Ana Petric

The crocodileagent: research for efficient agent-based cross-enterprise processes

The Trading Agent Competition (TAC) is an international forum which promotes high-quality research regarding the trading agent problem One of the TAC competitive scenarios is Supply Chain Management (SCM) where six agents compete by buying components, assembling PCs from these components and selling the manufactured PCs to customers The idea of TAC SCM is the development of agent-based architectures that implement wide-applicable business strategies which efficiently manage cross-enterprise processes In this paper, we analyze the TAC SCM environment and describe the main features of the CrocodileAgent, our entry in the TAC SCM Competition.

Software Agents in New Generation Networks: Towards the Automation of Telecom Processes

Today, there is a wide variety of telecom services available provided by a number of competing stakeholders in the telecom environment. Consequently, consumers in such an environment require efficient mechanisms to match their demands (requested services) to supplies (available services). Businesses, on the other hand, aim to achieve efficient allocation of their resources. This chapter introduces a combination of Artificial Intelligence mechanisms and Computational Economics concepts as a means of solving the above mentioned problems. These mechanisms and concepts are implemented in agent-based electronic markets. Electronic markets function as digital intermediaries that create value by bringing consumers and providers together to create transactional immediacy and supply liquidity, by supporting the exchange of demand and supply information, and reducing transaction costs. The efficiency of the created multi-agent system is realized by applying novel discovery and/or negotiation models.

Simulation of Mobile Agent Network

This paper deals with an event based multi-agent system simulator. Agents in the simulator are based on the mobile agent network formal model. The paper explains parts of the simulator such as operations, agents, nodes, network elements, etc. and how they work. In order to verify the simulation results, they were compared with the performance characteristics of a real multi-agent system, called the remote maintenance shell, measured in a laboratory.

The CrocodileAgent: Designing a Robust Trading Agent for Volatile E-Market Conditions

The Trading Agent Competition (TAC) simulates a challenging game environment where competing agents engage in complex decision-making activities with purpose of maximizing their profits. One of the TAC competitive scenarios is Supply Chain Management (SCM) where six trading agents compete by buying components, assembling PCs from these components and selling the assembled PCs to customers. In this paper, we briefly describe the TAC SCM environment and present the main features of the CrocodileAgent, our entry in the 2005 TAC SCM Competition. The agents performances in the 2005 TAC SCM, as well as in a series of controlled experiments, are discussed.

An agent-based optimization of service fulfillment in next-generation telecommunication systems

In order to increase revenues, reduce operating costs and satisfy new user demands, network providers have to develop new approaches for their service provisioning operations. One of the possible solutions for this problem is utilization of intelligent software agents. In such a scenario, software agents act on behalf of the network provider while performing certain actions in competitive environment of the telecom market. This paper presents an agent-based approach for optimization of service provisioning in a dynamic environment of the next-generation networks. Proposed solution is based on a genetic algorithm and assures a minimum operational costs regarding provisioning of new services to users.

Agent-Based Support for Context-Aware Provisioning of IMS-Enabled Ubiquitous Services

Multimedia applications executed on mobile devices allow users to be present and communicate with other users, anywhere and anytime, through wide area cellular networks, wireless local area networks (WLAN), or fixed networks. In order to enable ubiquitous personalized services, communication systems should allow users to specify their context, or their mobile devices and network infrastructures should automatically sense their context and offer enhanced service provisioning solutions. In this paper, we propose an agent-based solution that supports context-aware provisioning of IP multimedia subsystem (IMS)-enabled ubiquitous services. Using agent technology, multimedia communication, controlled by SIP and enriched with context-related events delivered by SIPs event mechanism, can be seamlessly provisioned, taking into account not only mobility issues and context-awareness, but also the semantics of exchanged events. This paper proposes a multi-agent system that will enable users to consume context-aware ubiquitous services in a seamless (i.e., automated) way, providing optimal provisioning of SIP-based multimedia services according to user preferences.

Reputation Tracking Procurement Auctions

The introduction of e-markets has created great challenges for both buyers and suppliers. Buyers have to decide how to take advantage of the possibilities offered on e-markets (i.e., higher savings, expanding the supplier base) but at the same time they should preserve values that are associated with their long-term relationships. As the use of reverse auctions in the industry grows,involved parties are increasingly concerned with how these auctions influence their previously established business relationships. Due to those existing relationships, reverse auctions should not be analyzed as stand-alone auctions. If the relationship is specified as a value-generating asset in the procurement process, then neither business party should expect relationships to be harmed. We propose a reputation tracking reverse auction model that exploits the advantages reverse auctions bring to buyers, while decreasing the disadvantages they bring to sellers. Several experiments were conducted and the analysis was focused on auctions that have different outcomes depending on whether they took reputation into account or not.

Agent-Based Provisioning of Group-Oriented Non-linear Telecommunication Services

The future of telecommunications is directed towards creating environments aware of user preferences, mobile device capabilities and communication context. Consequently, telecommunication operators have recognized the importance of dynamic formation of user groups according to similar characteristics (i.e., user preferences, user device, communication context, etc.). In this paper, we propose an agent-based solution that supports provisioning of group-oriented telecommunication services by applying ontology-based user profiling as well as semantic clustering techniques. Furthermore, proof-of-concept group-oriented service is presented.

The CrocodileAgent 2005: an overview of the TAC SCM agent

The Trading Agent Competition (TAC) is an international forum which promotes high quality research regarding the trading agent problem. One of the TAC competitive scenarios is Supply Chain Management (SCM) where six agents compete by buying components, assembling PCs from these components and selling the assembled PCs to customers. In this paper, we describe the strategies implemented in the Crocodile Agent, our entry in 2005 TAC SCM. We describe the structure and functionalities of the Crocodile Agent, the implementation of the basic agent tasks, and algorithms for ordering components and determining the profit margin. The agents performances in the 2005 TAC SCM competition, as well as in a series of controlled experiments, are discussed.

A multi-agent system for game trading on the B2B electronic market

In order to provision content-based services to their users, service providers need to purchase content distribution rights from various content providers. Sometimes the creation phase of certain content categories can last longer than planed so content providers deliver the content to service providers with delays. The delayed delivery can cause financial damages and inconveniences to service providers which have already announced the appearance of new content to their users. In this paper we propose a multi-agent system which is used to model an electronic market for trading the rights to distribute video and computer games. On the proposed market, a service provider agent uses the multiattribute reputation decision making mechanism to purchase content distribution rights from content provider agents. Several sets of experiments were conducted to demonstrate the efficiency of the multi-attribute reputation decision making mechanism.