Neighbor Cell List Optimization in Handover Management Using Cascading Bandits Algorithm

Abstract

Frequent handover is a key challenge in 5G Ultra-Dense Networks (UDN). In this paper, we show the significance of configuring Neighbor Cell List (NCL) in handover procedure. To cope with the high dynamic of UDN, we propose an online-learning method, namely the Cost-aware Cascading Bandits NCL configuration (CCB-NCL) algorithm, which applies the cascading model and Multi-Armed Bandits (MAB) theory to configure the efficient Neighbor Cell List (eNCL) and improves the handover performance by assisting the User Equipment (UE) to choose the optimal target Base Station (BS). We provide rigorous proof of regret bound to show the asymptotic convergence of the proposed CCB-NCL algorithm. The robustness and efficiency of the proposed algorithm are both demonstrated in different network scenarios, where varies BS densities, BS dynamic and network heterogeneity are considered respectively. In the simulation work, we reproduce two existing methods of configuring NCL in handover management, named dynamic threshold based solution and received signal strength based solution. In comparison with the existing solutions, the proposed algorithm can reduce the overlarge signaling cost and unnecessary delay in the preparation phase of handover procedure by significantly shortening the length of NCLs and reducing the number of scanned BSs. Extensive simulations are conducted in different scenarios to validate the robustness of the proposed algorithm and the results show that the proposed CCB-NCL algorithm is a superior approach to efficient handover management.