IRSML: An intelligent routing algorithm based on machine learning in software defined wireless networking

Thuy-Van T. Duong,Le Huu Binh 한국전자통신연구원 2022 ETRI Journal Vol.44 No.5

In software-defined wireless networking (SDWN), the optimal routing technique is one of the effective solutions to improve its performance. This routing technique is done by many different methods, with the most common using integer linear programming problem (ILP), building optimal routing metrics. These methods often only focus on one routing objective, such as minimizing the packet blocking probability, minimizing end-to-end delay (EED), and maximizing network throughput. It is difficult to consider multiple objectives concurrently in a routing algorithm. In this paper, we investigate the application of machine learning to control routing in the SDWN. An intelligent routing algorithm is then proposed based on the machine learning to improve the network performance. The proposed algorithm can optimize multiple routing objectives. Our idea is to combine supervised learning (SL) and reinforcement learning (RL) methods to discover new routes. The SL is used to predict the performance metrics of the links, including EED quality of transmission (QoT), and packet blocking probability (PBP). The routing is done by the RL method. We use the Q-value in the fundamental equation of the RL to store the PBP, which is used for the aim of route selection. Concurrently, the learning rate coefficient is flexibly changed to determine the constraints of routing during learning. These constraints include QoT and EED. Our performance evaluations based on OMNeT++ have shown that the proposed algorithm has significantly improved the network performance in terms of the QoT, EED, packet delivery ratio, and network throughput compared with other wellknown routing algorithms.

Hierarchical Routing Techniques for Wireless Sensor Networks : A Comprehensive Survey

Ruchi Aggarwal,Anupam Mittal,Ramandeep Kaur 보안공학연구지원센터 2016 International Journal of Future Generation Communi Vol.9 No.7

This paper describes the concept of routing in wireless sensor networks. Routing algorithm provides reliable path from source to destination. Energy efficiency is main constraint in Wireless Sensor Networks. For improving life time and energy consumption various routing algorithms have been proposed. In this paper describe the hierarchical routing techniques. Hierarchical routing includes tree based routing, cluster based routing, chain based protocol, and grid based routing. And also compare the hierarchical routing techniques.

Candidate Path Selection Method for TCP Performance Improvement in Fixed Robust Routing

Yukinobu Fukushima,Takashi Matsumura,Kazutaka Urushibara,Tokumi Yokohira 대한전자공학회 2016 IEIE Transactions on Smart Processing & Computing Vol.5 No.6

Fixed robust routing is attracting attention as routing that achieves high robustness against changes in traffic patterns without conducting traffic measurement and performing dynamic route changes. Fixed robust routing minimizes the worst-case maximum link load by distributing traffic of every source-destination (s-d) router pair onto multiple candidate paths (multipath routing). Multipath routing, however, can result in performance degradation of Transmission Control Protocol (TCP) because of frequent out-of-order packet arrivals. In this paper, we first investigate the influence of multipath routing on TCP performance under fixed robust routing with a simulation using ns-2. The simulation results clarify that TCP throughput greatly degrades with multipath routing. We next propose a candidate path selection method to improve TCP throughput while suppressing the worst-case maximum link load to less than the allowed level under fixed robust routing. The method selects a single candidate path for each of a predetermined ratio of s-d router pairs in order to avoid TCP performance degradation, and it selects multiple candidate paths for each of the other router pairs in order to suppress the worst-case maximum link load. Numerical examples show that, provided the worst-case maximum link load is less than 1.0, our proposed method achieves about six times the TCP throughput as the original fixed robust routing.

