• 로봇학회논문지
• /
• 제14권4호
• /
• pp.285-292
• /
• 2019

Path planning is an important problem to solve in robotics and there has been many related studies so far. In the previous research, we proposed the Heterogeneous-Ants-Based Path Planner (HAB-PP) for the global path planning of mobile robots. The conventional path planners using grid map had discrete state transitions that constrain the only movement of an agent to multiples of 45 degrees. The HAB-PP provided the smoother path using the heterogeneous ants unlike the conventional path planners based on Ant Colony Optimization (ACO) algorithm. The planner, however, has the problem that the optimization of the path once found is fast but it takes a lot of time to find the first path to the goal point. Also, the HAB-PP often falls into a local optimum solution. To solve these problems, this paper proposes an improved ant-inspired path planner using the Rapidly-exploring Random Tree-star ($RRT^*$). The key ideas are to use $RRT^*$ as the characteristic of another heterogeneous ant and to share the information for the found path through the pheromone field. The comparative simulations with several scenarios verify the performance of the improved HAB-PP.

• International Journal of Computer Science & Network Security
• /
• 제21권8호
• /
• pp.342-352
• /
• 2021

Multicast Routings is a big challenge due to limitations such as node power and bandwidth Mobile Ad-hoc Network (MANET). The path to be chosen from the source to the destination node requires protocols. Multicast protocols support group-oriented operations in a bandwidth-efficient way. While several protocols for multi-cast MANETs have been evolved, security remains a challenging problem. Consequently, MANET is required for high quality of service measures (QoS) such infrastructure and application to be identified. The goal of a MANETs QoS-aware protocol is to discover more optimal pathways between the network source/destination nodes and hence the QoS demands. It works by employing the optimization method to pick the route path with the emphasis on several QoS metrics. In this paper safe routing is guaranteed using the Secured Multicast Routing offered in MANET by utilizing the Ant Colony Optimization (ACO) technique to integrate the QOS-conscious route setup into the route selection. This implies that only the data transmission may select the way to meet the QoS limitations from source to destination. Furthermore, the track reliability is considered when selecting the best path between the source and destination nodes. For the optimization of the best path and its performance, the optimized algorithm called the micro artificial bee colony approach is chosen about the probabilistic ant routing technique.

• 한국환경복원기술학회지
• /
• 제21권2호
• /
• pp.27-38
• /
• 2018

Environmental planning includes resource allocation and spatial planning process for the conservation and management of environment. Because the spatialization of the environmental planning is not specifically addressed in the relevant statutes, it actually depends on the qualitative methodology such as expert judgement. The results of the qualitative methodology have the advantage that the accumulated knowledge and intuition of the experts can be utilized. However, it is difficult to objectively judge whether it is enough to solve the original problem or whether it is the best of the possible scenarios. Therefore, this study proposed a methodology to quantitatively and objectively spatialize various environmental planning. At first, we suggested a quantitative spatial planning model based on an optimization algorithm. Secondly, we applied this model to two kinds of environmental planning and discussed about the model performance to present the applicability. Since the models were developed based on conceptual study site, there was a limitation in showing possibility of practical use. However, we expected that this study can contribute to the fields related to environmental planning by suggesting flexible and novel methodology.

• Journal of Electrical Engineering and Technology
• /
• 제4권1호
• /
• pp.55-65
• /
• 2009

Due to the rapid increase of electricity demand, consideration of environmental constraints in optimal power flow (OPF) problems is increasingly important. In Algeria, up to 90% of electricity is produced by thermal generators (vapor, gas). In order to keep the emission of gaseous pollutants like sulfur dioxide (SO2) and Nitrogen (NO2) under the admissible ecological limits, many conventional and global optimization methods have been proposed to study the trade-off relation between fuel cost and emissions. This paper presents an efficient decomposed Parallel GA to solve the multi-objective environmental/economic dispatch problem. At the decomposed stage the length of the original chromosome is reduced successively and adapted to the topology of the new partition. Two subproblems are proposed: the first subproblem is related to the active power planning to minimize the total fuel cost, and the second subproblem is a reactive power planning design based in practical rules to make fine corrections to the voltage deviation and reactive power violation using a specified number of shunt dynamic compensators named Static Var Compensators (SVC). To validate the robustness of the proposed approach, the algorithm proposed was tested on the Algerian 59-bus network test and compared with conventional methods and with global optimization methods (GA, FGA, and ACO). The results show that the approach proposed can converge to the near solution and obtain a competitive solution at a critical situation and within a reasonable time.

