In this paper, a semantic communication framework for image transmission is
developed. In the investigated framework, a set of servers cooperatively
transmit images to a set of users utilizing semantic communication techniques.
To evaluate the performance of studied semantic communication system, a
multimodal metric is proposed to measure the correlation between the extracted
semantic information and the original image. To meet the ISS requirement of
each user, each server must jointly determine the semantic information to be
transmitted and the resource blocks (RBs) used for semantic information
transmission. We formulate this problem as an optimization problem aiming to
minimize each server's transmission latency while reaching the ISS requirement.
To solve this problem, a value decomposition based entropy-maximized
multi-agent reinforcement learning (RL) is proposed, which enables servers to
coordinate for training and execute RB allocation in a distributed manner to
approach to a globally optimal performance with less training iterations.
Compared to traditional multi-agent RL, the proposed RL improves the valuable
action exploration of servers and the probability of finding a globally optimal
RB allocation policy based on local observation. Simulation results show that
the proposed algorithm can reduce the transmission delay by up to 16.1%
compared to traditional multi-agent RL.

本研究开发了一种语义通信框架用于图像传输；引入多模态度量方法对比提取得到的语义信息与原始图像之间的相关性，以最小化每个服务器的传输延迟同时满足用户 ISS 需求为目标，提出了基于价值分解的最大熵多智能体强化学习算法以解决资源块的分配问题，在模拟实验中将传输延迟降低至传统多智能体强化学习的 16.1%。

合作语义通信网络中图像传输的优化

Optimization of Image Transmission in a Cooperative Semantic Communication Networks

This paper addresses the cell association problem in the downlink of a
multi-tier heterogeneous network (HetNet), where base stations (BSs) have
finite number of resource blocks (RBs) available to distribute among their
associated users. Two problems are defined and treated in this paper: sum
utility of long term rate maximization with long term rate quality of service
(QoS) constraints, and global outage probability minimization with outage QoS
constraints. The first problem is well-suited for low mobility environments,
while the second problem provides a framework to deal with environments with
fast fading. The defined optimization problems in this paper are solved in two
phases: cell association phase followed by the optional RB distribution phase.
We show that the cell association phase of both problems have the same
structure. Based on this similarity, we propose a unified distributed algorithm
with low levels of message passing to for the cell association phase. This
distributed algorithm is derived by relaxing the association constraints and
using Lagrange dual decomposition method. In the RB distribution phase, the
remaining RBs after the cell association phase are distributed among the users.
Simulation results show the superiority of our distributed cell association
scheme compared to schemes that are based on maximum signal to interference
plus noise ratio (SINR).

本文提出了一种针对多层异构网络中基站有限资源分配的小区关联问题的解决方案，通过分别考虑长期速率最大化和全局中断概率最小化两个问题，设计了一个统一的分布式算法来进行小区关联，与使用最大信干噪比（Signal to Interference plus Noise Ratio）方案相比表现更卓越。