Design of a web-based application of the coupled multi-agent system model and environmental model for watershed management analysis using Hadoop

Watersheds are modeled as coupled human and natural systems (CHNSs) by coupling a multi-agent system (MAS) model and an environmental model. The computational intensity and model accessibility of the coupled models are addressed in this paper. Multithreaded programming is used to improve the computa...

Full description

Saved in:
Bibliographic Details
Published in:Environmental modelling & software : with environment data news Vol. 70; pp. 149 - 162
Main Authors: Hu, Yao, Cai, Ximing, DuPont, Benjamin
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.08.2015
Subjects:
Accessibility
Apache Hadoop
Computation
computer software
Coupled human and natural system
Design engineering
Freshwater
humans
hydrologic models
Internet
Joining
Multi-agent system
Multiagent systems
Parallel computing
Running
watershed management
Watersheds
Web application
World Wide Web
Coupled human and natural system
Parallel computing
Multi-agent system
Web application
Apache Hadoop
ISSN:1364-8152
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Watersheds are modeled as coupled human and natural systems (CHNSs) by coupling a multi-agent system (MAS) model and an environmental model. The computational intensity and model accessibility of the coupled models are addressed in this paper. Multithreaded programming is used to improve the computational efficiency. As a result, the total running time of the coupled models is reduced by 80%, from one hour for a sequential run to twelve minutes with an eight-core desktop machine, running the model in parallel. To make the coupled models publicly accessible, a web-based application of the coupled models is implemented in the Hadoop-based cloud computing environment, which allows users to access and execute the model simultaneously without an increase in latency. This study presents a case of cyberinfrastructure design for complex watershed management problems, especially to parallelize computational models and provide model accessibility with user scalability. •Combine multithreaded programming with Hadoop-based cloud computing.•Reduce the runtime of the coupled models by 80% for the case study.•Enable the scalable execution of the coupled models via the network.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1364-8152
DOI:10.1016/j.envsoft.2015.04.011