iAgent: When AI Meets Mobile Agent

IEEE Access

Ahmad Almogren¹  Mohammad Mehedi Hassan¹  Ayman Altameem²  Wenjing Xiao³  Jiayi Lu³  Enmin Song³ 

[1] College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia;Department of Natural and Engineering Sciences, College of Applied Studies and Community Services, King Saud University, Riyadh, Saudi Arabia;School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China;

关键词: Mobile agent;    artificial intelligence;    wireless sensor network;   

DOI  :  10.1109/ACCESS.2019.2926286

来源: DOAJ

【 摘 要 】

The past few decades have seen the rapid development of artificial intelligence (AI) technology in diverse industries. Inspired by the fact that an agent is the central part of AI, we combine AI with the technology of the mobile agent. A mobile agent used in wireless sensor networks (WSNs) is popular for its mobility, executability, and autonomy. To improve the intelligence of the mobile agent, we proposed a conceptual theoretical framework named iAgent, where i means intelligent, and the agent refers to the mobile agent. Four designs of iAgent are detailed. Compared with the old mobile agent, the iAgent has a learning ability, which means that it can dynamically plan the path according to the external environment in order to reduce energy consumption. Based on iAgent, we also proposed a method to determine the number of iAgents and their visiting areas in a multi-iAgent WSN environment. The extensive simulation indicates that the multi-iAgent algorithm can significantly improve the performance of the WSNs, especially in saving energy and balancing network load.

【 授权许可】

Unknown