zyy341 / github_repository_collection Goto Github PK

2018-12-20更新：

• Deep-Learning-Power-Allocation-in-Massive-MIMO: 论文 Deep-Learning-Power-Allocation-in-Massive-MIMO的开源代码。This is the code package related to the follow scientific article: Luca Sanguinetti, Alessio Zappone, Merouane Debbah 'Deep-Learning-Power-Allocation-in-Massive-MIMO' presented at the Asilomar Conference on Signals, Systems, and Computers, 2018.
• deep-EE-opt:论文 Deep Learning for Optimal Energy-Efficient Power Control in Wireless Interference Networks的开源代码。Source code for "Deep Learning for Optimal Energy-Efficient Power Control in Wireless Interference Networks" by Bho Matthiesen, Alessio Zappone, Eduard A. Jorswieck, and Merouane Debbah, submitted to IEEE Journal on Selected Areas in Communication.

• hongzimao/deeprm：Resource Management with Deep Reinforcement Learning (HotNets '16) 虽然不是无线网络的资源分配，但是隐约感觉应该是一个
• mantecon/Self-organised-Admission-Control-for-Multi-tenant-5G-Networks：In this work, a self-organizing admission control algorithm for multi-tenant 5G networks is proposed and developed with novel artificial intelligence techniques. A simulation-based analysis is presented to assess the improvements of the proposed approach with respect to a baseline scheme.
• mylzwq / LoadBalanceControl-RL: Using Reinforcement Learning method to realize load balancing control in dynamic cellular network。 使用强化学习方法实现动态蜂窝网络的负载均衡。整体感觉下来，代码过于冗长，编写的框架混乱，可读性很差，本来想看一下动态环境怎么编写的，但是并没有找到 ....
• M.E-Energy-Efficient-Power-and-Subcarrier-Allocation-for-OFDMA-Systems-with-Value-Function-Approxima:同样开始以为会有帮助，但是大概看完之后，还是没有找到有帮助的代码块。唯一可能有用的就是其中queue_change.m这个函数有点用，功能是功率、子载波分配后，更新用户队列长度。这样或许可以增加一些动态性进去。
• fath0218 / channel_dqn：基于DQN的信道切换算法，虽然是中文注释，但是感觉代码结构还是很乱....
• shkrwnd/Deep-Reinforcement-Learning-for-Dynamic-Spectrum-Access：Using multi-agent Deep Q Learning with LSTM cells (DRQN) to train multiple users in cognitive radio to learn to share scarce resource (channels) equally without communication。动态，多智能体，本来和我想解决的问题很切合，但是为什么就是看不到可以复用的代码呢？也没有看出这也多智能体的reward的更新的不同！！！
• bjoluc/gymwipe：An OpenAI Gym Environment for Frequency Band Assignments in the Simulation of Wireless Networked Feedback Control Loops.基于OpenAI Gym环境的无线网络环境，用于频带分配。
• "https://github.com/mkoz71/Energy-Efficiency-in-Reinforcement-Learning">mkoz71 / Energy-Efficiency-in-Reinforcement-Learning：Code for the paper 'Energy Efficiency in Reinforcement Learning for Wireless Sensor Networks' 和超密集网络没有太大关系，场景模型应该是sensor networks for health monitoring。
• farismismar / Q-Learning-Power-Control：Code for my publication: Q-Learning Algorithm for VoLTE Closed-Loop Power Control in Indoor Small Cells. Paper accepted to 52nd Asilomar Conference on Signals, Systems, and Computers.感觉用处不大orz（找到的代码都是些什么鬼啊...）
• Traffic-Optimisation：Traffic Signal timings using Deep Q-Learning

使用深度强化学习交通灯管理。

代码写的格式很规范，即按照DQN给的格式（莫烦强化学习中提到的一种规范）。

• WlanDqn：A dqn application for using in wlan

在无线局域网中的应用，具体代码没有可以利用的，和资源分配领域没有一点关系。但是可以借鉴代码的编写框架，非常标准的框架。

对应文章："AIF: An Artificial Intelligence Framework for Smart Wireless Network Management"

• gym-radio-scheduler： 在gym库中加入了一个无线调度器，gym是谷歌开发的一个用于深度强化学习的库。待阅读ing

• Deep-Q-Learning-SON-Perf-Improvement:Code for my publication: Deep Q-Learning for Self-Organizing Networks Fault Management and Radio Performance Improvement. Paper accepted to 52nd Asilomar Conference on Signals, Systems, and Computers.如说明所示，是一篇会议论文的代码，算是有一定的参考性！但是真实感受而言，因为场景模型有较大的不同，可参考的还是很大不同！！

• ADGEfficiency/energy-py：reinforcement learning agents and environments for energy systems.

