Performance Optimization for Wireless Semantic Communications over Energy Harvesting Networks

Оптимизация производительности беспроводных семантических коммуникаций в сетях со сбором энергии
H. Vincent Poor, Mingzhe Chen, Yining Wang
2022-04-27

energy harvesting networksresource block allocationsemantic communicationssemantic similarityvalue decomposition deep Q network
In this paper, the optimization of semantic communications over energy harvesting networks is studied. In the considered model, a set of users use semantic communication techniques and the harvested energy to transmit text data to a base station (BS). Here, semantic communication techniques enable each user to transmit the meaning of the original data (called semantic information) thereby reducing its transmission delay and energy consumption. The BS will recover the data using the received semantic information. 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) that is used for semantic information transmission. This problem is formulated as an optimization problem whose goal is to maximize the sum of all users’ similarities that capture the differences between the original data that each user needs to transmit and the data recovered by the BS. To solve this problem, a value decomposition based deep Q network is proposed, which enables the users to jointly find the semantic information transmission and the RB allocation schemes that maximize the sum of all users’ similarities. Simulation results demonstrate that the proposed method can improve sum of all users’ similarities by up to threefold compared to the independent reinforcement learning.
1
A value-decomposition-based deep Q-network enables users to jointly learn semantic-information transmission and resource-block allocation policies.
2
Allowing partial semantic information transmission can reduce communication delay and energy consumption while maintaining recoverable data meaning.
3
Simulations show the proposed method improves the sum of users’ similarities by up to threefold compared with independent reinforcement learning.
4
The optimization objective maximizes the sum of users’ similarities between original texts and data recovered by the base station.
5
The study optimizes semantic text communications in energy-harvesting networks, jointly considering partial semantic information transmission and resource-block allocation.

Semantic communications over energy harvesting wireless networks, in which multiple users transmit text data to a base station

Joint optimization of partial semantic information selection and resource-block allocation to maximize the sum of users’ data-recovery similarities under harvested-energy constraints

Publication Details
Publication Date
2022-04-27
Journal
Publisher
ISSN
Cited by
31
Access Type
Author Information
Authors
H. Vincent Poor
Mingzhe Chen
Yining Wang
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%