A FUZZY NEURAL JOINT RADIO RESOURCE MANAGEMENT IN A MULTI-CELL SCENARIO SUPPORTING A MULTISERVICE ARCHITECTURE

摘要

In this paper an innovative mechanism to perform Joint radio Resource Management (JRRM), based on Fuzzy-Neural methodology, is introduced. A multicellular and multi-RAT scenario including UMTS, GERAN and WLAN Radio Access Technologies (RATs) is considered. It will be shown that the proposed framework is able to efficiently manage a multiservice architecture. The proposed JRRM algorithm is capable of dealing with different operator policies as well as controlling the most representative QoS objectives for each class of service, retaining them to a predefined target value by means of smart reinforcement learning mechanisms based on neural networks.