Knowledge Expansion Algorithm of Heterogeneous Network Big Data Based on Improved K-means Algorithm

In recent years, with the rapid progress of wireless communication technology and various intelligent terminal technologies, all kinds of business requirements have shown explosive growth. The high quality of service requirements of diversified services and large-scale network capacity problems have become major challenges that wireless networks will face. In order to meet the business needs of different users, rational NP is the most effective and economic method to improve the system capacity. However, how to achieve higher network throughput at a lower cost is a very important research topic. The main purpose of this paper is to study the knowledge expansion algorithm of heterogeneous network (HN) big data based on the improved K-means algorithm (IKA). This paper will focus on wireless network technology, NP and other related content. In addition, this paper will describe the relevant theories of big data technology for NP. This paper proposes a BS clustering scheme that can be applied to ultra-dense network scenarios. By using the proposed clustering algorithm, small cell BSIUDN can be effectively clustered, which greatly simplifies the network topology and facilitates the management of BS. At the same time, orthogonal time-frequency resource blocks are allocated within the cluster to reduce system interference to a certain extent. The simulation results show that the proposed KCA based on the improved WD can effectively cluster the small cell BS in the ultra-dense network.