EcoSimNet: A Multi-Agent System for Ecological Simulation and Optimization

Ecological models may be very complex due to the large number of physical, chemical, biological processes and variables and their interactions, leading to long simulation times. These models may be used to analyse different management scenarios providing support to decision-makers. Thus, the simultaneous simulation of different scenarios can make the process of analysis and decision quicker, provided that there are mechanisms to accelerate the generation of new scenarios and optimization of the choices between the results presented. This paper presents a new simulation platform --- EcoSimNet --- specially designed for environmental simulations, which allows the inclusion of intelligent agents and the introduction of parallel simulators to speed up and optimize the decision-making processes. Experiments were performed using EcoSimNet computational platform with an agent controlling several simulators and implementing a parallel version of the simulated annealing algorithm for optimizing aquaculture production. These experiments showed the capabilities of the framework, enabling a fast optimization process and making this work a step forward towards an agent based decision support system to optimize complex environmental problems.

[1]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[2]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[3]  Fred W. Glover,et al.  Future paths for integer programming and links to artificial intelligence , 1986, Comput. Oper. Res..

[4]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[5]  D. Janaki Ram,et al.  Parallel Simulated Annealing Algorithms , 1996, J. Parallel Distributed Comput..

[6]  R. Kates Climate Change 1995: Impacts, Adaptations, and Mitigation , 1997 .

[7]  Richard S. Sutton,et al.  Introduction to Reinforcement Learning , 1998 .

[8]  Michael N. Huhns,et al.  Multiagent systems and societies of agents , 1999 .

[9]  Michael Wooldridge,et al.  Multiagent Systems: A Modern Approach to Distributed Artificial Intelligence , 1999 .

[10]  Gerhard Weiss,et al.  Multiagent systems: a modern approach to distributed artificial intelligence , 1999 .

[11]  Sašo Džeroski,et al.  Applications of symbolic machine learning to ecological modelling , 2001 .

[12]  Jon Grant,et al.  Mathematical modelling to assess the carrying capacity for multi-species culture within coastal waters , 2003 .

[13]  Luís Paulo Reis,et al.  Agent-Based Simulation of Ecological Models , 2004 .

[14]  Manoj Kumar Tiwari,et al.  Hybrid tabu-simulated annealing based approach to solve multi-constraint product mix decision problem , 2005, Expert Syst. Appl..

[15]  Luís Paulo Reis,et al.  ECOLANG - A communication language for simulations of complex ecological systems , 2005 .

[16]  P. Duarte,et al.  How does Estimation of Environmental Carrying Capacity for Bivalve Culture Depend upon Spatial and Temporal Scales , 2005 .

[17]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[18]  Pedro Duarte,et al.  Different modelling tools of aquatic ecosystems: A proposal for a unified approach , 2006, Ecol. Informatics.

[19]  P. Negro,et al.  Picoplanktonic cyanobacteria in different Adriatic brackish environments , 2007 .

[20]  Luís Paulo Reis,et al.  Intelligent Farmer Agent for Multi-agent Ecological Simulations Optimization , 2007, EPIA Workshops.

[21]  P. Duarte,et al.  Management oriented mathematical modelling of Ria Formosa (South Portugal) , 2007 .