Optimization of workflow scheduling in Utility Management System with hierarchical neural network

Abstract

Grid computing could be the future computing paradigm for enterprise applications, one of its benefits being that it can be used for executing large scale applications. Utility Management Systems execute very large numbers of workflows with very high resource requirements. This paper proposes architecture for a new scheduling mechanism that dynamically executes a scheduling algorithm using feedback about the current status Grid nodes. Two Artificial Neural Networks were created in order to solve the scheduling problem. A case study is created for the Meter Data Management system with measurements from the Smart Metering system for the city of Novi Sad, Serbia. Performance tests show that significant improvement of overall execution time can be achieved by Hierarchical Artificial Neural Networks.

DMS Workflows Scheduling Concepts Comparison

“…Dynamic algorithms are necessary for adequate DMS operation, because workflows are generated at random timestamps and fluctuation of computing performance is constantly present [41]. Some papers propose solving similar problems by using artificial intelligence, like neural networks [39] and genetic algorithms [26]. On the other hand, some approaches are based on collecting information about Grid, executing predefined algorithms and making scheduling decisions [10,11,14].…”

A Study on Urban Road Traffic Safety Based on Matter Element Analysis

“…In the light of features of the urban road traffic safety, the analysis results achieved in the paper suggest the following: (i) on one hand, it is essential to improve the supervision and control measures of traffic safety. Urban road has been installed with advanced and modernized facilities, among which traffic control system is the key approach for urban road traffic management [ 18 ]. The traffic control system meets the needs of traffic control, monitoring, accessibility, and communication.…”

Optimal Workflow Scheduling in Critical Infrastructure Systems with Neural Networks

“…For this paper we have implemented five workflows which use different types of grid nodes. [15] All of them have two phases which are executed on different nodes so there is a constant migration of workflows between nodes. Figure 2 shows an example execution process of five types of nodes on grid nodes.…”