SciAgents-an agent based environment for distributed, cooperative scientific computing

Problem solving using complex mathematical models of physical phenomena requires expert knowledge in a variety of fields of computer science, such as parallel computing and numerical methods. SciAgents is a problem-solving environment to allow these models to become truly easy to use for the application scientists, much like PC-based systems. It is based on the agent-oriented model of computing. In this paper, we discuss the design and architecture of SciAgents in the context of models based on partial differential equations. We present a set of artificial/computational intelligence techniques used by the cooperating agents that constitute SciAgents, which allows them to complete the program specification and to carry out the program execution with minimal need for user intervention. SciAgents permits the non-expert user to cost-effectively and easily develop software for solving complex mathematical models. It is scalable and allows for extensive reuse of existing software.

[1]  Nicholas R. Jennings,et al.  Integrating Intelligent Systems into a Cooperating Community for Electricity Distribution Management , 1994 .

[2]  Alexander Repenning,et al.  Agentsheets: a tool for building domain-oriented dynamic, visual environments , 1993 .

[3]  Victor R. Lesser,et al.  A retrospective view of FA/C distributed problem solving , 1991, IEEE Trans. Syst. Man Cybern..

[4]  Jeffrey C. Schlimmer,et al.  Software Agents: Completing Patterns and Constructing User Interfaces , 1993, J. Artif. Intell. Res..

[5]  Cathleen Stasz,et al.  Network Structures for Distributed Situation Assessment , 1980, IEEE Transactions on Systems, Man, and Cybernetics.

[6]  John R. Rice,et al.  Modeling with collaborating PDE solvers—Theory and practice , 1995 .

[7]  John R. Rice,et al.  Parallel ELLPACK: A Develoment and Problem Solving Environment for High Performance Computing Machines , 1991, Programming Environments for High-Level Scientific Problem Solving.

[8]  Timothy W. Finin,et al.  KQML as an agent communication language , 1994, CIKM '94.

[9]  Michael Wooldridge,et al.  Intelligence agents: Theory and practice , 1994 .

[10]  Nicholas R. Jennings,et al.  Intelligent agents: theory and practice , 1995, The Knowledge Engineering Review.

[11]  John R. Rice,et al.  Neuro-Fuzzy Systems for Intelligent Scientific Computation , 1995 .

[12]  Jeffrey D. McWhirter,et al.  Escalante: an environment for the rapid construction of visual language applications , 1994, Proceedings of 1994 IEEE Symposium on Visual Languages.

[13]  Michael R. Genesereth,et al.  Software agents , 1994, CACM.

[14]  Gul Agha,et al.  Research directions in concurrent object-oriented programming , 1993 .

[15]  Victor R. Lesser,et al.  Cooperative information-gathering: a distributed problem-solving approach , 1997, IEE Proc. Softw. Eng..

[16]  Ángel Viña,et al.  Guardian: A Prototype Intelligent Agent for Intensive-Care Monitoring , 1994, AAAI.

[17]  Anupam Joshi,et al.  To Learn or not to Learn? , 2019, What are Exhibitions for?.

[18]  Anupam Joshi,et al.  To Learn or Not do Learn , 1995, Adaption and Learning in Multi-Agent Systems.

[19]  John R. Rice,et al.  Solving elliptic problems using ELLPACK , 1985, Springer series in computational mathematics.

[20]  Edward Mascarenhas,et al.  Process mobility in distributed-memory simulation systems , 1993, WSC '93.

[21]  Randall Steeb,et al.  Strategies of Cooperation in Distributed Problem Solving , 1983, IJCAI.

[22]  Randall Davis,et al.  Frameworks for Cooperation in Distributed Problem Solving , 1988, IEEE Transactions on Systems, Man, and Cybernetics.

[23]  John R. Rice,et al.  Processing PDE Interface Conditions II , 1994 .

[24]  Elias N. Houstis,et al.  The use of neural networks to support "intelligent" scientific computing , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[25]  Yoav Shoham.  Agent-Oriented Programming , 1993, Artif. Intell..