研究目的
To autonomously solve problems in the radio access network and to minimize their impact on the user through a root cause analysis system based on fuzzy logic and a genetic algorithm for learning the rule base.
研究成果
The proposed method for obtaining the rule base of fuzzy controllers for mobile network self-diagnosis using a learning method instead of direct knowledge acquisition is robust and reduces the need for expert intervention. The method is adaptable to the way of reasoning of troubleshooting experts, easing knowledge acquisition and system output interpretation.
研究不足
The main limitation is the requirement for a high collaboration degree from troubleshooting experts for knowledge acquisition, although the proposed method reduces this need compared to previous approaches.
1：Experimental Design and Method Selection:
The methodology involves the use of fuzzy logic and genetic algorithms for learning the rule base of a fuzzy logic controller (FLC) used for diagnosis in mobile networks.
2：Sample Selection and Data Sources:
The training data is a set of cases consisting of vectors of crisp values for several performance indicators (PIs) and a class label corresponding to the diagnosed fault cause.
3：List of Experimental Equipment and Materials:
The study utilizes a network emulator based on the knowledge of troubleshooting experts to generate fault causes and their associated PIs.
4：Experimental Procedures and Operational Workflow:
The algorithm involves reproduction, evaluation, selection, and postprocessing stages to evolve the rule base.
5：Data Analysis Methods:
The performance of the proposed method is evaluated based on diagnosis error rate, undetected rate, and false positive rate.
独家科研数据包，助您复现前沿成果，加速创新突破
获取完整内容
