Helping ants for adaptive network routing

Soltani, Azadeh; Akbarzadeh-T, Mohammad-R.; Naghibzadeh, Mahmoud

doi:10.1016/j.jfranklin.2006.02.007

Cited by 19 publications

(14 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance of AntNet routing detoriates as network size or link density is elevated [4], [5], [6]. It is robust to changes in the topology of network and confluence to a good solution.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Self-Adaptive Intelligent Routing in Dynamic WSN using Natural Inspired Computing

Mr.

Phanikumar

2017

IOP Conf. Ser.: Mater. Sci. Eng.

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

“…The formulation of  is expressed as in (6). (6) Where C 1 +C 2 >4, then the Kennedy and Eberhart's original PSO for velocity updating becomes (7) Clearly, the constriction factor  in (7) can be seen as a damping factor that controls the magnitude of the flying velocity of a particle.…”

Section: Proposed Systemmentioning

confidence: 99%

Self-Adaptive Intelligent Routing in Dynamic WSN using Natural Inspired Computing

Mr.

Phanikumar

2017

IOP Conf. Ser.: Mater. Sci. Eng.

View full text Add to dashboard Cite

“…The algorithm proposed in [19] utilized the ant/packet ratio to improve the throughput and decrease the average delay. Helping ants has been introduced in [20] as a new type of the used Ants to increase cooperation among neighboring nodes, thereby reducing AntNet algorithm's convergence time. In [21] a method for handling loss of ants and avoids retransmission of lost packets by reserving resources at nodes, was presented, which in turn enhances the performance.…”

Section: Related Workmentioning

confidence: 99%

Improving the performance of TAntNet-2 by using multi forward scouts

Ghazy

Hefny

2015

2015 Tenth International Conference on Computer Engineering &Amp; Systems (ICCES)

View full text Add to dashboard Cite

Dynamic Traffic Routing System is an important intelligent transport system that is used to direct vehicles to good routes and consequently reduce congestion on the road network. The performance of dynamic routing system depends on a dynamic routing algorithm. AntNet algorithm is a routing algorithm inspired from the foraging behavior of ants. TAntNet is a family of dynamic routing algorithms that uses a threshold travel time to enhance the performance of AntNet algorithm when applied to traffic road networks. This paper presents new improvements on TAntNet algorithms. The new improving TAntNet algorithm uses Multi forward agents instead of one compared with AntNet and TAntNet-2. The new technique saves the discovered routes of each of the forward agents and the corresponding backward ant uses the best of them. Experiments showed better performance for the proposed new mechanism of launching multi forward agents for each single agent compared with the old mechanisms of launching only one forward agent for each backward agent.

show abstract

“…Although decreasing the travelling entities over the network, results in decreasing the overall delay, two main drawbacks are arose: first, the overall throughput is decreased; secondly, it deteriorates system learning, convergence speed, network awareness, and adaptability. Another interesting approach is reported in [11], which uses a new kind of ants called helping ants to improve cooperation among neighboring nodes. Helping ants are responsible for distributing routing information to the neighboring nodes of a source node, according to the corresponding backward ant's routing information.…”

Section: Standard Antnet and The Related Workmentioning

confidence: 99%

AntNet with Reward-Penalty Reinforcement Learning

Lalbakhsh

Zaeri

Lalbakhsh

et al. 2010

2010 2nd International Conference on Computational Intelligence, Communication Systems and Networks

View full text Add to dashboard Cite

The paper deals with a modification in the learning phase of AntNet routing algorithm, which improves the system adaptability in the presence of undesirable events. Unlike most of the ACO algorithms which consider reward-inaction reinforcement learning, the proposed strategy considers both reward and penalty onto the action probabilities. As simulation results show, considering penalty in AntNet routing algorithm increases the exploration towards other possible and sometimes much optimal selections, which leads to a more adaptive strategy. The proposed algorithm also uses a selfmonitoring solution called Occurrence-Detection, to sense traffic fluctuations and make decision about the level of undesirability of the current status. The proposed algorithm makes use of the two mentioned strategies to prepare a selfhealing version of AntNet routing algorithm to face undesirable and unpredictable traffic conditions.

show abstract

Helping ants for adaptive network routing

Cited by 19 publications

References 11 publications

Self-Adaptive Intelligent Routing in Dynamic WSN using Natural Inspired Computing

Self-Adaptive Intelligent Routing in Dynamic WSN using Natural Inspired Computing

Improving the performance of TAntNet-2 by using multi forward scouts

AntNet with Reward-Penalty Reinforcement Learning

Contact Info

Product

Resources

About