Applying nonlinear learning scheme on AntNet routing algorithm

Lalbakhsh, Pooia; Zaeri, Bahram; Fesharaki, Mehdi N.

doi:10.1109/nafips.2010.5548215

Cited by 1 publication

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consider an example of a network which consists of 9 nodes as shown in Figure 3. It is required to transmit the packet from source node n s (1) to destination node n d (2). At present the packet is at node 2.…”

Section: Ant Colony Optimization Algorithmsmentioning

confidence: 99%

“…The learning structure of AntNet consists of colonies of learning automata. In 2010, Pooia Lalbakhsh [2] have proposed to replace the previously defined automata structure with the non-linear one, modifies the reinforcement process without imposing overhead into the system. In this paper, in order to select the appropriate non-linear functions, the convergence rates are mathematically analyzed and the functions with better rates are replaced at the core of the system's learning cycle.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Performance Analysis of AntNet-LA Protocol for Ad-hoc Networks based on Disaster Area Mobility Model

Godbole¹

2013

REV-JEC

View full text Add to dashboard Cite

Availability of cheap positioning instruments like GPS receivers makes it possible for routing algorithms to use the position of nodes in an ad hoc mobile network. Regular position based routing algorithms fail to find a route from a source to a destination in some cases when the network contains nodes with irregular transmission ranges or they find a route that is much longer than the shortest path. On the other hand routing algorithms based on Ant Colony Optimization (ACO) find routing paths that are close to the shortest paths even if the nodes in the network have different transmission ranges. The drawback of these algorithms is the large number of messages that needs to be sent or the long delay before the routes are established. In this paper, we propose a novel protocol AntNet-LA which combines the idea of ACO with information about position of all nodes. In this technique the distance between the nodes is considered to transmit the packets, hence overcomes the drawbacks of AntNet algorithm which considers only cumulative probability for packet transmission. We compare performance of AntNet-LA with AntNet, Ad-hoc On Demand Distance Vector (AODV), Ad-hoc On Demand Multipath Distance Vector (AOMDV), Dynamic Source Routing (DSR) and Destination-Sequenced Distance-Vector Routing (DSDV) protocols. We also compare performance of AntNet-LA with distance-aware protocols such as Location Aided Routing (LAR), Geographical AODV GeoAODV and Position Based ANT colony optimization (PBANT).

show abstract

Section: Ant Colony Optimization Algorithmsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%