• 정보처리학회논문지B
• /
• 제11B권1호
• /
• pp.77-82
• /
• 2004

강화학습에서 temporal-credit 할당 문제 즉, 에이전트가 현재 상태에서 어떤 행동을 선택하여 상태전이를 하였을 때 에이전트가 선택한 행동에 대해 어떻게 보상(reward)할 것인가는 강화학습에서 중요한 과제라 할 수 있다. 본 논문에서는 조합최적화(hard combinational optimization) 문제를 해결하기 위한 새로운 메타 휴리스틱(meta heuristic) 방법으로, greedy search뿐만 아니라 긍정적 반응의 탐색을 사용한 모집단에 근거한 접근법으로 Traveling Salesman Problem(TSP)를 풀기 위해 제안된 Ant Colony System(ACS) Algorithms에 Q-학습을 적용한 기존의 Ant-Q 학습방범을 살펴보고 이 학습 기법에 다양화 전략을 통한 상태전이와 TD-오류를 적용한 학습방법인 Ant-TD 강화학습 방법을 제안한다. 제안한 강화학습은 기존의 ACS, Ant-Q학습보다 최적해에 더 빠르게 수렴할 수 있음을 실험을 통해 알 수 있었다.

• 한국정보과학회논문지:시스템및이론
• /
• 제37권3호
• /
• pp.147-160
• /
• 2010

최근 서버의 통합을 통해 시스템 자원의 효율적인 활용을 제공할 수 있는 시스템 가상화가 많은 주목을 받고 있다. 이 시스템 가상화 기술을 통하여 보다 효과적으로 시스템 자원을 활용하고 가상화 소프트웨어의 성능을 향상시킬 수 있는 방안이 다양하게 연구되고 있다. 이러한 연구들은 CPU 측면에서 동적으로 가상머신에 할당된 양을 조절하거나 마이그레이션 기능을 활용하여 머신 간 자원 관리 등의 다양한 측면에서 활발하게 진행되고 있으나 메모리 측면에서는 그 연구가 매우 부족한 실정이다. 따라서 서버 통합에서의 메모리 자원의 이용은 가상머신 탑재 시에 정적으로 할당된 메모리를 사용하는 수준에서 머물고 있다. 하지만 본 논문의 성능 비교 환경인 Xen 가상화에서 가상머신에 정적으로 메모리를 할당하는 방식은 유휴메모리를 다량 발생시켜 메모리 이용률을 낮추게 된다. 메모리 이용률을 높이기 위하여 가상머신에 할당하는 메모리양을 줄일 경우 다른 시스템 자원에도 영향을 미치게 되며 가상머신에서 운영되는 서비스의 성능 저하를 유발하게 된다. 본 논문에서는 가상머신 사이의 메모리 할당량을 조절하여 가상머신의 서비스에 성능저하가 없으면서 이용률을 향상시킬 수 있는 메모리의 동적 할당을 제안한다. 메모리 사용량 예측을 위한 AR 모델과 메모리 이용률 최적화를 위한 개미 군집 알고리즘을 사용하여 구현한 메모리의 동적 할당 시스템을 통하여 정적 할당의 경우에 비하여 더 많은 수의 가상머신을 운영할 수 있게 되고 서버로 운영되는 가상머신의 서비스 성능 저하 없이 약 1.4배의 이용률 향상을 얻을 수 있었다.