http://nova.newcastle.edu.au/vital/access/services/Feed ${session.getAttribute("locale")} 5 http://nova.newcastle.edu.au/vital/access/manager/Repository/uon:11192 Personal computers contribute significantly to the growing problem of electronic waste. Every computer, when finished with, must be stored, dumped, recycled, or somehow re-used. Most are dumped, at a huge cost to health and the environment, as their owners succumb to the desire to keep up with the ever-increasing power of new computers. Supercomputers and computer clusters provide more power than ordinary desktop and laptop computers, but they too are subject to rapid obsolescence. The authors have built a cluster of obsolete computers and have found that it easily outperforms a fairly standard new desktop computer. They explore how this approach can help to mitigate e-waste, and discuss the advantages and limitations of using such a system. 2012-08-08T02:24:14.208Z ]]> http://nova.newcastle.edu.au/vital/access/manager/Repository/uon:9911 This paper examines economic resource allocation through a number of auction types for a grid of ewaste computers. It examines the time to complete tasks and the energy usage of completing the tasks on a grid. A model of a simulated grid is developed and used to evaluate the resource allocation mechanisms. The simulated grid is calibrated to a real e-waste grid. The paper finds that the choice of auction method makes a substantial difference in the time to complete tasks and in total energy consumption. 2012-02-07T02:00:04.476Z ]]> http://nova.newcastle.edu.au/vital/access/manager/Repository/uon:8812 The resource allocation mechanism of a computing grid decides which tasks to allocate to which nodes for processing. Resource allocation is an interesting problem for any grid, but particularly so for a grid of heterogeneous computers, where the choice of one node over a functionally different node can affect the time or energy used in the computation. We propose a resource allocation metric that combines aspects of both energy usage and computational performance. On a simulated grid we compare this new metric with a number of traditional grid resource allocation metrics, and conclude that the choice of metric can have a significant impact on the time taken for a set of computations and the energy used in performing those computations. 2012-02-05T23:10:05.675Z ]]> http://nova.newcastle.edu.au/vital/access/manager/Repository/uon:7241 This paper examines economic resource allocation through a number of auction types for a grid of e-waste computers. It examines the time to complete tasks and the energy usage of completing the tasks on a grid. A model of a simulated grid is developed and used to evaluate the resource allocation mechanisms. The model is an agent-based simulation where by user agents submit tasks to node agents that process these tasks. We evaluate three types of resource-allocator agents which all use a type of auction. The auction types are batch auction, continuous double auction and a pre-processed batch auction. The pre-processed batch auction is developed to try to have the advantages of both the continuous double auction and the batch auction. The simulated grid is calibrated to a real e-waste grid where each node has a performance index. This grid is a test grid of eight nodes of heterogenous computer hardware and with differing computational ability and energy usage. We simulate the auction types under the same task input streams. We consider a task impulse response stream on energy usage and time to complete all tasks and a input stream step response. Finally we consider the three auction allocation mechanisms under a random task stream. The paper finds that the choice of auction method makes a substantial difference in the time to complete tasks and in total energy consumption. 2011-09-26T23:20:02.725Z ]]> http://nova.newcastle.edu.au/vital/access/manager/Repository/uon:9053 While most grids and clusters are built from uniform nodes of new hardware, the notion of a grid of obsolete computers rescued from the scrapheap appeals in several ways such as lower environmental and financial cost. Existing resource allocation mechanisms, in assuming that nodes are equally capable, equally power efficient and equally reliable, fail to cater for the distinct features of an e-waste grid. This paper presents a resource allocation mechanism explicitly designed with the features of such an e-waste grid in mind, proposes an objective function to assess the mechanism, and tests the mechanism against two existing resource allocation mechanisms. In simulated tests of the three mechanisms, the new mechanism performs better than the other two, particularly under heavy load. 2011-09-26T23:20:01.909Z ]]> http://nova.newcastle.edu.au/vital/access/manager/Repository/uon:5967 Agent based models are often computationally intensive. Historically the size and scope of agent based models has been limited by a lack of accessible high performance computing equipment. Parallel programming and clustering techniques allow for the creation of high performance computing environments at a relatively low cost. The low cost of clustering can be further reduced by utilising discarded computer workstations. In this paper we evaluate the programming and implementation of an agent-based model on a cluster of inexpensive re-used workstations. The workstations are re-used PCs in a Linux based cluster and we concentrate on a Java based clustering and grid solution JavaParty. The agent based model we use is a resource allocation model through an auction between sellers and buyers. The paper reviews the chosen cluster technology then analyses the effectiveness of the implementation of an agent-based model on a cluster. An existing agent based auction model is used to demonstrate the difference in performance, before and after the implementation of the model on a cluster. The methods used to modify the existing model are detailed. We compare the performance of the cluster implemented agent based auction model with the existing auction model, and compare their execution times. 2010-04-27T04:42:27.025Z ]]>