wakes up in its slot times only and other nodes can enter to doze mode during the slot times. Slotted-PSM can reduce unnecessary energy consumption and idle listening problem in the Beyond-ATIM window.

UMONS: Ubiquitous monitoring system in smart space

Ubiquitous smart space consists of various ubiquitous objects (devices and applications) and their collaborations that provide convenient and intelligent services for users. Many studies have focused on developing convenient ubiquitous systems and their applications. However, to provide smooth and satisfactory services to users, a ubiquitous system must be aware of the real-time context of its ubiquitous objects and their collaborations during execution. Therefore, monitoring and analyzing must be provided, not only for the status of the functions and performance of individual ubiquitous objects, but also for their collaborative status. This paper discusses the challenges of monitoring systems for ubiquitous smart space, and proposes seven prerequisites for a monitoring system that examines and diagnoses ubiquitous smart space. We also developed a monitoring system for a ubiquitous smart space scenario, to verify our proposal.

Effective real-time scheduling algorithm for cyber physical systems society

CPS (Cyber Physical Systems) tightly couple their cyber factor and physical factor in distributed computing or Grids environments to provide real-time services such as avionics, transportation, manufacturing processes, energy, healthcare, etc. We need to consider not only the cyber space (CPU, network, storage systems, etc.) and the physical space (location, migration, etc.) but also the socio space and mental space for the precise analysis and useful services. In this paper, real-time scheduling algorithms, namely ELST (Effective Least Slack Time First) and H-ELST (Heuristic-Effective Least Slack Time First), are presented for CPS, where servicing node needs to move to serviced node for real-time services. We measure the real-time performance in terms of deadline meet ratio by mathematical analysis and simulations. The results show that our algorithms reduce a deadline miss ratio approximately up to 50% and 20% compared to the conventional real-time scheduling algorithm, FIFO (First In First Out) and LST (Least Slack Time First), respectively. Computers and physical systems are tightly coupled in cyber physical society.Conventional systems only consider cyber space.CPS should also consider physical, socio and mental space.Proposed scheduling algorithm considering physical factors.Efficiency of algorithm is verified by mathematical analysis and simulation.

Exploring protein fold space by secondary structure prediction using data distribution method on Grid platform

MOTIVATION Since the newly developed Grid platform has been considered as a powerful tool to share resources in the Internet environment, it is of interest to demonstrate an efficient methodology to process massive biological data on the Grid environments at a low cost. This paper presents an efficient and economical method based on a Grid platform to predict secondary structures of all proteins in a given organism, which normally requires a long computation time through sequential execution, by means of processing a large amount of protein sequence data simultaneously. From the prediction results, a genome scale protein fold space can be pursued. RESULTS Using the improved Grid platform, the secondary structure prediction on genomic scale and protein topology derived from the new scoring scheme for four different model proteomes was presented. This protein fold space was compared with structures from the Protein Data Bank, database and it showed similarly aligned distribution. Therefore, the fold space approach based on this new scoring scheme could be a guideline for predicting a folding family in a given organism.