Performance Optimization for Wireless Semantic Communications over Energy Harvesting Networks

In this paper, the optimization of semantic communications over energy harvesting networks is studied. In the considered model, users use semantic communication techniques and the harvested energy that follows unknown distributions to transmit data to a base station (BS). Here, semantic communication techniques enable each user to transmit the meaning of the original data (called semantic information) thus reducing its data transmission delay and energy consumption. To further improve communication efficiency, each user can transmit only partial semantic information to the BS. Therefore, each user needs to jointly determine the partial semantic information to be transmitted and the resource block (RB) used for information transmission. This problem is formulated as an optimization problem aiming to maximize the sum of all users? similarities that capture the differences between each user's original data and the data recovered by the BS. To solve this problem, a value decomposition based Q network is proposed, which enables the users to jointly find the semantic information transmission and the RB allocation schemes that can maximize the sum of all users? similarities. Simulation results demonstrate that the proposed method can improve the sum of all users? similarities by up to three-fold compared to the independent reinforcement learning.