Adaptive Routing for an Ad Hoc Network Based on Reinforcement Learning

2015 ◽  
Vol 11 (2) ◽  
pp. 40-52
Author(s):  
Rahul Desai ◽  
B.P. Patil
Keyword(s):  
Reinforcement Learning ◽  
Shortest Path ◽  
Ad Hoc Network ◽  
Ad Hoc ◽  
Learning Algorithms ◽  
High Mobility ◽  
Delivery Ratio ◽  
Shortest Path Routing ◽  
Minimum Number ◽  
Shortest Path Algorithms

This paper describes and evaluates the performance of various reinforcement learning algorithms with shortest path algorithms that are widely used for routing packets throughout the network. Shortest path routing is simplest policy used for routing the packets along the path having minimum number of hops. In high traffic or high mobility conditions, the shortest path gets flooded with huge number of packets and congestions occurs, so such shortest path does not provide the shortest path and increases delay for reaching the packets to the destination. Reinforcement learning algorithms are adaptive algorithms where the path is selected based on the traffic present on the network at real time. Thus they guarantee the least delivery time to reach the packets to the destination. Analysis is done on a 6-by-6 irregular grid and sample ad hoc network shows that performance parameters used for judging the network such as packet delivery ratio and delay provide optimum results using reinforcement learning algorithms.

Analysis of Reinforcement Based Adaptive Routing in MANET

2016 ◽  
Vol 2 (3) ◽  
pp. 648 ◽  
Author(s):  
Rahul Desai ◽  
B P Patil
Keyword(s):  
Reinforcement Learning ◽  
Shortest Path ◽  
Ad Hoc Network ◽  
Ad Hoc ◽  
Learning Algorithms ◽  
High Mobility ◽  
Delivery Ratio ◽  
Shortest Path Routing ◽  
Minimum Number ◽  
Shortest Path Algorithms

<p class="Abstract">This paper describes and evaluates the performance of various reinforcement learning algorithms with shortest path algorithms that are widely used for routing packets through the network. Shortest path routing is the simplest policy used for routing the packets along the path having minimum number of hops. In high traffic or high mobility conditions, the shortest path get flooded with huge number of packets and congestions occurs, So such shortest path does not provides the shortest path and increases delay for reaching the packets to the destination. Reinforcement learning algorithms are adaptive algorithms where the path is selected based on the traffic present on the network at real time. Thus they guarantee the least delivery time to reach the packets to the destination. Analysis done on a 6 by 6 irregular grid and sample ad hoc network shows that performance parameters used for judging the network - packet delivery ratio and delay provides optimum results using reinforcement learning algorithms. </p>

Prioritized Sweeping Reinforcement Learning Based Routing for MANETs

2017 ◽  
Vol 5 (2) ◽  
pp. 383 ◽  
Author(s):  
Rahul M Desai ◽  
B P Patil
Keyword(s):  
Reinforcement Learning ◽  
Shortest Path ◽  
Ad Hoc ◽  
Mobile Ad Hoc Network ◽  
Network Routing ◽  
Delivery Ratio ◽  
Learning Method ◽  
Shortest Path Routing ◽  
Mobile Ad Hoc ◽  
Prioritized Sweeping

<p class="Default">In this paper, prioritized sweeping confidence based dual reinforcement learning based adaptive network routing is investigated. Shortest Path routing is always not suitable for any wireless mobile network as in high traffic conditions, shortest path will always select the shortest path which is in terms of number of hops, between source and destination thus generating more congestion. In prioritized sweeping reinforcement learning method, optimization is carried out over confidence based dual reinforcement routing on mobile ad hoc network and path is selected based on the actual traffic present on the network at real time. Thus they guarantee the least delivery time to reach the packets to the destination. Analysis is done on 50 Nodes Mobile ad hoc networks with random mobility. Various performance parameters such as Interval and number of nodes are used for judging the network. Packet delivery ratio, dropping ratio and delay shows optimum results using the prioritized sweeping reinforcement learning method.</p>

scholarly journals TEKNIK KOMUNIKASI DATA PADA AD HOC NETWORK COMMUNICATION

2014 ◽  
Vol 11 (2) ◽  
Author(s):  
Budi Rahmadya
Keyword(s):  
Mobile Networks ◽  
Ad Hoc Network ◽  
Ad Hoc ◽  
Data Communication ◽  
High Mobility ◽  
Delay Tolerant Network ◽  
Network Communication ◽  
Destination Node ◽  
Delivery Ratio ◽  
Data Packets

