Artificial life techniques for load balancing in computational grids

Abstract

Load balancing is a very important and complex problem in computational grids. A computational grid differs from traditional high performance computing systems in the heterogeneity of the computing nodes and communication links, as well as background workloads that may be present in the computing nodes. There is a need to develop algorithms that could capture this complexity yet can be easily implemented and used to solve a wide range of load balancing scenarios. Artificial life techniques have been used to solve a wide range of complex problems in recent times. The power of these techniques stems from their capability in searching large search spaces, which arise in many combinatorial optimization problems, very efficiently. This paper studies several wellknown artificial life techniques to gauge their suitability for solving grid load balancing problems. Due to their popularity and robustness, a genetic algorithm (GA) and tabu search (TS) are used to solve the grid load balancing problem. The effectiveness of each algorithm is shown for a number of test problems, especially when prediction information is not fully accurate. Performance comparisons with Min-min, Max-min, and Sufferage are also discussed. Crown

Increasing efficiency in Grid by using glow worm Algorithm

“…The difference of load balance in dynamic and static mode is that, in static mode, the decisions related to load balance are made in compiling time, while, in dynamic mode, decisions related to load balance are made in performing time. That is, in static mode, these decisions are made in the time of request for the source, but, in dynamic mode, the behavior of balancer varies according to the changes of parameters and policies [5]. Load balancing is divided into three groups: concentrated, non -concentrated and hierarchy.…”

“…In hierarchy method, the scheduler is organized in the hierarchy form [6] In load balance of concentrated method, many studies have been conducted. In order to balance the load, genetic algorithm has been used by [5], and its Simulation result has been compared with Min -Max and Max -Min algorithm. In [2], a new genetic algorithm has been presented by using resource fault occurrence history (RFOH) for certain scheduling in computing Grid.…”

Performance Evaluation of Grid using Random Scheduling

“…Issues such as task allocation and load balancing are major challenges for Grids [3]. In a computational Grid, the aim of resource management and scheduling is allocation of user defined jobs effectively by meeting deadlines and using all available resources [4].…”

Comparison Of Multi-Criteria Scheduling Techniques

“…It helps to keep the schedule up to date, however for large number of jobs this approach may be quite time consuming as was discussed in case of GORBA [17]. Works [1] and [18] propose local search based methods to solve Grid scheduling problems. The schedule is kept valid in time without total re-computation, however no experimental evaluation was presented in [1], and [18] does include resource changes but no dynamic job arrivals.…”

“…Works [1] and [18] propose local search based methods to solve Grid scheduling problems. The schedule is kept valid in time without total re-computation, however no experimental evaluation was presented in [1], and [18] does include resource changes but no dynamic job arrivals.…”