An Efficiency-Improved Clustering Algorithm Based on KNN Under Ultra-Dense Network

Abstract

Ultra-Dense Network (UDN) is one of the key techniques for the next generation of mobile network due to providing high system throughput. However, severe interference often occurs in UDN, which greatly impact the data rates of cell-edge users. User-centric wireless access virtualization has been widely adopted in UDN to mitigate the interference of cell-edge users by sharing resources and eliminating cell boundary. However, it's only effective for moderate scale networks. Moreover, the efficiency needs further improvement. In this paper, we study effective cooperative clustering method for large scale UDN with less computations in order to improve the throughput of cell-edge users. We formulate a convex optimization problem in which the objective is to maximize the system throughput with overlapping virtual cells. We propose a clustering method to solve this optimization problem. We design a fast-convergent iterative algorithm called K-Nearest Neighbor (KNN) algorithm to perform users clustering. Simulation results show that our proposed algorithm has better throughput performance for both average and cell-edge users. Especially, the per-carrier throughput is improved, which leads to more serviceable users with limited resources. INDEX TERMS Ultra-dense networks, virtual cell, interference mitigation, green communications, clustering.

A Lightweight Cell Switching and Traffic Offloading Scheme for Energy Optimization in Ultra-Dense Heterogeneous Networks

“…1) Complexity: One of the ways of evaluating the complexity of an algorithm is to determine its time complexity, that is, the simulation run time or time taken for the simulation to be complete [48]. Fig.…”

Practical Optimization and Game Theory for 6G Ultra-Dense Networks: Overview and Research Challenges

“…Cell clustering methods help to not only disperse the big scenario of UDNs to decrease the computational complexity but localize the different objectives. There are three categories of cell clustering methods: network-based (static), user-based (dynamic), and hybrid (semi-dynamic) ones [35]. Networkbased clustering methods divide cells into clusters according to given targets, and the clusters do not change over time.…”

“…The network-based clustering scheme is less flexible with interference, and the user-based clustering one is more complex with system scheduling and exhaustive information exchange. The hybrid clustering methods consider the tradeoff of these two joint categories [35]. In [42], [43], measurement BS clusters (MBCs) are formed according to measurement information and CSI.…”

“…Then, coordination BS clusters (CBCs) which are the subsets of the fixed MBCs are created by cooperative BSs. Furthermore, user clustering methods considered in [24], [35], [44] are used as the next stages after the cell clustering methods to minimize the intracluster interference.…”

Know Your Enemy: User Segmentation Based on Human Aspects of Information Security

“…Most identified studies employ an experimental research design. For example, clustering has been applied to various research areas, such as users of smartphone applications [32], [33], behavior of retail customers [34], downloading behavior of academic search engine users [35], online shopping customer loyalty [36], and mobile network users [37]. All these studies use automatically generated data (e.g., application usage, online shopping transactions) as input into user segmentation.…”