• 대한임베디드공학회논문지
• /
• 제19권2호
• /
• pp.107-114
• /
• 2024

Mobile ad hoc networks represent self-configuring networks of mobile devices that communicate without relying on a fixed infrastructure. However, traditional routing protocols in such networks encounter challenges in selecting efficient and reliable routes due to dynamic nature of these networks caused by unpredictable mobility of nodes. This often results in a failure to meet the low-delay and low-energy consumption requirements crucial for such networks. In order to overcome such challenges, our paper introduces a novel multi-objective and adaptive routing scheme based on the Q-learning reinforcement learning algorithm. The proposed routing scheme dynamically adjusts itself based on measured network states, such as traffic congestion and mobility. The proposed approach utilizes Q-learning to select routes in a decentralized manner, considering factors like energy consumption, load balancing, and the selection of stable links. We present a formulation of the multi-objective optimization problem and discuss adaptive adjustments of the Q-learning parameters to handle the dynamic nature of the network. To speed up the learning process, our scheme incorporates informative shaped rewards, providing additional guidance to the learning agents for better solutions. Implemented on the widely-used AODV routing protocol, our proposed approaches demonstrate better performance in terms of energy efficiency and improved message delivery delay, even in highly dynamic network environments, when compared to the traditional AODV. These findings show the potential of leveraging reinforcement learning for efficient routing in ad hoc networks, making the way for future advancements in the field of mobile ad hoc networking.

• 한국해양공학회지
• /
• 제29권3호
• /
• pp.263-269
• /
• 2015

This paper proposes a new approach for solving the weather routing problem by dividing it into two phases with the goal of fuel saving. The problem is to decide two optimal variables: the heading angle and speed of the ship under several constraints. In the first phase, the optimal route is obtained using the Real-Time Adaptive A* algorithm with a fixed ship speed. In other words, only the heading angle is decided. The second phase is the speed scheduling phase. In this phase, the original problem, which is a nonlinear optimization problem, is converted into a geometric programming problem. By solving this geometric programming problem, which is a convex optimization problem, we can obtain an optimal speed scheduling solution very efficiently. A simple case of numerical simulation is conducted in order to validate the proposed method, and the results show that the proposed method can save fuel compared to a constant engine output voyage and constant speed voyage.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2006년도 추계 종합학술대회 논문집
• /
• pp.716-720
• /
• 2006

본 논문에서는 원격의료지원을 위한 Ubiquitous Sensor Network에서 생체신호를 효율적으로 전송하기 위하여 생체신호의 데이터 종류에 따라 전송 전력의 크기와 경로설정 빈도수를 변화시키는 새로운 라우팅 방안을 제안한다. 제안한 라우팅 알고리즘에서는 위급한 생체신호 트래픽에 대해서는 경로 설정 지연을 줄일 수 있도록 전송전력의 크기를 크게 설정하여 경유하는 흡수를 줄이고 경로 설정에 우선순위를 주며, 위급하지 않은 생체신호 트래픽에 대해서는 전송전력의 크기를 작게 설정하고, 경로설정 빈도수를 적응적으로 감소시킨다 따라서 위급한 생체신호 트래픽에 대해서는 평균 흡수 및 호 블로킹 확률을 줄일 수 있어서 기존의 획일적인 전송전력의 크기를 사용하는 방안에 비해 복잡한 USN에서 위급한 생체신호의 QoS를 만족할 수 있을 것이다.

• 한국통신학회논문지
• /
• 제30권5B호
• /
• pp.304-309
• /
• 2005

본 논문에서는 TD(temporal differences) 기법을 사용한 localized QoS 라우팅 기법을 제안하였다. 이 기법은 이웃노드로부터 얻어지는 성공 기댓값을 통해 라우팅 정책을 결정하는 기법이다. 이에 본 논문에서는 라우팅 성공 기댓값을 기반으로 한 다양한 탐색기법으로 경로 선택 시 라우팅 성능을 비교 평가하였으며, 특히 Exploration Bonus를 적용한 탐색 기법이 다른 탐색 기법에 비해 더욱 우수한 성능을 보여주고 있는데, 이는 다른 탐색 기법에 비해 네트워크 상황에 더 적응적으로 경로를 선택할 수 있기 때문이다.

