International Journal of Computer Applications (0975 – 8887) Volume 77 – No.9, September 2013 20 Implementation of Different Ant based Techniques for Network Load Analysis Nidhi Nayak T.I.T, Bhopal, India Bhupesh Gour, Ph. D Professor, Dept. of C.S.E. T.I.T, Bhopal, India Asif Ullah Khan, Ph. D Professor, Dept. of C.S.E. T.I.T, Bhopal, India ABSTRACT Network Load balancing is a technique of balancing at each node the number of packets received and the number of packets forward to the other node so that the chance of network congestion problem has been reduced and bandwidth is utilized. Although there are many techniques implemented for the balancing of nodes based on maintaining a routing table at each node and is updated as the packet get forward from that node. Ant Colony Optimization is one of the techniques used in the network for the balancing of number of packets at each node. Here in this paper is proposed a comparative study of different ant colony optimization techniques implemented for the analysis of the network load balancing. Here the ant based techniques are implemented are simulated for different conditions and on the basis of which proposed the best ant based techniques for the network load balancing. Keywords ACO, multi congestion, QOS, hierarchical routing, pheromone, particle velocity 1. INTRODUCTION Ant Colony Optimization (ACO) is a paradigm for designing met heuristic algorithms for combinatorial optimization problems [1]. The first algorithm which can be classified within this framework was presented 1991[21, 13] and, since then, many diverse variants of the basic principle have been reported in the literature. The necessary attribute of ACO algorithms is the combination of a priori information about the structure of a promising solution with posterior information about the structure of previously obtained good solution. An enhanced Ant colony optimization algorithm is used to resolve this difficulty in this paper. Ant Colony Optimization (ACO) is based on the behavior of ants seeking a path between their colony and a source of food, and proposed by Italy scholar M. Dorigo . The original idea is to solve a wider class of numerical problems, until now, various aspects are studied about the behavior of ants. ACO can be briefly introduced as follows. In the natural world, the behavior of ant is very simple; ants wander randomly to find food and then back to their colony while laying down pheromone trails. Once other ant’s find the path, they are likely to follow the trail, but not to keep wandering at random as before. Also the followed ants can reinforce the trail if they get the food successfully. Thus, when a good path is discovered by one ant from the colony to a food source, other ants have a larger probability to pursue that path, and constructive feedback eventually lead all the ants following a single path at last. With the rapid growth of information applications as well as the increasing bandwidth necessities, it is clear that optical networks scale to multi-layer and multi-domain. In the MRN/MLN optical transport network, traffic Engineering (TE) turns to be an essential requirement for Internet Service Provider (ISPs) to improve the utilization of the total network resources and to maintain a desired overall Quality of Service (QoS) with limited network resources. Load balancing technique may improve the performance and scalability of Internet to a great extent. Many researchers focal point on intra-domain load balancing which distributes traffic over multiple paths or server farms in a single domain. However, resources in inter-domain are more limited than intra-domain, thus load balancing is an effective strategy to avoid the resources congestion in inter-domain. Many multi- level and multi-domain route algorithms have been proposed aiming at load balancing to reduce the service request blocking, they only can generate the optimal solutions for some specific network, but original route algorithms (such as hierarchical routing algorithm) in multi level and multi- domain can't compute the global optimization path. 1.2 ANT COLONY OPTIMIZATION ACO [2, 3] is a class of algorithms, whose primary part, called Ant System, was originally planned by Colorni, Dorigo and Maniezzo [4, 5, and 6]. The main underlying idea, loosely inspired by the behavior of actual ants, is that of a parallel search over several productive computational threads based on local problem data and on a dynamic memory structure containing information on the quality of previously obtained result. The collective performance emerging from the interaction of the different search threads has proved effective in solving combinatorial optimization (CO) problems. Furthermore, an ACO algorithm includes two more mechanisms: trail disappearance and, optionally, daemon events. Trail vanishing decreases all trail value over time, in order to keep away from infinite accumulation of trails over some component. Daemon actions can be used to implement centralized actions which cannot be performed by solo ants, such as the invocation of a local optimization process, or the revise of global information to be used to decide whether to bias the search process from a non-local perspective [7]. More specifically, an ant is a simple computational agent, which iteratively constructs a explanation for the instance to resolve. Partial problem solutions are seen as states. At the center of the ACO algorithm lies a loop, where at every iteration, each ant move (performs a step) from a state i to another one y, consequent to a more complete fractional solution. That is, at each step s, each ant k computes a set AK s (i) of possible expansions to its present state, and move to one of these in probability. The probability allocation is specified as follows. For ant k, the probability piy k of stirring from state i to state y depends on the grouping of two values: · the attractiveness h(iy) of the progress, as compute by some heuristic signifying the a priori desirability of that move; the trail level t(iy) of the progress, signifying how capable it has been in the past to make that particular move: it represents therefore an a