Ad Hoc Network Communication is mobile networks communications and have a high mobility for each of its nodes. This type of network communications is a temporary networkwith utilizing a WiFi network or Bluethoot as a medium of communications. In the entirenetwork, node moves with a speed varying and unpredictable direction. Packets data delivery from the source node to destination node by using an ad hoc network requires its owntechniques. In this research discussed the existing data communication technique inVehicular Ad Hoc Network (VANETs) Communications with attention: Broadcasting Time, Routing Protocol, Message Dissemination, Delay Tolerant Network Dissemination and / DTN.These techniques can increase the delivery ratio / sending data packets to the destination as well as a smaller delay time. In order to maintain the integrity of the data packets received bythe destination node, the authors have proposed a method of duplicate messages in thisresearch.

Disaster Relief Management Using Reinforcement Learning-Based Routing

2021 ◽  
Vol 17 (1) ◽  
pp. 24-37
Author(s):  
Gajanan Madhavrao Walunjkar ◽  
Anne Koteswara Rao ◽  
V. Srinivasa Rao
Keyword(s):  
Reinforcement Learning ◽  
Routing Protocol ◽  
Ad Hoc ◽  
Average Energy ◽  
High Mobility ◽  
Adaptive Routing ◽  
Mobility Model ◽  
Delivery Ratio ◽  
Disaster Area ◽  
Disaster Scenario

Effective disaster management is required for the peoples who are trapped in the disaster scenario but unfortunately when disaster situation occurs the infrastructure support is no longer available to the rescue team. Ad hoc networks which are infrastructure-less networks can easily deploy in such situation. In disaster area mobility model, disaster area is divided into different zones such as incident zone, casualty treatment zones, transport areas, hospital zones, etc. Also, in order to tackle high mobility of nodes and frequent failure of links in a network, there is a need of adaptive routing protocol. Reinforcement learning is used to design such adaptive routing protocol which shows good improvement in packet delivery ratio, delay and average energy consumed.

Analysis of Effective Routing Protocols for Flying Ad-Hoc Networks

2020 ◽  
Vol 3 (2) ◽  
pp. 1-18 ◽  
Author(s):  
Sudesh Kumar ◽  
Abhishek Bansal ◽  
Ram Shringar Raw
Keyword(s):  
Routing Protocol ◽  
Ad Hoc Network ◽  
High Speed ◽  
Ad Hoc ◽  
Network Formation ◽  
High Mobility ◽  
Delivery Ratio ◽  
Data Packets ◽  
Hoc Networks ◽  
Networking Technology

Recently, the flying ad-hoc network (FANETs) is a popular networking technology used to create a wireless network through unmanned aerial vehicles (UAVs). In this network, the UAV nodes work as intermediate nodes that communicate with each other to transmit data packets over the network, in the absence of fixed an infrastructure. Due to high mobility degree of UAV nodes, network formation and deformation among the UAVs are very frequent. Therefore, effective routing is a more challenging issue in FANETs. This paper presents performance evaluations and comparisons of the popular topology-based routing protocol namely AODV and position-based routing protocol, namely LAR for high speed mobility as well as a verity of the density of UAV nodes in the FANETs environment through NS-2 simulator. The extensive simulation results have shown that LAR gives better performance than AODV significantly in terms of the packet delivery ratio, normalized routing overhead, end-to-end delay, and average throughput, which make it a more effective routing protocol for the highly dynamic nature of FANETs.

