Gyung-Leen Park

DFRN: a new approach for duplication based scheduling for distributed memory multiprocessor systems

Duplication based scheduling (DBS) is a relatively new approach for solving multiprocessor scheduling problems. The problem is defined as finding an optimal schedule which minimizes the parallel execution time of an application on a target system. We classify DBS algorithms into two categories according to the task duplication method used. We then present our new DBS algorithm that extracts the strong features of the two categories of DBS algorithms. Our simulation study shows that the proposed algorithm achieves considerable performance improvement over existing DBS algorithms with equal or less time complexity. We analytically obtain the boundary condition for the worst case behavior of the proposed algorithm and also prove that the algorithm generates an optimal schedule for a tree structured input directed acyclic graph.

Analysis of the Passenger Pick-Up Pattern for Taxi Location Recommendation

This paper analyzes a pick-up pattern of taxi service in Jeju area based on the real-life location history data collected from the Taxi Telematics system, aiming at obtaining useful background data necessary to design a location recommendation service for empty taxis. Out of the great amount of location records, pick-up data are extracted by tracing the state change in the predefined taxi state diagram. To decide a reasonable granularity of location recommendation, refined clustering is performed by means of the well-known k-means method supported by the E-Miner statistics software package. In addition, within each cluster, the temporal analysis creates time-dependent pick-up pattern change along the time axis. As a result, the cluster and its spatio-temporal pick-up frequency make it possible to suggest that the empty taxi go to the nearby cluster location, resulting in the reduction of empty taxi ratio.

A Telematics Service System Based on the Linux Cluster

This paper designs and implements a taxi telematics service system, aiming at providing an efficient framework by means of a Linux cluster to host emerging telematics services that need intensive computing. Combined with global positioning system and radio communication technology, the taxi telematics service system traces the position of taxis, finds a time saving route between start and destination points, dispatches the nearest taxi to the service call point based on the latest traffic information, and finally decides an efficient route for multiple destinations. The performance measurement result demonstrates that the implemented system can process up to 200 map matches for every minute, keeping average response time for other requests below 1.5 seconds.

Viewer Identification and Authentication in IPTV using RFID Technique

This paper presents the application of RFID (radio frequency identification) to identify and authenticate the viewer for personalized and interactive services offered by the IPTV (internet protocol television). Main purpose of the setup is to identify and authenticate the viewer, the person who is watching the TV, for parental control, payment services, consumer feedback and input etc. Using RFID reader with IPTV STB (set-top box) for authentication of viewer and service verification results in identifying viewer, using RFID tag wirelessly and at low cost. With RFID service becoming ubiquitous and its application and connectivity with home automation systems, the proposed system is thought to be widely adaptable. This Interactive identification technique also provides reliable security to protect the viewer contents, media and parental control.

Energy consumption scheduler for demand response systems in the smart grid

This paper presents a design and evaluates the performance of a power consumption scheduler in smart grid homes or buildings, aiming at reducing the peak load in them as well as in the system-wide power transmission network. Following the task model consist of actuation time, operation length, deadline, and a consumption profile, the scheduler linearly copies the profile entry or maps a combinatory vector to the allocation table one by one according to the task type, which can be either preemptive or nonpreemptive. The proposed scheme expands the search space recursively to traverse all the feasible allocations for a task set. A pilot implementation of this scheduling method reduces the peak load by up to 23.1% for the given task set. The execution time, basically approximated by (The equation is abbreviated), where M, N(subscript NP), and N(subscript P) are the number of time slots, nonpreemptive tasks, and preemptive tasks, respectively, is reduced almost to 2% taking advantage of an efficient constraint processing mechanism which prunes a search branch when the partial peak value already exceeds the current best. In addition, local peak reduction brings global peak reduction by up to 16% for the home-scale scheduling units without any global coordination, avoiding uncontrollable peak resonance.

