Similar User Assisted Mobility Prediction

Abstract

In 5G systems, user mobility research can provide basic support for mobile communications in terms of handover management, resource reservation, etc., improve the robustness of mission-critical services, and reduce total energy consumption and communication delay. In this paper, the association analysis algorithm is used to mine the key movement patterns of users, and the definition of user mobility similarity is proposed. Based on the similar user found by similarity calculation, this paper proposes a similar user assisted mobility prediction model for predicting the mobility of individual users in the dataset, and discusses the impact of two important parameters of the model. Compared with the single-user model, this model achieves a 4% performance improvement, which verifies the validity of the model and the importance of similar user for prediction.