A communicating scheme for adaptive resource allocation in wireless networks

To achieve the best possible bandwidth utilization in wireless networks adaptive resource assignment is a requirement. Distributed or centralized resource allocation schemes can be used to reach such an objective. However, the means to actually implement these resource adaptive features represent a major implementation challenge. In addition, the schemes should be self adaptive and eventually self learning since large scale traffic variations on an hourly and a daily basis exhibit patterns with low expected variance. At a much finer scale, in micro and pico cellular environments variations due to user mobility are unpredictable and only dynamic channel allocation methods can adequately adapt to the rather large traffic variations. This contribution relates to the larger scale traffic variations and proposes an adaptive resource assignment approach based on the multi-agent technique which relies on self learning. The adaptive resource allocation scheme "channel segregation (CS)" containing inherently the self learning attribute was selected to test and validate the concept of using intelligent agents in base stations. Using the multi-agent platform DIMA (development and implementation of multi agent system), CS has been integrated and implemented in a simulation model of base stations to introduce the self learning feature in the network. The obtained simulation results validate the intelligent agent implementation and illustrate the feasibility of using such agents in base stations to introduce the self adaptive feature in mobile networks.