Power consumption scheduling for peak load reduction in smart grid homes

This paper presents a design and evaluates the performance of a power consumption scheduler in smart grid homes, aiming at reducing the peak load in individual homes as well as in the system-wide power transmission network. Following the task model consist of actuation time, operation length, deadline, and a consumption profile, the scheduler copies or maps the profile according to the task type, which can be either preemptive or nonpreemptive. The proposed scheme expands the search space recursively to traverse all the feasible allocations for a task set. A pilot implementation of this scheduling method reduces the peak load by up to 23.1% for the given task set. The execution time greatly depends on the search space of a preemptive task, as its time complexity is estimated to be <i>O</i> (<i>M</i>^<i>N</i>_<i>np</i> · (<i>M</i>^<i>M/2</i>)^<i>N</i>_<i>p</i>), where <i>M, N</i>_<i>np</i>, and <i>N</i>_<i>p</i> are the number of time slots, preemptive tasks, and nonpreemptive tasks, respectively. However, it can not only be reduced almost to 2% but also made stable with a basic constraint processing mechanism which prunes a search branch when the partial peak value already exceeds the current best.

An Efficient Scheduling Scheme on Charging Stations for Smart Transportation

This paper proposes a reservation-based scheduling scheme for the charging station to decide the service order of multiple requests, aiming at improving the satisfiability of electric vehicles. The proposed scheme makes it possible for a customer to reduce the charge cost and waiting time, while a station can extend the number of clients it can serve. A linear rank function is defined based on estimated arrival time, waiting time bound, and the amount of needed power, reducing the scheduling complexity. Receiving the requests from the clients, the power station decides the charge order by the rank function and then replies to the requesters with the waiting time and cost it can guarantee. Each requester can decide whether to charge at that station or try another station. This scheduler can evolve to integrate a new pricing policy and services, enriching the electric vehicle transport system.

Design and implementation of a tour planning system for telematics users

Aiming at providing an efficient tour schedule to tourists driving with a telematics device, this paper designs and implements an intelligent tour planning system based on the personalized tour recommender that may generate lots of destinations. To overcome the problem of long response time due to the computation of O(2n ċ n!) complexity solver, we used initial set reduction, distributed computing via MPI-based Linux cluster, and finally Lin-Kernighan heuristic. An user interface was also implemented on a portable device using the utility of embedded operating system. Performance measurement results exhibit that the tour schedule can not only be offered to the user within 5 seconds when the number of TPOIs is less than 22, but also find a schedule whose satisfaction degree is very close to the optimal value.

Intrusion detection based on clustering a data stream

In anomaly intrusion detection, how to model the normal behavior of activities performed by a user is an important issue. To extract the normal behavior as a profile, conventional data mining techniques are widely applied to a finite audit data set. However, these approaches can only model the static behavior of a user in the audit data set. This drawback can be overcome by viewing the continuous activities of a user as an audit data stream. This paper proposes a new clustering algorithm, which continuously models a data stream. A set of features is used to represent the characteristics of an activity. For each feature, the clusters of feature values corresponding to activities observed so far in an audit data stream are identified by the proposed clustering algorithm for data streams. As a result, without maintaining any historical activity of a user physically, new activities of the user can be continuously reflected to the on-going result of clustering.

Integration of battery charging to tour schedule generation for an EV-Based rent-a-car business

To promote an electric vehicle-based rent-a-car business, this paper designs a tour scheduler capable of minimizing the waiting time induced by frequent and long battery charging during the tour. As charging can be conducted during the stay time in each tourist spot, the waiting time is greatly dependent on the visiting order. After formulating the per-spot waiting time according to the initial battery amount and the earned distance credit, our scheme traverses the search space to find the visiting sequence having the minimum waiting time. The performance measurement results obtained from a prototype implementation reveal that the proposed scheme can add just 40 minutes when the total trip length is about 195 km, which may need about a few hour charging in slow chargers, for the given parameter set including average stay time and inter-spot distance. Moreover, our scheme outperforms the well-known traveling salesman problem solver by up to 14.7 % in terms of tour time.