Chunsheng Li

An agent-based framework for petroleum information services from distributed heterogeneous data resources

For making good decisions in the area of petroleum production, it is becoming a big problem how to timely gather sufficient and correct information, which may be stored in databases, data files, or on the World Wide Web. In this paper, Gaia methodology and Open Agent Architecture were employed to contribute a framework to solve above problem. The framework consists of three levels, namely, role mode, agent type, and agent instance. The model with five roles is analyzed. Four agent types are designed Six agent instances are developed for constructing the system of petroleum information services. The experimental results show that all agents in the system can work cooperatively to organize and retrieve relevant petroleum information. The successful implementation of the framework shows that agent-based technology can significantly facilitate the construction of complex systems in distributed heterogeneous data resource environment.

A Practical Framework for Agent-Based Hybrid Intelligent Systems

The design and development of hybrid intelligent systems are difficult because there are many interactions between various components. Existing software development techniques cannot manage those complex interactions efficiently as those interactions may occur at unpredictable times, for unpredictable reasons, between unpredictable components. In this paper, we contribute a multi-agent framework to organize those components and interactions. The framework consists of user interface, decision making, knowledge discovering, information management facilitators, and distributed heterogeneous data resources. We employ the middle agent concept to match task requesters with specific intelligent agents. We demonstrate the potentials of the framework by case study and present theoretical and empirical evidence that our framework is available and robust.

An agent-based curve-digitizing system for well-logging data management

To permanently keep and efficiently use data implied in curves on well-logging parameter graphs is becoming very important in the petroleum industry. In this paper, we contribute a system based on multi-agent technology to digitize well-logging curves and store the data into the Oracle database by means of an agent-based database broker. We employed some ideas of Gaia and Open Agent Architecture (OAA) to analyze and design the system. We applied the line adjacency graph (LAG) data structure to develop the image-compressing agent, which compresses image files with great efficiency. According to the characteristics of the well-logging parameter graph, the digitizing algorithms based on a centimeter grid of coordinates, which perfectly rectify the distortion of the parameter graph, are proposed for implementing the digitizing agent. We applied middleware agents to operate databases in the uniform Database-based Agent Communication Language (DBACL). The experimental results show that all agents in the system can work cooperatively.

A Ring-Based Architectural Model for Middle Agents in Agent-Based System

In agent-based systems, the performance of middle agents not only relies on the matchmaking algorithms employed by them, but also the architecture that organizes them with suitable organizational structure and coordination mechanism. In this paper, we contribute a framework and develop a couple of middle agents with logical ring organizational structure to match requester agents with service provider agents. The middle agent is of the features of proliferation and self-cancellation according to the sensory input from its environment. The token-based coordination mechanism of middle agents is designed. Two kinds of middle agents, namely, host and duplicate, are designed for promoting the scalability and robustness of agent-based systems. We demonstrate the potentials of the architecture by case study.

MAHIS: an agent-oriented methodology for constructing dynamic platform-based HIS

Hierarchical structure, reusable and dynamic components, and predictable interactions are distinct characteristics of hybrid intelligent systems (HIS). The existing agent-oriented methodologies are deficient in HIS construction because they did not take into account the characteristics of HIS. In this paper, we propose a Methodology for constructing Agent-based HIS (MAHIS). MAHIS consists of eight models: Hybrid Strategy Identification Model, Organization Model, Task Model, Agent Model, Expertise Model, Coordination Model, Reorganization Model, and Design Model. The Reorganization Model is the key model to support dynamic platform-based HIS. It consists of category role, group roles, virtual organization role, and dynamics rules. This model describes the characteristics of HIS with virtual organization, category, and group perspectives. Some previously developed agents can be reused by means of involving them in a new virtual organization dynamically. The output of the Reorganization Model is the specification of the dynamic platform which comprises middle agents and makes all agents and agent groups hierarchical and dynamic.

Theoretical evaluation of ring-based architectural model for middle agents in agent-based system

Ring-based architectural model is usually employed to promote the scalability and robustness of agent-based systems. However there are no criteria for evaluating the performance of ring-based architectural model. In this paper, we introduce an evaluation approach to comparing the performance of ring-based architectural model with other ones. In order to evaluate ring-based architectural model, we proposed an application-based information-gathering system with middle agents, which are organized with ring-based architectural model and solve the matching problem between service provider agents and requester agents. We evaluate the ring-based architectural model with performance predictability, adaptability, and availability. We demonstrate the potentials of ring-based architectural model by the results of evaluation.

An agent-based intelligent system for information gathering from World Wide Web environment

To use the vast amount of information efficiently and effectively from Web sites is very important for making informed decisions. There are, however, still many problems that need to be overcome in the information gathering research arena to enable the delivery of relevant information required by users. In this paper, an information gathering system is develop by means of multiple agents to solve those problems. We employed some ideas of Gaias methodology and an open agent architecture to analyze and design the system. The system consists of a query preprocessing agent, information retrieval agent, information filtering agent, and information management agent. The filtering agent is trained with categorized documents and can provide users with the necessary information. The experimental results show that all agents in the system can work cooperatively to retrieve relevant information from the World Wide Web environment.

An Agent-Based Hybrid Intelligent System for Financial Investment Planning

The design and development of hybrid intelligent systems such as financial investment planning are difficult because they have a large number of components that have many interactions. Existing software development techniques cannot manage those complex interactions efficiently as those interactions may occur at unpredictable times, for unpredictable reasons, between unpredictable components. In this paper, we employed fussy algorithms, genetic algorithms, etc. to solve complicated financial portfolio management. The system starts with the financial risk tolerance evaluation based on fussy algorithms. Asset allocation, portfolio selections, interest predictions, and ordered weighted averaging can be conducted by using hybrid intelligent techniques. The planning agent in the system can easily access all intelligent processing agents, including financial risk tolerance assessment agent, asset allocation agent, portfolio selection agents, interest prediction agents, and decision aggregation agent. Overall system robustness is facilitated.

A platform for dynamic organization of agents in agent-based systems

In most agent-based systems, different middle agents are employed to increase their flexibility. However, there are still three issues remain unsolved. In centralized architecture with single middle agent, the middle agent itself is a bottleneck and suffers from single point failure; middle agents in distributed architecture lack capability of dynamic organization of agents; The reliability is not strong because of the single point failure and lack of effective architecture. We introduce a platform with ring architectural model to solve all above problems. In the platform, multiple middle agents are dynamically supported for solving the first problem. For solving the second problem, middle agents dynamically manage the registration and cancellation of service provider agents and application teams, each of which includes a set of closely interacting requester agents to complete an independent task. Redundancy middle agent technique is proposed for solving the third problem. All middle agents are of the feature of proliferation and self-cancellation according to the sensory inputs from their environment. For organizing the middle agents effectively, a ring architectural model is proposed. We demonstrate the applicability of the platform by its application and present experimental evidence that the platform is flexible and robust.

An approach to digitizing and managing well-logging parameter graphs with agent-based perspective

The curves on well-logging parameter graph are very important to reservoir description. But how to keep the parameter graphs permanently and use the data implied in those curves efficiently are still open problems in petroleum industry. In this paper, we contribute an approach to digitizing well log curves and storing the digitized information into Oracle database or data file server with multi-agent perspective. We employed Gaia methodology and open agent architecture to analyze and design the system. According to the characteristics of the well-logging parameter graphs, we implement the SCTR (Scanning, Compressing, Tracing, and Rectifying) algorithms with four agents to digitize well log curves. Two data management agents are developed for operating database and data files in uniform agent communication language. The experimental results show that this approach is effective.