A Multi-agent System for Resource Management in GSM Cellular Networks

This paper presents a new experience in designing and developing a multi-agent system for managing frequency resources in a Regional Access Network (RAN) in GSM system (Global System for Mobile Communications). In our approach, a group of agents are distributed in the network with each regional network overseen by a supervisor agent; i.e. combining a cooperative agent to each cell called the station agent that handles the assignment of a frequency. Within a Radio Area Network RAN and at each step, an agent is elected by all its neighbors: The election is based on empirical rules for calculating the degree of separation of an agent, the degree of saturation and the improvement claimed by the neighbors for an assignment. The elected agent assigns the smallest frequency in the spectrum that meets all its constraints. In the case of a non permitted assignment, the agent may be served by a neighboring RAN, through a mechanism of cooperation between supervisor agents of both RANs. All RANs are handled in a localized region regardless of the operating band. Our multi-agent system has been implemented in JADE, a well-known multi-agent platform based in JAVA [4]. Experimental evaluations using standard benchmarks of frequency assignment problems show that this approach can find optimal solutions and exact solutions for some instances of these problems and the results obtained are equivalent to those of current methods using simulated annealing, constraint satisfaction/optimization techniques, or neural networks. These results show that our approach is more efficient in terms of flexibility and produces an excellent degree of optimality in terms of flexibility, autonomy and resource requirements.