SWIPT-D2D通信中基于深度强化学习的资源分配

针对信道状态信息未知SWIPT-D2D((Simultaneous Wireless Information and Power Transfer Device to Device)无线通信网络环境下设备间信号干扰以及设备能量损耗问题,提出通过使用近端策略优化(Proximal Policy Optimization, PPO)算法,在满足蜂窝用户通信质量要求的前提下同时对D2D用户的资源块、发射功率以及功率分割比三部分进行联合优化。仿真结果表明,所提算法相比于其他算法能够为D2D用户制定更好的资源分配方案,在保证蜂窝用户保持较高通信速率的同时使D2D用户获得更高的能效。同时,当环境中用户数量增加时,所提算法相比于Dueling Double DQN(Deep Q-Network)以及DQN算法,D2D能效分别平均提高了15.95%和23.59%,当通信网络规模变大时所提算法具有更强的鲁棒性。     

异构网络中基于能效优化的D2D资源分配机制

针对异构网络中D2D通信复用蜂窝用户频谱时存在的频谱分配问题,该文提出一种基于改进离散鸽群优化(PIO)算法的D2D通信资源分配机制。通过设置信干噪比(SINR)门限值来保证用户的通信服务质量(QoS),采用功率控制算法为用户设置发射功率,使用基于运动权值的二进制离散鸽群优化(MWBPIO)算法为D2D用户进行资源分配,并将D2D通信技术与中继技术进行有效结合,为边缘用户建立D2D中继链路,保证边缘用户的通信质量,最大化系统性能目标。仿真结果表明,该方案有效抑制了异构通信系统中引入D2D用户后导致的干扰问题,提高了边缘用户的通信质量和系统的频谱利用率以及系统的能效。     

D2D通信中联合链路共享与功率分配算法研究

针对D2D （Device-to-Device,D2D）通信过程中的资源分配问题,提出一种联合链路共享和功率分配算法.在保证系统内蜂窝用户服务质量（Quality of Service,QoS）需求的前提下,利用系统的信道状态信息,为D2D用户生成一个由蜂窝用户组成的通信链路的候选集合;在通信链路候选集合内使用凸优化方法得到D2D用户最优功率分配策略;最后利用（Kuhn-Munkres,KM）算法求解最大加权二部图匹配（Maximum Weight Bipartite Matching,MWBM）问题,为D2D用户选择最优的蜂窝用户进行资源共享.仿真结果表明该算法能有效的提升通信网络的吞吐量,可以为D2D用户选择最优的资源分配策略.     

Dynamic resource allocation for Device‐to‐Device communication underlaying cellular networks

Future cellular networks such as IMT‐Advanced are expected to allow underlaying direct Device‐to‐Device (D2D) communication for spectrum efficiency. However, enabling D2D communication in a cellular network presents a challenge in resource allocation because of the potentially severe interference it may cause to the cellular network by reusing the spectrum with the cellular users. In this paper, we analyze the resource allocation problem in a single cell system when both cellular users and D2D users are present in the system. We first consider the scenario where cellular users and D2D users are allocated resource independently and propose an optimal algorithm and a heuristic algorithm, and then extend the methods to the scenario where cellular users and D2D users are allocated resource jointly. The number of permitted D2D pairs is selected as a performance measure because it is a more specific performance measure than spectrum efficiency. The proposed schemes maximize the number of permitted D2D communication pairs in a system meanwhile avoiding the strong interference from D2D links to the cellular links. Finally, the performance of the proposed methods is evaluated through the numerical simulation. The simulation results show that the proposed methods enhance the number of permitted D2D communication pairs significantly and that the performance of the proposed scheme for jointly allocation scenario is better than that of the proposed scheme for independently allocation scenario. Copyright © 2012 John Wiley & Sons, Ltd.     