• Advances in aircraft and spacecraft science
• /
• 제10권5호
• /
• pp.393-418
• /
• 2023

Drones are increasingly used in logistics delivery due to their low cost, high-speed and straight-line flight. Considering the small cargo capacity, limited endurance and other factors, this paper optimized the pickup and delivery vehicle routing problem with time windows in the mode of "truck+drone". A mixed integer programming model with the objective of minimizing transportation cost was proposed and an improved adaptive large neighborhood search algorithm is designed to solve the problem. In this algorithm, the performance of the algorithm is improved by designing various efficient destroy operators and repair operators based on the characteristics of the model and introducing a simulated annealing strategy to avoid falling into local optimum solutions. The effectiveness of the model and the algorithm is verified through the numerical experiments, and the impact of the "truck+drone" on the route cost is analyzed, the result of this study provides a decision basis for the route planning of "truck+drone" mode delivery.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권5호
• /
• pp.1790-1806
• /
• 2015

Utility-based routing is a special type of routing approach using a composite utility metric when making routing decisions in ad hoc and sensor networks. Previous studies on the utility-based routing all use fixed retry limit and a very simple distance related energy model, which makes the utility maximization less efficient and the implementation separated from practice. In this paper, we refine the basic utility model by capturing the correlation of the transmit power, the retry limit, the link reliability and the energy cost. A routing algorithm based on the refined utility model with adaptive transmit power and retry limit allocation is proposed. With this algorithm, packets with different priorities will automatically receive utility-optimal delivery. The design of this algorithm is based on the observation that for a given benefit, there exists a utility-maximum route with optimal transmit power and retry limit allocated to intermediate forwarding nodes. Delivery along the utility-optimal route makes a good balance between the energy cost and the reliability according to the value of the packets. Both centralized algorithm and distributed implementations are discussed. Simulations prove the satisfying performance of the proposed algorithm.

• ETRI Journal
• /
• 제28권6호
• /
• pp.815-818
• /
• 2006

In the global Internet, a constraint-based routing algorithm performs the function of selecting a routing path while satisfying some given constraints rather than selecting the shortest path based on physical topology. It is necessary for constraint-based routing to disseminate and update link state information. The triggering policy of link state updates significantly affects the volume of update traffic and the quality of services (QoS). In this letter, we propose an adaptive triggering policy based on link-usage statistics in order to reduce the volume of link state update traffic without deterioration of QoS. Also, we evaluate the performance of the proposed policy via simulations.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권12호
• /
• pp.5729-5744
• /
• 2017

Vehicular Ad Hoc Networks (VANET) in the large-scale road section usually have typical characteristics of large number of vehicles and unevenly distribution over geographic spaces. These two inherent characteristics lead to the unsatisfactory performance of VANETs. This poor performance is mainly due to fragile communication link and low dissemination efficiency. We propose a novel routing mechanism to address the issue in the paper, which includes a competition-based routing discovery with priority metrics and a local routing repair strategy. In the routing discovery stage, the algorithm uses adaptive scheme to select a stable route by the priorities of routing metrics, which are the length of each hop, as well as the residual lifetime of each link. Comparisons of different ratios over link length and link stability further show outstanding improvements. In the routing repair process, upstream and downstream nodes also compete for the right to establish repair process and to remain as a member of the active route after repair. Our simulation results confirm the improved performance of the proposed algorithm.

• 정보처리학회논문지A
• /
• 제9A권4호
• /
• pp.547-554
• /
• 2002

본 논문은 분산 공유메모리 환경의 다단계 버스망을 위한 동적 라우팅 방범을 제안한다. 제안된 라우팅 방법의 특징은 다단계 버스망이 제공하는 잉여경로를 활용하고 스위치 트래픽에 따라 적응적으로 경로를 결정하여 스위치의 트래픽을 분산시키는 것이다. 구체적으로는 잉여경로 상의 다음 단계 스위치의 트래픽 정도가 높고 낮음을 판단하여 트래픽 정도가 낮은 스위치로 패킷을 전달한다. 그 결과 평균 응답시간과 스위치상의 평균 대기패킷수를 줄이는 효과를 얻는다. 프로세서수와 스위치 크기를 변화시키면서 시뮬레이션을 하여 제안된 알고리즘이 잉여경로를 고려하지 않는 기존의 알고리즘에 비하여 평균 응답시간은 약 9%, 스위치 상의 평균 대기패킷수는 21.6% 정토 향상시킨다는 것을 보여준다

• 대한전자공학회논문지TC
• /
• 제42권5호
• /
• pp.29-38
• /
• 2005

본 논문은 생태계 군집 시스템을 네트워크 기술에 응용한 적응형 라우팅 알고리즘인 AntNet을 기존의 상용 네트워크 프로세서 기반에서 최적화할 수 있도록 개선된 알고리즘을 제안하는 연구이다. 현재 사용되고 있는 네트워크 프로세서는 단순한 패킷 프로세싱만을 위해 설계되어 AntNet과 같은 복잡한 연산이 필요한 적응형 라우팅 알고리즘을 구현하는데 많은 문제점을 가지고 있다. 이를 분석하고 해결하기 위해 AntNet의 강화인자를 연산하는 부분을 중심으로 적응 성능은 유지하면서도 효율적으로 연산실행시간을 줄일 수 있는 개선된 AntNet알고리즘을 제안하였다. 이를 시뮬레이션을 통해 비교분석함으로서 제안한 개선된 AntNet알고리즘의 효용성을 검증한다.