Abstract—The efficiency of sensor networks depends on the coverage of the monitoring area. Although, in general, a sufficient number of sensors are used to ensure a certain degree of redundancy in coverage, a good sensor deployment is still necessary to balance the workload of sensors. In a sensor network with locomotion facilities, sensors can move around to self-deploy. The movement-assisted sensor deployment deals with moving sensors from an initial unbalanced state to a balanced state. Therefore, various optimization problems can be defined to minimize different parameters, including total moving distance, total number of moves, communication/computation cost, and convergence rate. In this paper, we first propose a Hungarian-algorithm-based optimal solution, which is centralized. Then, a localized Scan-based Movement-Assisted sensoR deploymenT method (SMART) and its several variations that use scan and dimension exchange to achieve a balanced state are proposed. An extended SMART is developed to address a unique problem called communication holes in sensor networks. Extensive simulations have been done to verify the effectiveness of the proposed scheme.

The World Wide Web (WWW) has recently become a very popular facility for the dissemination of information. As a result of this popularity, it is experiencing rapidly increasing traffic load. Single machine servers cannot keep pace with the ever greater load being placed upon them. To alleviate this problem, we have implemented a distributed Web server group. The server group can effectively balance request load amongst its members (within about 10% of optimal), and client response time is no worse than in the single server case. Client response time was not improved because the measured client traffic consumed all available network throughput. The distributed operation of the server groups is completely transparent to standard Web clients. This research is sponsored in part by the Wright Laboratory, Aeronautical SystemsCenter, Air Force Materiel Command, USAF, and the Advanced Research Projects Agency (ARPA) under grant F33615-93-1-1330. The US Government is authorized to reproduce and...

Parallel application can be divided into tasks that can be executed simultaneously. A mechanism for assigning these tasks to the processors is required. The objective is to minimize the overall execution time of a single application running in parallel on a multicomputer system. We propose a new dynamic load balancing algorithm based on the diffusion approach which employs overlapping balancing domains (a processor and its neighbors) to achieve global balancing. Since current diffusion methods consider discrete units, the algorithms may produce solutions which, although they are locally balanced, prove to be globally unbalanced. Our method solves this problem taking into account the load maximum difference between two processors within each domain, providing a more efficient load balancing process. This method is performed in a distributed fashion and can easily be scaled to support highly parallel machines. The algorithm has been applied to different interconnection networks and the results obtained are very encouraging I.-

In this paper we present discuss the task assignment problem for distributed systems. We also show how this problem is very similar to that of clustering transactions for load balancing purposes and for their efficient execution in a distributed environment. The formalization of these problems in terms of a graph theoretic representation of a distributed program, or of a set of related transactions, is given. The cost function which needs to be minimized by an assignment of tasks to processors or of transactions to clusters is detailed, and we survey related work, as well work on the dynamic load balancing problem. Since the task assignment problem is NP-hard, we present three novel heuristic algorithms that we have tested for solving it and compare them to the well-known greedy heuristic. These novel heuristics use neural networks, genetic algorithms and simulated annealing. Both the resulting performance and the computational cost for these algorithms is evaluated on a large number o...

This paper presents techniques for dynamic load balancing in heterogeneous computing environments. That is, the techniques are designed for sets of machines with varying processing capabilities and memory capacities. These methods can also be applied to homogenous systems in which the effective compute speed or memory availability is reduced by the presence of other programs running outside the target computation. To handle heterogeneous systems, a precise distinction is made between an abstract quantity of work, which might be measured as the number of iterations of a loop or the count of some data structure, and the utilization of resources, measured in seconds of processor time or bytes of memory, required by that work. Once that distinction is clearly drawn, the modifications to existing load balancing techniques are fairly straight-forward. The effectiveness of the resulting load balancing system is demonstrated for a large-scale particle simulation on a network of heterogeneous P...

