A Linear Programming Driven Genetic Algorithm for Meta-Scheduling on Utility Grids

TL;DR

This paper introduces a novel LP/IP-based model and a hybrid LPGA algorithm that optimizes meta-scheduling in utility grids, reducing costs and contention among users.

Contribution

It presents a new integrated LP/IP and genetic algorithm approach for efficient, cost-minimizing meta-scheduling in utility grids, outperforming traditional methods.

Findings

LPGA achieves lower processing costs than existing algorithms.

The proposed method has negligible time overhead.

Simulation results validate the effectiveness of the approach.

Abstract

The user-level brokers in grids consider individual application QoS requirements and minimize their cost without considering demands from other users. This results in contention for resources and sub-optimal schedules. Meta-scheduling in grids aims to address this scheduling problem, which is NP hard due to its combinatorial nature. Thus, many heuristic-based solutions using Genetic Algorithm (GA) have been proposed, apart from traditional algorithms such as Greedy and FCFS. We propose a Linear Programming/Integer Programming model (LP/IP) for scheduling these applications to multiple resources. We also propose a novel algorithm LPGA (Linear programming driven Genetic Algorithm) which combines the capabilities of LP and GA. The aim of this algorithm is to obtain the best metaschedule for utility grids which minimize combined cost of all users in a coordinated manner. Simulation results show that our proposed integrated algorithm offers the best schedule having the minimum processing cost with negligible time overhead.