A Reinforcement Learning Network based Novel Adaptive Routing Algorithm for Wireless Ad-Hoc Network

Elaboration 2014 6 Pages

Computer Science - Technical Computer Science



A Wireless network is a collection of autonomous mobile nodes that communicate with each other over wireless links without any fixed infrastructure. It is a method by which homes, telecommunications networks and enterprise installations avoid the costly process of introducing cables into a building, or as a connection between various equipment locations. A routing protocol is taking a vital role in the modern Wireless Network. Mobile ad hoc network (MANET) is an autonomous system of mobile nodes connected by wireless links. Each node operates not only as an end system, but also as a router to forward packets .The nodes are free to move about and a network.A routing protocol which is responsible to determine how nodes communicate with each other and forward the packets through the optimal path to travel from a source node to a destination node. The purpose of paper is to contribute the study and comparison of routing protocols performance in MANET

Keywords: Wireless, Routing Protocol, AODV, DSR, ZRP..


In the computing industry the importance of Wireless network is become very high. Wireless network are adapted to enable mobility to a great extend. There are two types of network they are Infra-structured network and ad-hoc network. In Infra-structured network have the network with fixed and wired gateway. In ad hoc networks, where all devices have equal status on a network and are free to associate with any other ad hoc network devices in link range. A mobile ad-hoc network is self-configuring network of mobile nodes which do not need any pre-existing infrastructure. In MANET the mobility of the nodes affects the performance of network. The network topology changes frequently due to mobility of nodes. In MANET each router has priori knowledge only of networks attached to it directly [1]. MANET is very attractive in tactical and military applications because of rapidly deployable and self-organizing configurability. Like tactical communications in a battlefield, where the environment is unfavorable, but fast network establishment self reconfiguration and security-sensitive operations are absolutely essential.

Data packets that successfully delivered to destinations that counted. It can be calculated as follows: Σ ( arrive time – send time ) / Σ Number of connections


A routing protocol is the protocols that specify how routers communicate with each other, [2] disseminating information that enables them to select routes between any two nodes on a computer network

illustration not visible in this excerpt

Figure 1: Categorization of Routing Protocols

Table Driven (proactive) Routing Protocol

The proactive routing protocol maintains its table in order to store routing information. Change in the network topology caused by anything need to be reflected to this table and propagate the updating information throughout the network [3].


Destination Sequenced Distance Vector (DSDV) is a proactive routing protocol. Each mobile node maintains a routing table in which all the possible destinations and the number of hops to them in the network are stored. The entries in the table are updated periodically. It assigns sequence number to routing entries. During communication route with highest sequence number is selected, in case of same sequence number higher metric value route is selected [3].

On-Demand (Reactive) Routing Protocol

On Demand-Driven Protocol routes only when desired by source node. When a node requires a route to a destination, it initiates a route discovery process within the network [2] [3].On demand routing protocols were designed with the aim of reducing control overhead, thus increasing bandwidth and conserving power at the mobile stations

In On-Demand routing protocols, the routes are created as and when it is needed. Once a route has been established in the network, it is maintained until either the destination becomes inaccessible or until the route is no longer used [1].

Existing on-demand re-active routing protocols are:

A. DSR (Dynamic Source Routing),
B. AODV (ad hoc On-Demand Distance Vector Routing)
C. AOMDV (Ad-Hoc On-Demand Multi-Path Distance Vector Routing)
D. LAR (Location Aided Routing)
E. TORA (Temporally-Ordered Routing Algorithm)
F. ABR (Associatively Based Routing)
G. LMR (Light-Weight Mobile Routing)
H. SSA (Signal Stability Based Adaptive Routing Algorithm)
I. CBRP (Cluster Based Routing)
J. RDMAR (Relative Distance Micro-Discovery Ad-Hoc Routing)
K. MSR (Multi-Path Source Routing)
L. ARA (Ant-Colony Based Routing Algorithm)



ISBN (eBook)
ISBN (Book)
File size
529 KB
Catalog Number
reinforcement learning network novel adaptive routing algorithm wireless ad-hoc




Title: A Reinforcement Learning Network based Novel Adaptive Routing Algorithm for Wireless Ad-Hoc Network