No abstract

In the 5G era, the operational cost of network is expected to increase significantly because of networks' densification, the concurrent operation at multiple frequency bands, and the simultaneous use of different medium access as latent components of 5G. To decrease the operational cost of networks, engineers have tuned to self-organizing networks (SON) that facilitate automatic operation of a network. Challenges have emerged, however, that hinder the current SON paradigm from meeting the requirements of 5G. To overcome these challenges, researchers have proposed a framework for empowering SON with big data. The framework of big data empowered SON analyzes the relationship between key performance indicators (KPIs) and related network parameters (NPs) using machine learning tools; with those parameters, the framework develops regression models using Gaussian process. These models are then applied to the SON engine to be further optimized for operation. The problem, however, is that the methods of finding NPs related to KPI differ case by case. In addition, it is not easy to apprehend the relationship between a KPI and the various NPs related to that KPI with the Gaussian process regression model because it is a single regression. In this paper, to alleviate these two problems, we propose multiple regression models based on MapReduce, where a KPI is the dependent variable and NPs are the independent variables; then we also describe implementation issues with MapReduce.Keywords-Self-organizing networks; big data empowered SON; Hadoop; MapReduce; multiple regression; scalable matrix inversion I.

No abstract

No abstract

In future, more devices such as wearable devices will be connected to the networks. This will increase simultaneous handovers. The coverage of a cell will be small because a superhigh frequency used in 5G wireless networks does not propagate very far. This trend will increase the number of neighbour cell lists and it will accelerate the change of neighbour cell lists since the coverage of cells can be altered by the environment. Meanwhile, the ANR technology will be essential in 5G networks. Since the network environment in the future is not similar to the present, the strategy of ANR should also be different from the present. First, since practical neighbour cell lists in each cell are changed frequently and individually, it is necessary to optimize them frequently and individually. Second, since the neighbour cell lists in each cell are not changed similarly, it is necessary to operate ANR flexibly. To respond to these issues, we propose to use network function virtualization (NFV) for ANR. To evaluate the proposed strategies, we measured additional resource consumption and the latency of handover if neighbour cell lists are not optimized when UEs perform handover simultaneously. These experiments are conducted using Amarisoft LTE-100 Platform.