• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권11호
• /
• pp.5243-5263
• /
• 2017

Data center networks provide critical bandwidth for the continuous growth of cloud computing, multimedia storage, data analysis and other businesses. The problem of low link bandwidth utilization in data center network is gradually addressed in more hot fields. However, the current scheduling strategies applied in data center network do not adapt to the real-time dynamic change of the traffic in the network. Thus, they fail to distribute resources due to the lack of intelligent management. In this paper, we present an improved adaptive traffic scheduling strategy utilizing the simulated annealing genetic algorithm (SAGA). Inspired by the idea of software defined network, when a flow arrives, our strategy changes the bandwidth demand dynamically to filter out the flow. Then, SAGA distributes the path for the flow by considering the scheduling of the different pods as well as the same pod. It is implemented through software defined network technology. Simulation results show that the bisection bandwidth of our strategy is higher than state-of-the-art mechanisms.

• 한국콘텐츠학회논문지
• /
• 제21권7호
• /
• pp.164-170
• /
• 2021

VLSI 설계에서의 분할(partitioning)은 기능의 최적화를 위하여 설계하고자 하는 회로의 그룹화(grouping)하는 단계로서 레이아웃(layout)에서 면적과 전파지연의 최소화를 위해 함께 배치할 소자를 결정하는 문제이다. 이러한 분할 문제에서 해를 얻기 위해 사용되는 알고리즘은 Kernighan-Lin 알고리즘, Fiduccia Mattheyses heuristic, 시뮬레이티드 어닐링, 유전자 알고리즘 등의 방식이 이용된다. 본 논문에서는 회로 분할 문제에 대하여 유전자 알고리즘과 확률 진화 알고리즘을 결합한 어댑티드 유전자 알고리즘을 이용한 해 공간 탐색(solution space search) 방식을 제안하였으며, 제안한 방식을 유전자 알고리즘 및 시뮬레이티드 어닐링 방식과 비교, 분석하였고, 어댑티드 유전자 알고리즘이 시뮬레이티드 어닐링 및 유전자 알고리즘보다 더 효과적으로 최적해에 근접하는 것을 알 수 있었다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.162-164
• /
• 2004

This paper proposes a new classification system combining the adaptive feature weighting algorithm using the genetic algorithm and the modified KNN rule. GA is employed to choose the middle value of weights and weights of features for high performance of the system. The modified KNN rule is proposed to estimate the class of test pattern using adaptive feature space. Experiments with the unconstrained handwritten digit database of Concordia University in Canada are conducted to show the performance of the proposed method.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제2권1호
• /
• pp.59-64
• /
• 2002

In the sender-initiated load balancing algorithms, the sender continues to send an unnecessary request message fur load transfer until a receiver is found while the system load is heavy. Meanwhile, in the receiver-initiated load balancing algorithms, the receiver continues to send an unnecessary request message for load acquisition until a sender is found while the system load is light. These unnecessary request messages result in inefficient communications, low CPU utilization, and low system throughput in distributed systems. To solve these problems, in this paper, we propose a genetic algorithm based approach fur improved sender-initiated and receiver-initiated load balancing. The proposed algorithm is used for new adaptive load balancing approach. Compared with the conventional sender-initiated and receiver-initiated load balancing algorithms, the proposed algorithm decreases the response time and increases the acceptance rate.

• 한국항공우주학회지
• /
• 제37권3호
• /
• pp.248-254
• /
• 2009

유전자 알고리즘은 공기역학적 최적 형상 설계를 위해 매우 유용한 도구임에도 불구하고 인구수 기반의 탐색 알고리즘이 내포하고 있는 과도한 계산 시간으로 말미암아 제한적으로 적용된다. 본 연구에서는 과도한 계산 시간을 줄이고 정확한 최적해를 유도하기 위해 근사모델인 역전파 신경망과 전역적 최적화 기법인 실수기반 적응영역 유전자 알고리즘을 결합한 하이브리드 기법을 제안한다. 그 결과 하이브리드 기법이 에어포일의 항력 및 최적화 계산 시간 측면에서 일반적인 유전자 알고리즘 대비 14%, 33% 향상된 결과를 나타내었다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2000년도 추계학술대회 학술발표 논문집
• /
• pp.157-160
• /
• 2000

This paper deals with the fuzzy modeling for the complex and uncertain system in which conventional and mathematical models may fail to give satisfactory results. mGA(messy Genetic Algorithm) has more effective and adaptive structure than sGA with respect to using changeable-length string and VEGA(Virus Evolution Genetic) Algorithm) can search the global and local optimal solution simultaneously with reverse transcription operator and transduction operator. Therefore in this paper, the optimal fuzzy model is obtained using Virus-messy Genetic Algorithm(Virus-mGA). In this method local information is exchanged in population so that population may sustain genetic divergence. To prove the surperioty of the proposed approach, we provide the numerical example.

• 전기학회논문지
• /
• 제67권5호
• /
• pp.663-668
• /
• 2018

A combined CPG (Central Pattern Generator) based foot trajectory and GA (Genetic Algorithm) based joint compensation method is presented for adaptive humanoid walking. In order to increase an adaptability of humanoid walking for rough terrains, the experiment for rolling terrains are introduced. The CPG based foot trajectory method has been successfully applied to basic slops and variable slops, but has a limitation for the rolling terrains. The experiments are conducted in an ODE based Webots simulation environment using humanoid robot Nao to verify a stability of walking for various rolling terrains. The proposed method is compared to the previous CPG foot trajectory technique and shows better performance especially for the cascade rolling terrains.

• 동력기계공학회지
• /
• 제18권5호
• /
• pp.129-136
• /
• 2014

This paper proposes improvement on sensorless vector control performance of a permanent magnet synchronous motor (PMSM) with sliding mode observer. An adaptive observer gain and second order cascade low-pass filter (LPF) were used to improve the estimation accuracy of the rotor position and speed. The adaptive observer gain was applied to suppress the chattering intensity and obtained by using the Lyapunov's stability criterion. The second order cascade LPF was designed for the system to escalate the filtering performance of the back-emf estimation. Furthermore, genetic algorithm was used to optimize the system PI controller's performance. Simulation results showed the effectiveness of the suggested improvement strategy. Moreover, the strategy was useful for the sensorless vector control of PMSM to operate on the low-speed area.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.234-234
• /
• 2000

A direct torque control(DTC) based sensorless speed control system which employs a new closed loop flux observer is proposed. The flux observer takes an adaptive scheduling gains where motet speed is used as the scheduling variable. Adaptive nature comes from the fact that the estimated values of stator resistance and speed are included as observer parameters. The parameters of the PI controllers adopted in the adaptive law for the estimation of stator resistance and motor speed are determined by simple genetic algorithm. Simulation results in low speed region are given for comparison between proposed and conventional flux estimate scheme.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 하계학술대회 논문집 D
• /
• pp.2693-2695
• /
• 2001

In this paper, we present an adaptive image filter using genetic algorithm. The filter is robust to the characteristic variance of image and noise, by evolving the parameter and combination of image preprocessors properly. And we have adopted adaptive mutation strategy, which use different mutation rate for specific region of chromosome. The filter is implemented on FPGA board and controlled by host PC.