Opportunistic Shortcut Tree Routing in ZigBee Networks

Taehong Kim,Daeyoung Kim IEEE 2016 IEEE SENSORS JOURNAL Vol.16 No.12

<P>The shortcut tree routing has been proposed to provide near optimal routing path as well as maintaining the advantages of the ZigBee tree routing, such as resource-free multi-hop routing capability. However, in spite of the efforts to provide an efficient and reliable protocol, the unicast routing itself has the fundamental limitation in wireless environment due to lossy, time-varying, and broadcast nature of wireless medium. For example, even one lossy link on a path may result in the failure of end-to-end packet delivery in wireless network environment. In this paper, we propose the opportunistic shortcut tree routing that combines the shortcut tree routing and the opportunistic routing. Instead of specifying a next hop node, the opportunistic shortcut tree routing allows the receiving nodes to compete to forward a packet with the priority of remaining hops. Since it has inherited advantages of both routing protocols, it can provide reliable packet delivery service without any resources for multi-hop routing and forwarder candidate selection for opportunistic routing. The performance evaluation proves that the opportunistic approach significantly enhances diverse network performances, while suppressing duplicate forwarding effectively with a metric of the remaining hops and the one-hop neighbor table.</P>

Analysis of Inter-Domain Collaborative Routing: Provider Competition for Clients

Martin O. Nicholes,Chen-Nee Chuah,Shyhtsun Felix Wu,Biswanath Mukherjee 한국통신학회 2011 Journal of communications and networks Vol.13 No.5

Any server offering a routing service in the Internet would naturally be in competition for clients, and clients may need to utilize service from a specific server in order to achieve a desired result. We study the various properties of this competition,such as the fraction of route requests handled by a routing service provider and the fraction of total revenue obtained. As the routing service providers (i.e., servers or routers in this context) compete,they may alter behavior in order to optimize one of the above properties. For example, a service provider may lower the price charged for its service, in order to increase the number of clients served. Our models are based on servers offering a routing service to clients within representative network topologies based on actual Internet sub-graphs. These models provide a framework for evaluating competition in the Internet. We monitor key aspects of the service, as several variables are introduced into the models. The first variable is the fraction of client requests that will pay more for a better quality route. The remaining requests are normal client requests that are satisfied by the most economical route. The second variable is the fraction of servers who choose to lower service prices in order to maximize the number of client requests served. As this fraction increases, it is more likely that a server will lower the price. Finally, there are some resource constraints applied to the model, to increase the dif-ficulty in providing a routing solution, i.e., to simulate a realistic scenario. We seek to understand the effect on the overall network, as service providers compete. In simple cases, we show that this competition could have a negative impact on the overall efficiency of a service. We show that the routing variety present in the larger models is unable to mask this tendency and the routing service performance is decreased due to competition.

Geographic Routing Protocol : A Review

Harminder Kaur,Harsukhpreet Singh,Anurag Sharma 보안공학연구지원센터 2016 International Journal of Grid and Distributed Comp Vol.9 No.2

Mobile Adhoc Networks (MANETs) are the self-organized networks in which connections are not established for exchange the information. In MANET, there are major problems like scalability, dynamic topology, high mobility and routing. The network can be damaged due to the high mobility. Topology based routing can fail when there is a dynamic change in the network topology. To avoid these problems, Geographic routing is used. The geographic routing protocols are more efficient and scalable when there is a dynamic change in the network topology and when the mobility is high. In this paper, we have surveyed on the Hybrid Routing and Geographic routing protocol. The hybrid routing can be done into two ways i.e. greedy routing and face-2 algorithm or perimeter routing.

Analysis of Inter-Domain Collaborative Routing: Provider Competition for Clients

Nicholes, Martin O,Chuah, Chen-Nee,Wu, Shyhtsun Felix,Mukherjee, Biswanath The Korea Institute of Information and Commucation 2011 Journal of communications and networks Vol.13 No.5

