Handover algorithm based on Bayesian-optimized LSTM and multi-attribute decision making for heterogeneous networks

Abstract

Heterogeneous networks (HetNets) which can satisfy the diverse requirements of future terminal tasks through providing different network access services for terminals, have emerged as a vital technology for the development of next-generation networks. However, frequent access to different networks often leads to high handover delay and handover failure, resulting in a degradation of user experience. Therefore, maintaining seamless network connectivity has become a challenging problem for applications with high real-time and reliability requirements in HetNets. To address this problem, we propose a handover algorithm based on Bayesian-optimized Long Short-Term Memory (BO-LSTM) and multiple attribute decision making (HO-BLM) to reduce handover latency and failure, ensuring seamless network connectivity. To reduce handover delay, we designed a handover decision prediction algorithm based on BO-LSTM to trigger handover in advance by predicting the network state of users in the future. Additionally, we propose a preselection mechanism based on current network status to further reduce the calculation delay. Moreover, a multi-attribute decision making (MADM)-based selection approach is designed to select the best alternative network for a specific user, where the utility value of the best alternative network is calculated by weighing the users’ preferences for network parameters of different business types and the actual status of the candidate networks. Simulation results show that the proposed algorithm decreases the handover failure by up to 42.1% and the handover delay by up to 68% compared with traditional handover approaches.