Efficient performative actions for e-commerce agents

Qasim, A; Amin, H; Aziz, ZUH; Khalid, A

Abstract

The foundational features of multi-agent systems are communication and interaction with other agents. To achieve these features, agents have to transfer messages in the predefined format and semantics. The communication among these agents takes place with the help of ACL (Agent Communication Language). ACL is a predefined language for communication among agents that has been standardised by the FIPA (Foundation for Intelligent Physical Agent). FIPA-ACL defines different performatives for communication among the agents. These performatives are generic, and it becomes computationally expensive to use them for a specific domain like e-commerce. These performatives do not define the exact meaning of communication for any specific domain like e-commerce. In the present research, we introduced new performatives specifically for e-commerce domain. Our designed performatives are based on FIPA-ACL so that they can still support communication within diverse agent platforms. The proposed performatives are helpful in modelling e-commerce negotiation protocol applications using the paradigm of multi-agent systems for efficient communication. For exact semantic interpretation of the proposed performatives, we also performed formal modelling of these performatives using BNF. The primary objective of our research was to provide the negotiation facility to agents, working in an e-commerce domain, in a succinct way to reduce the number of negotiation messages, time consumption and network overhead on the platform. We used an e-commerce based bidding case study among agents to demonstrate the efficiency of our approach. The results showed that there was a lot of reduction in total time required for the bidding process.

Citation

Qasim, A., Amin, H., Aziz, Z., & Khalid, A. (2020). Efficient performative actions for e-commerce agents. Applied Computer Systems, 25(1), 19-32. https://doi.org/10.2478/acss-2020-0003

• Journal Article Type: Article
• Online Publication Date: Jun 5, 2020
• Publication Date: Jun 5, 2020
• Deposit Date: Jul 13, 2020
• Publicly Available Date: Jul 13, 2020
• Journal: Applied Computer Systems
• Electronic ISSN: 2255-8691
• Publisher: De Gruyter
• Volume: 25
• Issue: 1
• Pages: 19-32
• DOI: https://doi.org/10.2478/acss-2020-0003
• Publisher URL: https://doi.org/10.2478/acss-2020-0003
• Related Public URLs: https://content.sciendo.com/view/journals/acss/acss-overview.xml