Any server offering a routing service in the Internet would naturally be in competition for clients, and clients may need to utilize service from a specific server in order to achieve a desired result. We study the various properties of this competition, such as the fraction of route requests handled by a routing service provider and the fraction of total revenue obtained. As the routing service providers (i.e., servers or routers in this context) compete, they may alter behavior in order to optimize one of the above properties. For example, a service provider may lower the price charged for its service, in order to increase the number of clients served. Our models are based on servers offering a routing service to clients within representative network topologies based on actual Internet sub-graphs. These models provide, a framework for evaluating competition in the Internet. We monitor key aspects of the service, as several variables are introduced into the models. The first variable is the fraction of client requests that will pay more for a better quality route. The remaining requests are normal client requests that are satisfied by the most economical route. The second variable is the fraction of servers who choose to lower service prices in order to maximize the number of client requests served. As this fraction increases, it is more likely that a server will lower the price. Finally, there are some resource constraints applied to the model, to increase the difficulty in providing a routing solution, i.e., to simulate a realistic scenario. We seek to understand the effect on the overall network, as service providers compete. In simple cases, we show that this competition could have a negative impact on the overall efficiency of a service. We show that the routing variety present in the larger models is unable to mask this tendency and the routing service performance is decreased due to competition.

Code Analysis and Improvement of Onion Routing Anonymous Systems

Tianbo Lu,Youwen Wang,Lingling Zhao,Yang Lin,Xiaoyan Zhang 보안공학연구지원센터 2016 International Journal of Future Generation Communi Vol.9 No.8

With the development of Internet technology, network based activities such as e-commerce, internet voting and e-government, etc. have become increasingly frequent, People are increasingly concerned about the identity of network activity, content and other private information. In order to protect user privacy in network communications, governments, companies, universities and research institutes are pushing the research and development of the onion routing systems (TOR). Tor is the most popular anonymous communication system currently, which is based on technology of the second-generation onion routing. Tor has a low latency, encrypted data transmission, secure channel, etc., which are widely used in anonymous Web browsing, instant messaging, Secure Shell Client (SSH), etc. However, the development of the onion routing systems is constrained by complicated code factors. According to this situation, this paper put forward an overall architecture of TOR code, which contains Application Needs, Code Analysis and Improvement. This paper summarizes the overall framework of tor code structure, in order to make the code structure clearer, the whole code module is divided into several sub modules, using the function call diagram and UML diagram illustrates the main function of each module and call relation between each module. This paper gives code analysis for anonymous architecture of TOR. Finally, this paper put forward the improvement of routing algorithms of TOR. Based on this paper, a method has been created which is used to understand the tor code easily. Furthermore, systematic analysis of the tor code provided in this paper aims to research the working principle and promote the further development of the onion routing.

