AoI Minimization in Energy Harvesting and Spectrum Sharing Enabled 6G Networks

Abstract

Spectrum sharing is a method to solve the problem of frequency spectrum deficiency. This paper studies a novel spectrum sharing and energy harvesting system using artificial intelligence (AI) in which the freshness of information is guaranteed. The system is based on licensed shared access (LSA) which includes a primary user with access rights to the spectrum and a secondary user. The secondary user is an energy harvesting sensor that intends to use the primary user’s spectrum opportunistically. The problem is formulated as partially observable Markov decision processes (POMDPs) and solved using two methods: 1) a deep Q-network (DQN) and 2) a dueling double deep Q-Network (D3QN) to achieve the optimal policy. The purpose is to choose the best action adaptively in every time slot based on the user’s observations from the environment in overlay and underlay modes to minimize the average AoI of the secondary user. Finally, the simulation analyses are performed to evaluate the effectiveness of the proposed scheme compared to the overlay mode. According to the results, the average age of information (AoI) in the proposed system is less than that of the existing models, including only the overlay mode. The average user access is improved from 30% in the overlay mode to 45% and 48% in the proposed scheme which is implemented using DQN and D3QN, respectively.