QUT ePrints

A Generic Adaptive Simulation Framework For Outcome-Driven Collaborative Planning For Sustainability

Caldeweyher, Daniel, Pham, Binh, & Zhang, Jinglan (2007) A Generic Adaptive Simulation Framework For Outcome-Driven Collaborative Planning For Sustainability. In SimTecT2007 - Simulation Industry Association of Australia Conference, June 4 - 7, 2007, Brisbane, Queensland, Australia.

Abstract

With the rapidly increasing world population, the need for sustainable planning and management of depletable as well as renewable natural resources is greater than ever. Accurately predicting the impacts of Natural Resource Management decisions across multiple temporal and spatial scales can significantly aid decision makers with planning for sustainability. Current simulation as well as decision making tools however do not explicitely supports any of the emerging trends in sustainable planning; participatory planning and backcasting. Backcasting is a methodology for planning under uncertainty that is particularly helpful when problems at hand are complex and when present trends are part of the problems. It is process of envisioning a desired future state, analysing the present, and developing sustainable strategies of moving from the present to the future. The concept of this sounds simple enough in theory; however, modelling such goal-oriented behaviour in an open environment is complex and has yet to be explored. As for participatory planning, most tools lack collaboration support, because are single user and single use, meaning, simulation runs are effectively independent of each other. This prevents or hinders the reuse and sharing of simulation results, therefore making inefficient use of available resources, and more importantly, wasting valuable information and gained knowledge. A generic, adaptive multi-user simulation framework and sustainable planning support system is being developed to address these shortcomings of current simulation and planning tools. The simulation framework enables collaboration by providing multi-user support and implicit knowledge-sharing between simulations and users. Backcasting is achieved through outcome-driven scenario formulation and the use of recursive simulation for optimisation. In addition, due to the sharing and reusing of information, the system has been design to be capable of ‘learning’, thus improving its simulation accuracy and decision-making capacity over time. For example, recording which user made which decisions under what circumstances allows the system over time to identify patterns and preference. While it may not be possible to publicly share this knowledge for reasons of privacy, intellectual property etc., it could be used for training autonomous decision-making agents to reduce user involvement, and to give better recommendations to the user, e.g. “under similar conditions x% of the users made decision a, and y% made decision b”. The framework is required to seamlessly and dynamically integrate various technologies (incl. cellular automata, multi agent system, With the rapidly increasing world population, the need for sustainable planning and management of depletable as well as renewable natural resources is greater than ever. Accurately simulating the impacts of Natural Resource Management decisions across multiple temporal and spatial scales under consideration of various indirectly related factors can significantly aid decision makers with planning for sustainability. A generic adaptive multi-user simulation framework is being developed to address the shortcomings of current simulation tools to provide for collaboration and knowledge sharing between users and across individual simulations, allowing for continuous improvement of the resource and knowledge base. The general infrastructure of the system has been implemented based on enterprise application architecture and tested successfully. It is found to be a suitable design to provide simulation and optimisation capabilities to third-party decision support systems.

Impact and interest:

Citation countsare sourced monthly from Scopus and Web of Science® citation databases.

These databases contain citations from different subsets of available publications and different time periods and thus the citation count from each is usually different. Some works are not in either database and no count is displayed. Scopus includes citations from articles published in 1996 onwards, and Web of Science® generally from 1980 onwards.

Citations counts from the Google Scholar™ indexing service can be viewed at the linked Google Scholar™ search.

Full-text downloads:

266 since deposited on 19 Feb 2008
21 in the past twelve months

Full-text downloadsdisplays the total number of times this work’s files (e.g., a PDF) have been downloaded from QUT ePrints as well as the number of downloads in the previous 365 days. The count includes downloads for all files if a work has more than one.

ID Code: 12517
Item Type: Conference Paper
Additional Information: The contents of this conference can be freely accessed online via the publisher’s web page (see hypertext link).
Additional URLs:
ISBN: 0977525724
Subjects: Australian and New Zealand Standard Research Classification > INFORMATION AND COMPUTING SCIENCES (080000) > ARTIFICIAL INTELLIGENCE AND IMAGE PROCESSING (080100) > Simulation and Modelling (080110)
Divisions: Past > QUT Faculties & Divisions > Faculty of Science and Technology
Copyright Owner: Copyright 2007 (please consult author)
Deposited On: 19 Feb 2008
Last Modified: 29 Feb 2012 23:35

Export: EndNote | Dublin Core | BibTeX

Repository Staff Only: item control page