基于用户中断概率的D2D通信干扰协调与资源分配

在LTE系统中引入设备直传(D2D)通信技术,会因为D2D用户复用蜂窝用户资源进行通信而产生同频干扰.在现有的干扰协调与资源分配研究中,都需要基站获取各个通信链路的信道状态信息(CSI),但这样无疑会增加基站的信令负担.为减小干扰与基站的信令负担,提出了一种基于用户中断概率的干扰协调与资源分配算法,首先在保证蜂窝用户正常通信的情况下,通过限制D2D用户到基站间的距离来降低干扰;其次通过遍历所有蜂窝用户的频谱资源,选择能使D2D用户的总中断概率最低的频谱资源进行复用.仿真结果表明,所提算法能够在保证蜂窝用户正常通信的情况下,明显降低D2D用户的平均中断概率,同时还能够降低基站信令负担.     

D2D通信系统中基于QoS的分簇信道分配算法

D2D(Device-to-Device)通信作为第五代移动通信(5G, 5-generation)的关键技术之一,因其高频谱效率、低能耗等优点受到广泛关注。为了更好地满足D2D用户的服务质量(quality of service, QoS)需求,本文引入用户满意度的概念,提出了一种基于QoS的分簇信道分配算法。该算法运用图论着色方法为D2D用户分配信道,可分为三个步骤:首先构建D2D用户间的干扰图,然后在保证蜂窝用户QoS需求的情况下建立D2D用户的可用颜色列表,最后为D2D用户分簇,位于同一簇内的用户可以共享信道。仿真结果表明,本文算法可以有效提高D2D用户的满意度和系统公平性。      

An intra–inter-cell device-to-device communication scheme to enhance 5G network throughput with delay modeling

As the number of mobile users is growing, so is the demand for more bandwidth. It becomes important that the required bandwidth and spectral resources do not scale with traffic in the next generation of wireless networks [i.e. fifth generation (5G)]. Device-to-device (D2D) communication underlaying cellular networks has been recognized as an essential technique in 5G networks. By applying definite principles and strategies, D2D communication not only increases the spectral and energy efficiency, but also enhances network throughput, network coverage and reduces delay. In this paper, we present an intra–inter-cell D2D communication scheme to enhance throughput of 5G networks. We study call setup delay of two developed communication scenarios and throughput gain comparing three systems. Firstly, we show the enhancements required in current cellular architectures to support inter-cell D2D communication. We develop protocols for two scenarios and demonstrate how architecture entities cooperate for the call setup between D2D users. We measure the overall call setup time for the developed protocols and derive a closed-form delay formula to estimate call setup time probability. Secondly, we perform simulations using a topology similar to that found in realistic urban environments to study throughput gains of the proposed intra–inter-cell D2D communication scheme. We compare three systems in terms of throughput: (1) pure cellular system (with cellular users only), (2) pure cellular system with intra-cell D2D users sharing the same cellular resource, and (3) pure cellular system with intra–inter-cell D2D users sharing the same cellular resource. Simulation results show that the proposed scheme substantially increases the network throughput and spectrum efficiency.     

5G网络中DR-OC型D2D通信收益模型及定价研究

Device-to-Device(D2D)通信是下一代(5G)移动网络的重要组成部分。D2D设备间在不依赖基站的情况下直接进行数据传输,并通过重复使用蜂窝小区的频率资源从而提高移动通信系统的容量。为了激励蜂窝网络用户参与到D2D通信,运营商对D2D通信的定价是一个很关键的问题。文中首先介绍了D2D的基本概念及其四种主要类型,并就其中DR-OC型D2D通信定价提出了运营商和D2D设备的收益模型,然后仿真分析了网络中谱单价和奖励带宽对双方收益的影响。仿真结果显示运营商可以通过调整奖励带宽来协调双方收益以激励更多的用户参与到D2D通信。     