차량 통신망에서 Angle 우선순위를 가진 Forwarding 프로토콜

유석대,이동춘 한국융합보안학회 2010 융합보안 논문지 Vol.10 No.1

Greedy 프로토콜은 일반적으로 VANETs에서 좋은 성능을 보인다. 그렇지만 일시적으로 거리 를 비게 만드는 교통신호가 존재하는 구간이나 분리된 도로가 합류하는 지점이 없는 urban의 도로에서 지형적인 영향으로 greedy 라우팅 프로토콜은 잘못된 경로 라우팅된 경우 불필요하게 경로가 길어지거나 라우팅 실패로 나타난다. 기존의 Greedy 라우팅 프로토콜은 단순하게 목적 지 노드와의 직선거리를 가지고 노드들의 우선순위를 부여하고 가장 낮은 값을 가진 노드를 중 계노드로 선택한다. VANET에서는 지리적인 환경의 특성 때문에 거리뿐만 아니라 전달 방향도 중요하다. 제안된 방법에서는 하나의 노드가 패킷을 전달할 때 목적지 노드까지의 거리와 함께 전달 방향을 고려하여 다음 노드를 선정하여 보다 안정적인 경로 설정을 할 수 있고 지형 모델 이 따라 변경이 가능하다. 제안된 방법의 성능은 두 가지의 이동모델을 적용한 네트워크 시뮬레 이션을 통하여 검증하였고 대부분의 경우 기존 프로토콜보다 좋은 성능을 보였다. Greedy protocols show good performance in Vehicular Ad-hoc Networks (VANETs) environment in general. But they make longer routes causing by surroundings or turn out routing failures in some cases when there are many traffic signals which generate empty streets temporary, or there is no merge roads after a road divide into two roads. When a node selects the next node simply using the distance to the destination node, the longer route is made by traditional greedy protocols in some cases and sometimes the route ends up routing failure. Most of traditional greedy protocols just take into account the distance to the destination to select a next node. Each node needs to consider not only the distance to the destination node but also the direction to the destination while routing a packet because of geographical environment. The proposed routing scheme considers both of the distance and the direction for forwarding packets to make a stable route. And the protocol can configure as the surrounding environment. We evaluate the performance of the protocol using two mobility models and network simulations. Most of network performances are improved rather than in compared with traditional greedy protocols.Greedy protocols show good performance in Vehicular Ad-hoc Networks (VANETs) environment in general. But they make longer routes causing by surroundings or turn out routing failures in some cases when there are many traffic signals which generate empty streets temporary, or there is no merge roads after a road divide into two roads. When a node selects the next node simply using the distance to the destination node, the longer route is made by traditional greedy protocols in some cases and sometimes the route ends up routing failure. Most of traditional greedy protocols just take into account the distance to the destination to select a next node. Each node needs to consider not only the distance to the destination node but also the direction to the destination while routing a packet because of geographical environment. The proposed routing scheme considers both of the distance and the direction for forwarding packets to make a stable route. And the protocol can configure as the surrounding environment. We evaluate the performance of the protocol using two mobility models and network simulations. Most of network performances are improved rather than in compared with traditional greedy protocols.

Blind Detouring Problem in Geographic Routing for Wireless Ad - hoc Networks

나종근(Jongkeun Na),김종권(Chongkwon Kim) 한국정보과학회 2006 정보과학회논문지 : 정보통신 Vol.33 No.6

최근 몇년간 무선 애드-혹 라우팅을 위한 많은 스킴들이 광범위하게 연구되었다. 위치기반 라우팅은 애드-혹 라우팅의 한 부류로써, 각 중계노드는 자신 및 목적지, 그리고 이웃노드들의 위치정보에 기반하여 독립적으로 다음-홉(next-hop) 노드를 선택한다. 이러한 위치기반 라우팅은 라우팅 상태 정보를 유지해야 하는 부담이 없기 때문에 대규모 애드-혹 망에 적합하다. 그러나, 위치기반 라우팅은 발신지와 목적지 사이에 빈공간(void)이 존재할 경우 매우 긴 우회 경로를 선택하는 문제를 안고 있다. 이 문제를 해결하기 위해, 본 논문에서는 랜드마크를 이용하는 위치기반 라우팅 방안(GLR)을 제안한다. GLR은 랜드마크(landmark)라고 불리우는 중계노드를 재귀적으로 발견하고 랜드마크 사이를 연결하는 서브패스(sub-path)를 구성한다. 다양한 망 위상에서 행해진 시뮬레이션 결과를 통해서, 제안된 방안(GLR)이 위치 기반 라우팅의 성능을 크게 향상시킬 수 있음을 보인다. Wireless ad-hoc routing has been extensively studied and many clever schemes have been proposed over the last several years. One class of ad-hoc routing is geographic routing where each intermediate node independently selects the next hop using the given location information of destination. Geographic routing, which eliminates the overhead of route request packet flooding, is scalable and suitable for large scale ad hoc networks. However, geographic routing may select the long detour paths when there are voids between a source and a destination. In this paper, we propose a novel geographic routing approach called Geographic Landmark Routing (GLR). GLR recursively discovers the intermediate nodes called landmarks and constructs sub-paths that connect the subsequent landmarks. Simulation results on various network topologies show that GLR significantly improves the performance of geographic routing.