• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.319-319
• /
• 2020

최근 데이터 과학의 획기적인 발전 덕분에 딥러닝 (Deep Learning) 알고리즘이 개발되어 다양한 분야에 널리 적용되고 있다. 본 연구에서는 인공신경망 중 하나인 LSTM(Long-Short Term Memory) 네트워크를 사용하여 댐 유입량을 예측하였다. 구체적인 내용으로, (1) LSTM에 필요한 입력 데이터를 효율적으로 사전 처리하는 방법, (2) LSTM의 하이퍼 매개변수를 결정하는 방법 및 (3) 다양한 손실 함수(Loss function)를 선택하고 그 영향을 평가하는 방법 등을 다루었다. 제안된 LSTM 모델은 강우량(R), 댐유입량(Q) 기온(T), 기저유량(BF) 등을 포함한 다양한 입력 변수들의 함수로 가정하였으며, CCF(Cross Correlations), ACF(Autocorrelations) 및 PACF(Partial Autocorrelations) 등의 기법을 사용하여 입력 변수를 결정하였다. 다양한 sequence length를 갖는 (즉 t, t-1, … t-n의 시간 지연을 갖는) 입력 변수를 적용하여 데이터 학습에 최적의 시퀀스 길이를 결정하였다. LSTM 네트워크 모델을 적용하여 2014년부터 2020년까지 한강 유역 9개의 댐 유입량을 추정하였다. 본 연구로부터 댐 유입량을 예측하는 것은 홍수 및 가뭄 통제를 위한 필수 요건들 중 하나이며 수자원 계획 및 관리에 도움이 될 것이다.

• Journal of KIISE:Software and Applications
• /
• v.29 no.12
• /
• pp.957-965
• /
• 2002

Garbage collection in the CLDC typically employs a stop-the-world GC algorithm which is performing a complete garbage collection when needed. This technique is unsuitable for the interactive Java embedded system because this can lead to long and unpredictable delays. In this paper, We present a garbage collection algorithm which reduces the average delay time and supports the interactive environment. Our garbage collector is composed of the allocator and the collector. The allocator determines the allocation position of free-list according to object size, and the collector uses an incremental mark-sweep algorithm. The garbage collector is called periodically by the thread scheduling policy and the allocator allocates the objects of marked state during collection cycle. Also, we introduce a color toggle mechanism that changes the meaning of the bit patterns at the end of the collection cycle. We compared the performance of our implementation with stop-the-world mark-sweep GC. The experimental results show that our algorithm reduces the average delay time and that it provides uniformly low response times.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.4
• /
• pp.1211-1216
• /
• 2000

Asynchronous transfer mode (ATM) can be efficiently used to transport packet data services. The switching system will support voice and packet data services simultaneously from end to end applications. To guarantee quality of service (QoS) of the offered services, source rateot send packet data is needed to control the network overload condition. Most existing control algorithms are shown to provide the threshold-based feedback control technique. However, real-time voice calls can be dynamically connected and released during data services in the network. If the feedback control information delays, quality of the serviced voice can be degraded due to a time delay between source and destination in the high speed link. An adaptive algorithm based on the optimal least mean square error technique is presented for the predictive feedback control technique. The algorithm attempts to predict a future buffer size from weight (slope) adaptation of unknown functions, which are used fro feedback control. Simulation results are presented, which show the effectiveness of the algorithm.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10c
• /
• pp.631-633
• /
• 2003

인터넷 가반 분산/병렬 처리 프레임 워크 PDP(Parallel/Distributed Processing Scheme on Web)는 네트워크 내 유휴 상태 호스트들을 활용하여 대용량 작업을 병렬로 처리한다. 본 논문에서는 이러한 서브 작업을 할당받는 자원이 동작하는 네트워크 환경을 모니터링 함으로써 수시로 변화하는 네트워크 환경에 대처하는 방안을 제시한다. 특히 네트워크 환경 모니터링 예측 결과를 PDP의 작업 할당 알고리즘에 적용하여 네트워크 과부하 및 결함 등으로 인해 발생되는 작업 지연 요소에 적응적 대처함으로써 전체 작업 수행 처리율 향상을 도모하는 방법을 제안한다.

• Journal of KIISE:Computer Systems and Theory
• /
• v.28 no.3
• /
• pp.144-154
• /
• 2001

다중 결합 질의에 포함된 다수의 결합 연산지를 효율적으로 처리하기 위해 서는 효율적인 병렬 알고리즘이 필요하다. 최근 다중 해쉬 결합 질의의 처리를 위해 할당 트리를 이용한 방법이 가장 우수한 것으로 알려져 있다. 그러나 이 방법은 실제 결합 시에 할당 트리의 각 노드에서 필연적인 지연이 발생되는 데 이는 튜플-시험 단계에서 외부 릴레이션을 디스크로부터 페이지 단위로 읽는 비용과 이미 읽는 페이지에 대한 해쉬 결합 비용간의 차이에 의해 발생하게 된다. 이들 사이의 실행시간을 가급적 일치시키기 위한 '페이지 실행시간 동기화'기법이 제안되었고 이를 통해 할당 트리 한 노드 실행에 있어서의 지연 시간을 줄일 수 있었다. 하지만 지연 시간을 최소화하기 위해 할당되어질 프로세서의 수 즉, 페이지 실행시간 동기화 계수(k)는 실제 결합 시의 결합률에 따라 상당한 차이를 보이게 되고 결국, 이 차이를 고려하지 않은 다중 해쉬 결합은 성능 면에서 크게 저하될 수밖에 없다. 본 논문에서는 결합 이전에 어느 정도의 결합률을 예측할 수 있다는 전제하에 다중 해쉬 결합 실행 시에 발생할 수 있는 지연 시간을 최소화 할 수 있도록 결합률에 따라 최적의 프로세서들을 노드에 할당함으로서 다중 해쉬 결합의 실행 성능을 개선하였다. 그리고 분석적 비용 모형을 세워 기존 방식과의 다양한 성능 분석을 통해 비용 모형의 타당성을 입증하였다.

