Reconfigurable Intelligent Surface Assisted Mobile Edge Computing with Heterogeneous Learning Tasks

本文构建了一个实现边缘计算的框架,特别关注AI算法在通信系统中的应用。研究重点在于从用户设备到基站的数据传输,而非AI算法的具体实现。文章提出了针对移动用户发射功率、基站波束成形向量及RIS相移矩阵的优化算法。

摘要生成于 C知道 ,由 DeepSeek-R1 满血版支持, 前往体验 >

文献阅读系列文章

I will share the papers in the filed of CIM (computing in memory) based on emerging NVM (nonvolatile memory), especially RRAM.
The ideal state is that I will update the series blogs every day. However, I can not guarantee this because I am BUSY now. You know, homeworks, class projects and my own research projects.


Reconfigurable Intelligent Surface Assisted Mobile Edge Computing with Heterogeneous Learning Tasks

Abstract

This article built a framework to implement the edge computing, and the computing here is specifically AI algorithm. This work focuses on the data transmission from users devices to base station but not the AI algorithm implementation. Because the raw data sampled by sensors cannot be used directly by AI model. The problem is more of a communication problem. The highlight of this paper is the proposed algorithms to get the optimal solutions of the three variables, transmit power of mobile users, beamforming vectors of the base station (BS), and the phase-shift matrix of the RIS under the loss function. Unfortunately, I don't focus on these algorithms very much, therefore, I am not going to go into detail on them.

Main ideas

1.

在这里插入图片描述
在这里插入图片描述
joint optimization problem


Inspirations

I want to find more applications scenarios of NN algorithm in communication system. The phase-shift matrix of the RIS has been demonstrated that it can be implemented using CNN. How about the other two variables in this articles? They are all the nonconvex problems with high complexity. If the algorithms of the two problems can be replaced by NN, maybe the NVM can be used.

the url of this paper

### 可重构智能表面辅助毫米波无人机通信中的鲁棒与安全传输方案 #### 基于机器学习的方法概述 在可重构智能表面(Reconfigurable Intelligent Surface, RIS)辅助的毫米波无人机通信系统中,采用基于机器学习的技术可以显著提升系统的鲁棒性和安全性。这些技术不仅能够处理复杂的信道条件,还能有效抵御潜在的安全威胁。 #### 信道估计与预测 为了实现高效的通信,在复杂多变的环境中准确地估计和预测信道状态至关重要。通过收集大量历史数据并应用监督学习算法,如支持向量机和支持向量回归,可以构建精确的信道模型[^2]。这有助于提前感知可能发生的干扰情况,并采取预防措施。 #### 波束成形优化 针对毫米波频段特有的短波长特性以及高路径损耗问题,利用深度神经网络来进行自适应波束成形设计成为一种有效的解决方案。具体来说,可以通过训练卷积神经网络来识别最优的发射/接收角度组合,进而最大化链路增益的同时减少旁瓣泄漏带来的负面影响[^1]。 ```python import numpy as np from keras.models import Sequential from keras.layers import Dense, Conv2D, Flatten def create_beamforming_model(input_shape): model = Sequential() # Add convolutional layers to learn spatial features of the channel matrix model.add(Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=input_shape)) model.add(Flatten()) # Fully connected layer for final beamforming vector prediction model.add(Dense(np.prod(input_shape[:-1]), activation='linear')) return model ``` #### 安全机制强化 考虑到无线通信中存在的窃听风险,引入对抗生成网络(GANs)作为防御手段之一。该方法旨在模拟恶意攻击者的行为模式,并据此调整RIS参数配置以混淆其视线;另一方面,则是借助联邦学习框架下的分布式训练方式保护本地敏感信息不被泄露给中心服务器或其他节点。 #### 实验验证与性能评估 实验结果显示,在不同场景下部署上述策略均能取得良好效果——无论是静态还是移动状态下都能保持较高的吞吐率和服务质量水平;更重要的是,即使面对有意图性的干扰行为也表现出较强的抗扰能力[^4]。
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值