When using the computing resources of workstation networks by parallel programs dynamic load balancing is an important task. We describe a distributed, local migration algorithm, called precomputation-based load balancing, which treats this problem efficiently. Its performance is empirically demonstrated solving the satisfiability problem on an heterogenous network of 12 workstations. We discuss the influence of processor weighting and parameter adaption on speedup and idle times.

An algorithm, called PLB is introduced, which redistributes workload in a processor network N in order to supply every processor of N with (about) the same amount of workload. PLB is defined in its basic form for trees, but can be extended to other topologies. The redistribution is done locally on the basis of information of over- or underload in subnetworks of N . We show, that PLB performs O(\Delta) steps, only, where \Delta denotes the diameter of N , and in the average case at most four times as many workload has to be migrated in complete binary trees compared to clique networks, the best possible networks. We describe an implementation of PLB and present experimental results when solving the Boolean satisfiability problem, demonstrating that PLB performs very well in practice.

Abstract—Grid networks provide the ability to perform higher throughput computing by taking advantage of many networked computer’s resources to solve large-scale computation problems. As the popularity of the Grid networks has increased, there is a need to efficiently distribute the load among the resources accessible on the network. In this paper, we present a stochastic network system that gives a distributed load-balancing scheme by generating almost regular networks. This network system is self-organized and depends only on local information for load distribution and resource discovery. The in-degree of each node is refers to its free resources, and job assignment and resource discovery processes required for load balancing is accomplished by using fitted random sampling. Simulation results show that the generated network system provides an effective, scalable, and reliable load-balancing scheme for the distributed resources accessible on Grid networks.

Many large web sites get more than 100 million hits everyday. They need a scalable web server system that can provide better performance to all the clients that may be in dierent geographical regions. Higher delays and losses are common on WAN links. To provide a better service to all the clients, it is natural to have fully replicated web server clusters in dierent geographical regions. In such an environment, one of the most important issue is that of server selection (and load balancing). The client's request should be directed to one of the servers in a way that the response can be quick. We assume that web servers are functionally homogeneous, i.e. any one of them can serve any client request. Another important point is that this system should not require modication of any client side component or existing standard protocol.

Abstract—Grid networks provide the ability to perform higher throughput computing by taking advantage of many networked computer’s resources to solve large-scale computation problems. As the popularity of the Grid networks has increased, there is a need to efficiently distribute the load among the resources accessible on the network. In this paper, we present a stochastic network system that gives a distributed load-balancing scheme by generating almost regular networks. This network system is self-organized and depends only on local information for load distribution and resource discovery. The in-degree of each node is refers to its free resources, and job assignment and resource discovery processes required for load balancing is accomplished by using fitted random sampling. Simulation results show that the generated network system provides an effective, scalable, and reliable load-balancing scheme for the distributed resources accessible on Grid networks.

Load distribution is a well known critical problem in every distributed system. From operating systems to agent oriented applications it is not difficult to find cases where processing nodes are overloaded when, at the same time, other peers present low levels of activity. In agent oriented applications, where the appeal to cooperation is almost a constant event, these unbalanced situations may generate serious cases of contention, deadlock or simply large idle times. The implementation of load distribution strategies in a distributed system may help significantly to improve its overall performance and reduce effectively such undesirable situations. In order to study the effects of different load distribution policies in agent based applications a generic load distribution simulation system was design and implemented. The system allows the

Abstract- The importance of social network applications on mobile devices is becoming more popular. The mobile presence service is a vital component in social network through which it handles every mobile user information, such as the network address, present status and GPS location, and also updates the user online buddies with the information frequently. When plenty updates occur continuously more number of messages are sent to the servers, this may lead to scalability problem in large scale mobile presence services. To address this, we use a server architecture known as PresenceCloud, which supports large scale social network applications. In day to day life, the number of mobile users of social network applications is increasing rapidly, due to this the response time from the server may be decreased by getting more requests from the mobile users. In our proposed method we are introducing an algorithm for Load balancing, which allocate the work to the clusters of presence server. The load balancing algorithm is Transaction-Least-Work-Left(TLWL), used to allocate work to least values of the servers. This algorithm reduces the response time by distributing the requests to all other servers. Keywords- Distributed Presence servers, cloud computing, social networks, load balancing, mobile presence services I.