• The KIPS Transactions:PartC
• /
• v.11C no.2
• /
• pp.193-202
• /
• 2004

Handoff if the most Important feature for the user's mobility in a cellular communication system, which is related to resource reservation at nearby cells. For efficient resource reservation, mobility prediction has been reported as an effective means to decrease call dropping probability and to shorten handoff latency in wireless cellular environments. Several early proposed handoff schemes making use of tile user's movement history on a cell-by-cell basis work on the assumption that the user's movements are restricted to the indoor locations such as an office or a building. However, those algorithms cannot be applied to a micro-cell structure or a metropolis with complicated structure of roads. In this paper, to overcome those drawbacks we propose a new mobility prediction algorithm, which stores and uses the history of the user's positions within the current cell to predict the next cell.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.4 no.2
• /
• pp.307-312
• /
• 2000

Asynchronous transfer mode(ATM) is flexible to support the various multimedia communication services such as data, voice, and image by applying asynchronous time-sharing and statistical multiplexing techniques to the existing data communication. ATM service is categorized to CBR, VBR, UBR, and ABR according to characteristics of the traffic and a required service qualities. Among them, ABR service guarantees a minimal bandwidth and can transmit cells at a maximum transmission rate within the available bandwidth. To minimize the cell losses in transmission and switching, a feedback information in ATM network is used to control the traffic. In this paper, predictive control algorithms are proposed for the feedback information. When the feedback information takes a long propagation delay to the backward nodes, ATM switch can experience a congestion situation from the queue length increases, and a high queue length fluctuations in time. The control algorithms proposed in this paper provides predictive control model using slop changes of the queue length function and previous data of the queue lengths. Simulation shows the effectiveness result of the proposed control algorithms.

• Journal of Satellite, Information and Communications
• /
• v.7 no.1
• /
• pp.65-74
• /
• 2012

The QoS guarantee for the forward link in satellite communication networks is very important because there are a variety of packets with multiplexing. Especially, the packets are processed depending on the available bandwidth in satellite network changing the wireless channel state in accordance with weather condition. The DVB-S2 increases the transmission efficiency by applying the adaptive coding and modulation (ACM) techniques as a countermeasure of rain attenuations. However, the channel estimation algorithm is required to support the ACM techniques that select the MODCOD values depending on the feedback data transmitted by RCSTs(Return Channel via Satellite Terminal) because satellite communication networks have a long propagation delay. In this paper, we proposed the channel estimation algorithm using rain attenuation values and reference data and the packet scheduling scheme to support the QoS and fairness. As a result of performance evaluation, we showed that proposed algorithm exactly predicts the channel conditions and supports bandwidth fairness to the individual RCST and guarantees QoS for user traffics.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.12 no.2
• /
• pp.35-44
• /
• 2002

In this paper, an implementation method of RSA exponentiator based on Radix-$2^k$ modular multiplication algorithm is presented and verified. We use Booth receding algorithm to implement Radix-$2^k$ modular multiplication and implement radix-16 modular multiplier using 2K-byte memory and CSA(carry-save adder) array - with two full adder and three half adder delays. For high speed final addition we use a reduced carry generation and propagation scheme called pseudo carry look-ahead adder. Furthermore, the optimum value of the radix is presented through the trade-off between the operating frequency and the throughput for given Silicon technology. We have verified 1,024-bit RSA processor using Altera FPGA EP2K1500E device and Samsung 0.3$\mu\textrm{m}$ technology. In case of the radix-16 modular multiplication algorithm, (n+4+1)/4 clock cycles are needed and the 1,024-bit modular exponentiation is performed in 5.38ms at 50MHz.

• Journal of the Korea Society for Simulation
• /
• v.15 no.3
• /
• pp.31-37
• /
• 2006

To achieve the efficient performance within a mobile grid considering the intermittent network connectivity and non-dedicated heterogeneous mobile devices, this paper suggests the scheduling algorithm of job allocation as a viable solution. The suggested scheduling algorithm has two core functions, the prediction of response time for task processing and the identification of the optimal number of mobile devices to process the mobile grid applications. This scheduling algorithm suggests the numerical formulas to calculate the network latency considering the effects of heterogeneous non-dedicated mobile system in wireless network environments. Also we evaluate the performance of mobile grid system using the processing the distributed applications in implemented mobile grid environments.