This paper presents a scalable hierarchical approach for dynamic load balancing in large parallel and distributed systems, which is not only different from classical centralized and decentralized approaches, but also different from known hierarchical schemes. The present system, which is implemented as a prototype on the shared-nothing supercomputer architecture Intel Paragon XP/S, uses multi-level control for dynamic load balancing as well as for the communication manager. The control tree consists of three different components: the root component, the inner components and the leaf components. The hierarchical load balancer uses non-preemptive as well as preemptive process migration to balance load between the nodes of the parallel/distributed system. The performance of the system has been evaluated by two existing real world applications: a computational fluid dynamic program and a parallel raytracer. 1 Introduction As a result of the evolutionary advancements in computation and c...

Efficiently scheduling parallel tasks on to the processors of a shared-memory multiprocessor is critical to achieving high performance.Given perfect information at compile-time, astatic scheduling strategy can produce an assignment of tasks to processorsthat ideally balances the load among the processors while minimizing the run-time scheduling overhead and the average memory referencing delay. Since perfect information is seldom available, however, dynamic scheduling strategies distribute the task assignment function to the processors by having idle processors allocate work to themselves from a shared queue. While this approach can improvethe load balancing compared to static scheduling,the time required to access the shared work queue adds directly to the overall execution time.To overlap the time required to dynamically schedule tasks with the execution of the tasks, we examine a class of Self-Adjusting Dynamic Scheduling (SADS) algorithms that centralizes the assignment of tasks to processors. These algorithms dedicate a single processor of the multiprocessor to perform a novel on-line branch-and-bound technique that dynamically computes partial schedules based on the loads of the other processors and the memory locality (affinity) of the tasks and the processors. Our simulation results show that this centralized scheduling outperforms self-scheduling algorithms even when using only a small number of processors.

This paper presents a new approach that uses neural networks to predict the performance of a number of dynamic decentralized load balancing strategies. A distributed multicomputer system using any distributed load balancing strategy is represented by a unified analytical queu-ing model. A large simulation data set is used to train a neural network using the back–propa-gation learning algorithm based on gradient descent. The performance model using the predict-ed data from the neural network produces the average response time of various load balancing algorithms under various system parameters. The validation and comparison with simulation data show that the neural network is very effective in predicting the performance of dynamic load balancing algorithms. Our work leads to interesting techniques for designing load balanc-ing schemes (for large distributed systems) that are computationally very expensive to simulate. One of the important findings is that performance is affected least by the number of nodes, and most by the number of links at each node in a large distributed system. 1

Autonomous Decentralized Systems concurrently work on different types of jobs which consist of interdependent tasks ("steps"). Steps are characterized by their service requirements. It is the load balancing problem to increase the system throughput by reducing contention between steps accessing the same resources. In this paper, we propose a dynamic decentralized look-ahead scheduling algorithm and a cooperation protocol. The goal is to utilize information about the internal job structure concerning future service requirements and system state information for dynamically arranging schedules such that jobs can take advantage of inevitable waiting times of others. We evaluated the proposed algorithm by simulation. Waiting time reductions in sample configurations of up to 75% for single job types at the expense of only slightly worse response times for other job types compared to systems not applying the algorithm proof the algorithm's success. 1 Introduction Autonomous Decentralized Sys...

In distributed systems, servers offer their service to independent clients. It is the load balancing problem to assign jobs to servers. Dynamic load balancing has great potential to outperform static policies in spite of the overhead for measurement and system state information exchange. Problems arise if the system state information used as criterion for the job assignment is not up to date. This happens if the mean time between system state changes and the communication delay are in the same order of magnitude. We propose two different distributed cooperation algorithms that enable servers to calculate the current system state by evaluating minimum client information without additional message exchange. Results from simulation show that the algorithms perform well especially in highloaded systems. The average job waiting time is compared to a lower bound derived from the M/D/n queuing model and "random routing" as an upper bound. Problems arise with dynamic policies if the system st...