ES-DQN-Based Vertical Handoff Algorithm for Heterogeneous Wireless Networks

Abstract

One of the most challenging topics for next generation wireless networks is vertical handoff concept since several wireless technologies are supposed to cooperate. In this letter, evolution strategy and deep Q-network (ES-DQN) has been proposed to make vertical handoff simple and effective. The algorithm executes the deep Q-network (DQN) with the objective of maximizing the benefit of the system, and combined with evolution strategy (ES) algorithm with global optimization capability to set initial parameters of the back propagation (BP) network in order to improve the convergence speed and precision of parameter learning. The results show that the proposed method not only outperforms existing schemes with handoff latency and throughput, but also reduce handoff failure probability and call blocking probability.