Study on a Novel GIS-Based Routing Strategy

2014 ◽  
Vol 644-650 ◽  
pp. 2969-2972
Author(s):  
Yue Wei Wang ◽  
Ding Yi Ji
Keyword(s):  
Routing Protocols ◽  
Ad Hoc Network ◽  
Ad Hoc ◽  
High Mobility ◽  
Delivery Ratio ◽  
Scenario Simulation ◽  
Packet Delivery ◽  
Routing Strategy ◽  
Topology Changes ◽  
The City

Given a scenario of Vehicle Ad hoc Network (VANET), this paper presented a GIS-Based routing (GBR) strategy to resolve frequent reconstruction caused by rapid topology changes. Due to the use of road information based on GIS, the protocol can evade permanent or temporary topology holes respectively which frequently occurred in the city scenario. Simulation results showed new routing protocols could achieve better performance in packet delivery ratio and proved GBR’s lower routing overhead, as well as it is better performances in high mobility, compared with DSR in urban vehicle environment.

scholarly journals TEKNIK KOMUNIKASI DATA PADA AD HOC NETWORK COMMUNICATION

2014 ◽  
Vol 11 (2) ◽  
Author(s):  
Budi Rahmadya
Keyword(s):  
Mobile Networks ◽  
Ad Hoc Network ◽  
Ad Hoc ◽  
Data Communication ◽  
High Mobility ◽  
Delay Tolerant Network ◽  
Network Communication ◽  
Destination Node ◽  
Delivery Ratio ◽  
Data Packets

Ad Hoc Network Communication is mobile networks communications and have a high mobility for each of its nodes. This type of network communications is a temporary networkwith utilizing a WiFi network or Bluethoot as a medium of communications. In the entirenetwork, node moves with a speed varying and unpredictable direction. Packets data delivery from the source node to destination node by using an ad hoc network requires its owntechniques. In this research discussed the existing data communication technique inVehicular Ad Hoc Network (VANETs) Communications with attention: Broadcasting Time, Routing Protocol, Message Dissemination, Delay Tolerant Network Dissemination and / DTN.These techniques can increase the delivery ratio / sending data packets to the destination as well as a smaller delay time. In order to maintain the integrity of the data packets received bythe destination node, the authors have proposed a method of duplicate messages in thisresearch.

scholarly journals A Hybrid and Robust Delay and Link Stability Aware (DLSA) Routing Protocol for Unmanned Aerial Ad-hoc Networks (UAANETs)

2021 ◽  
Author(s):  
Altaf Hussain
Keyword(s):  
Network Lifetime ◽  
Ad Hoc Network ◽  
Ad Hoc ◽  
Mobile Ad Hoc Network ◽  
Transmission Loss ◽  
Three Dimensional ◽  
High Mobility ◽  
Threshold Value ◽  
Delivery Ratio ◽  
Link Stability

Abstract Unmanned Aerial Ad-hoc Network (UAANET) also knows as by the name of Flying Ad-hoc NETwork (FANET) is a new class of Mobile Ad-hoc NETwork (MANET) in which the nodes move in three dimensional (3-D) ways in the air simultaneously. These nodes are known as Unmanned Aerial Vehicles (UAVs) that are operated live remotely or by pre-defined mechanism which involve no human personnel. Due to high mobility of nodes and dynamic topology, the link stability is a research challenge in FANET. From this viewpoint, recent research has focused on link stability with highest threshold value by maximizing Packet Delivery Ratio (PDR) and minimizing End-to-End Delay (E2ED). In this research, a hybrid scheme named Delay and Link Stability Aware (DLSA) routing scheme has been proposed with the contrast of Distributed Priority Tree-based Routing (DPTR) and Link Stability Estimation-based Routing (LEPR) FANET’s existing routing schemes. Unlike existing schemes, the proposed scheme possesses the features in collaborative data forwarding and link stability by merging the positive features of DPTR and LEPR. The link stability via maximum threshold value has been introduced to acquire and select the most feasible route from source to destination. The simulation was carried out using Matrix Laboratory (MATLAB) tool for the concerned research. Simulation results have showed improved performance of the proposed protocol in contrast to the selected existing ones in terms of E2ED, PDR, Network Lifetime and Transmission Loss. Average E2ED in (milliseconds) of DLSA measured 0.457, while DPTR was 1.492 and LEPR was 1.006. Similarly, Average PDR (in %age) of DLSA measured 3.106, while DPTR was 2.303 and LEPR was 0.682. Average Network Lifetime in (seconds) for DLSA measured 62.141, while DPTR was 23.036 and LEPR was 27.298. Average Transmission Loss in (dBm) for DLSA measured 0.975, while DPTR was 1.053 and LEPR was 1.227.

Sign in / Sign up

Export Citation Format

Share Document