Research On Fractional Frequency Reuse And Uplink Interference Classification Algorithm In LTE

With the development of mobile communication technologies,people have higher and higher requirements for data services,which has promoted the rapid maturation of LTE networks.However,2G and 3G networks have not completely exited the market,resulting in the coexistence of different standard communication networks.The interference from the inside and outside of the LTE network is also becoming more and more serious.In the face of more and more complex communication network environments and diverse application scenarios,this paper conducts related research work on the interferences of the system based on frequency reuse and machine learning techniques.The main research contents of this paper are as follows:(1)In view of the uneven distribution of cell users,some frequency reuse algorithms based on competition are proposed to improve the inter-cell interference problem and improve the cell edge user throughput.The ability of the cell to compete for edge spectrum resources is adjusted by the number of cell-edge users,thereby realizing the allocation of edge spectrum resources.The simulation results show that,compared with the traditional partial frequency reuse algorithm,the proposed algorithm can improve the throughput of cell edge users and improve the quality of cell edge user communication under the scenario of uneven distribution of cell users.(2)For LTE network uplink interference investigation,which takes a lot of manpower and material resources and low efficiency,this paper proposes a LTE uplink interference classification algorithm based on machine learning to assist the LTE network system in the external uplink interference investigation,using the PRB uplink average interference level values.The LTE uplink interference data set enhances the interference characteristics through feature engineering based on principal component analysis and skewness characteristics,and then selects an ensemble learning model represented by a random forest to classify and identify uplink interference data.The cost-sensitive function and artificial sample synthesis method are used to improve the unbalanced category of uplink interference data sets.Experimental results show that the LTE uplink interference classification algorithm based on machine learning in this paper can achieve good classification effect for LTE uplink interference data sets,and can be used in the interference investigation work of LTE systems,and improve the work efficiency of LTE system interference investigation.