A DISTRIBUTED MODIFIED BIN BACKING FOR COMPUTING INFRASTRUCTURE USING SMARTPHONES
Publication Date : 30/03/2016
Daily night , so many smartphones are connected into a power socket for recharging the battery. Given the increasing computing efficiency of smartphones, these idle phones constitute a sizeable computing infrastructure which says that, an enterprise can tackle the combined computing power of such smartphones, to construct a distributed computing infrastructure. Such an infrastructure has the potential to reduce both the capital expenses and energy costs incurred by enterprises. Introduce a new framework CWC, which stands for computing while charging. CWC uses a server that connected to the Internet, for job scheduling on the smartphones and collecting the outputs from the computations. The scheduling algorithms on the server are lightweight, and thus, a rudimentary low cost PC will suffice. The scheduling algorithm should have the capacity to maintain the job working set which utilizes all resources available. The root of this scheduling issue is a d-capacity bin-packing problem where every system resource is represented by a capacity in the bin and the requirements of each waiting job are denoted by the d-capacities of an item in the input list. Implement and evaluate the model of CWC that handle a scheduling algorithm to minimize the make span of a set of computing tasks. Our CWC’s scheduler produces a make span which is 1.6x faster than other scheduling approaches by evaluating 8 android phones.
No. of Downloads :