• sisl / MADRL：Repo containing code for multi-agent deep reinforcement learning (MADRL).包含对智能体的胜读强化学习，待阅读ing，看看能不能找到多智能体reward更新的方法。

• AlexVic / ResourceAllocationDelayedCSI &AlexVic / ResourceAllocationV2Xgraph&AlexVic/ResourceAllocationV2X： 良心代码，三篇层次递进的论文的代码。

• xushushu231 / The-JUAD-resource-allocation-for-D2D-in-a-FDD-cellular-network：也是良心代码，将代码和论文思路都写进来了。

• chamara84 / jointChannelAndPowerAlloFDCR：This contains joint channel and power allocation scheme for a full duplex cognitive radio network underlying a cellular network 在全双工的认知网络中联合优化信道和功率分配方案。

• Chenxi-Liu/UDN：应该是基于随机几何的超密集网络性能分析，但是只有一份代码，readme没有，描述也没有。

• Haoran-S / DNN_WMMSE：Code to reproduce our works on DNN research.

• D2D-communication：optimal mode selection between normal cellular and D2D mode.

• dreamian / D2DCommSimul：This repository includes the idea of effective D2D Communication method using Matching theoretic approach基于匹配理论的D2D通信。

• adrikayak / D2D_cellular_network_simulator：Simulator used in the study "D2D frequency allocation using GADIA in a cellular network" (Matlab)整体而言，也没有什么可以借鉴的，GADIA也没有看出是什么算法....有用的地方应该是场景模型可以借鉴一下。

• himanshukumar660 / Hungarian-Method：The repo consist of a implementation of Hungarian method for resource allocation.匈牙利算法的python语言实现。

• hpaulkeeler / kcoverage_single_MATLAB: Probability of connecting to multiple base stations in a Poisson network based on the SINR. 多基站的连接概率。

• hpaulkeeler / kcoverage_multi_MATLAB：Probability of connecting to multiple base stations in a multi-tier Poisson network based on the SINR. 多层泊松网络下的多基站连接概率

• DELMU:Simulation scripts used to produce the results presented in our paper R. LI et al. " DELMU: A Deep Learning Approach to Maximising the Utility of Virtualised Millimetre-Wave Backhauls" 没有仔细看，因为和Resource Allocation不太相关。

• Master-Thesis：Source Code to my master's thesis with the topic "End-to-end optimisation of MIMO systems using deep learning autoencoders" 大致看了一点，参考的是"An Introduction to Deep Learning for the Physical Layer"

• DeepMIMODetection: The paper "Deep MIMO Detection" presented at SPAWC 2017.

• Haoran-S / TSP-DNN：Training deep neural networks for wireless resource management使用深度神经网络对无线资源管理算法的拟合。

• pradeepshekhar/V2VchannelEstimator：车车信道估计器

• tyshiwo / DRRN_CVPR17:Code for our CVPR'17 paper "Image Super-Resolution via Deep Recursive Residual Network" 图像超分辨率

• oyamad/game_theory_models ： python编写的博弈论模型，没有去看。

• yangzhen0512/IntelligentOptimizationAlgorithms：This repository displays the demos of some Intelligent Optimization Algorithms 主要是一些智能优化算法，主要模拟退火，遗传算法，粒子群算法。

• farismismar - Overview：A part-time Ph.D. student in the electrical and computer engineering department at UT Austin.有几个深度强化学习的仓库。

• qiyuangong/Search_a_Paper_in_SEU_for_CSE：文献搜索的技巧

• highD-dataset:This repository contains a collection of functions to handle highD data files implemented in Matlab and Python. The functionality ranges from data handling to visualizing the data.

• sydney222 / Python_CsiNet：Python code for "Deep Learning for Massive MIMO CSI Feedback"深度学习用于CSI的压缩和解压，减少CSI的传输开销。

• chihkuanyeh / Automatic-Bridge-Bidding-by-Deep-Reinforcement-Learning：The released model of the paper 'Automatic Bridge Bidding by Deep Reinforcement Learning' in ECAI 2016使用深度强化学习玩桥牌。

• zhaoxrthu/DQN_of_DWA_matlab：使用深度强化学习进行机器人的动态窗口方法进行避障。这个up主（该怎么称呼github上的上传者呢？作为一名B站用户，就暂且称之为up主吧。）的几个库包括一些和图像，音频的。