Developing a Shared Knowledge Area Mechanism for Multi-Mobile Agents to Improve Performance Using Machine Learning: Classification-Rule

Abstract

A mobile agent system is a mobile computing approach where agents move autonomously among hosts to perform tasks. It offers advantages such as low latency, reduced bandwidth use, and cost efficiency. This paper proposes the Shared Knowledge Area Mechanism (SKAM) to improve mobile agent performance. SKAM uses a shared knowledge database that stores classification rules based on agents’ travel experiences. Each rule is an IF–THEN statement linking service combinations to host locations. We extract these rules using support, confidence, and lift to ensure reliability. Before starting a task, an agent queries the database to select hosts based on the most relevant rules. This reduces unnecessary host visits and shortens travel time. SKAM is implemented within the Secure Mobile Agent Generator (SMAG), a platform used to simulate mobile agent behavior. SKAM also applies rule prioritization to support accurate itinerary planning. Experimental results show that SKAM reduces average task completion time from 41,146.5 ms to 23,445.5 ms—a 43% improvement. This gain is statistically significant (p < 0.05) and consistent across all agents. It confirms that SKAM lowers both search overhead and travel time. These results highlight SKAM’s effectiveness and practical value for real-time, large-scale mobile agent systems.