A Novel Mobility Prediction Algorithm Based on LSVR for Heterogeneous Wireless Networks

Mobility prediction algorithm is the significant aspect to improve QoS (Quality of Service) for heterogeneous wireless networks because it decreases handoff latency and preserves resources in arriving cells for users. Since, existing mobility prediction algorithms based on GPS (Global Positioning System) often suffer from low prediction accuracy for complex and irregular trajectory, this paper combines support vector regression with local prediction to propose a novel mobility prediction algorithms based on Local Support Vector Regression (LSVR) to overcome above deficiency. Simulation results show that LSVR algorithm achieves high prediction accuracy for a size of historical data in three typical mobile scenes.