D2D中基于社交关系的按需用户发现策略

无线多媒体业务的爆炸式增长使得D2D(Device-to-Device)通信技术成为下一代移动通信系统的研究热点。用户发现策略,作为D2D关键技术之一,旨在有效发现潜在的D2D邻居用户。基于现有用户发现策略建立D2D链路,正面临着有效性和安全性的巨大挑战。本文考虑到每个用户不可避免地处于移动社交网络中,提出了基于社交关系的按需用户发现策略。主要根据用户请求的文件、具有的社交关系以及基站反馈和更新系统用户的状态信息表,来发现潜在的D2D用户对并建立D2D链路。理论分析及仿真结果表明,该策略可以更有效地发现邻居用户,并提高了D2D链路建立的安全性。      

D2D通信中一种基于FFR的动态功率控制方案

工作在underlay方式下的D2D(device-to-device)通信利用资源复用共享蜂窝网络中的资源,在提高频谱资源利用率、降低移动终端功耗的同时,会给已有蜂窝网络带来干扰。在保证D2D用户和蜂窝用户的服务质量的前提下,研究了蜂窝用户和D2D用户的功率控制和资源分配问题。首先引入部分频率复用(FFR)实现蜂窝用户和D2D用户之间的资源划分和复用;然后以系统吞吐量最大化为原则,建立优化目标。结合部分功率控制(FPC)的基本思想,进而提出了一种动态功率控制(DPC)策略。仿真结果表明,所提出的方案能够有效地提高多小区系统的性能。     

Efficient target tracking in directional sensor networks with selective target area’s coverage

Device-to-Device (D2D) communication technology, under the standardization of third generation partnership project and a component of the evolving fifth generation architecture, is mainly aimed to increase system capacity and data rate via providing direct communications between end devices without the use of routing data through the network. Apart from the attracting features, due to the resource sharing between cellular user equipment (CUE) and D2D user equipment (DUE) in such communications, an efficient algorithm for resource and power allocation to DUE, especially for mobile users is necessary to maintain the performance. The current paper introduces a joint mode algorithm for mobile user to choose between cellular and D2D communications and thereby, analyzes resource allocation issues. We propose an efficient algorithm for mobility management of users based on their current connection modes. The locations of D2D pairs are estimated by Levenberg–Marquardt method based on the received signal strength (RSS) from different macrocells. Since the range of D2D communication is much shorter than that of cellular communication, in order to prevent ping-pong handoffs between cellular and D2D modes, we propose the estimation of the next RSS samples in cellular mode prior to switching to D2D mode. In both cellular and D2D modes, the allocated resource block (RB) is the one with the highest signal to interference plus noise ratio (SINR) in order to increase the throughput, under the condition of providing minimum SINR requirement of CUE. This is achieved via transmission power control of the D2D pair. For performance evaluation, we studied the effects of increasing velocity of D2D and cellular users, number of users, and SINR threshold. The results indicate that the proposed solution fairly manages the communication mode of mobile users and incurs improvement in system throughput.     

基于多智能体深度强化学习的D2D通信资源联合分配方法

设备对设备(D2D)通信作为一种短距离通信技术,能够极大地减轻蜂窝基站的负载压力和提高频谱利用率。然而将D2D直接部署在授权频段或者免授权频段必然导致与现有用户的严重干扰。当前联合部署在授权和免授权频段的D2D通信的资源分配通常被建模为混合整数非线性约束的组合优化问题,传统优化方法难以解决。针对这个挑战性问题,该文提出一种基于多智能体深度强化学习的D2D通信资源联合分配方法。在该算法中,将蜂窝网络中的每个D2D发射端作为智能体,智能体能够通过深度强化学习方法智能地选择接入免授权信道或者最优的授权信道并发射功率。通过选择使用免授权信道的D2D对(基于“先听后说”机制)向蜂窝基站的信息反馈,蜂窝基站能够在非协作的情况下获得WiFi网络吞吐量信息,使得算法能够在异构环境中执行并能够确保WiFi用户的QoS。与多智能体深度Q网络(MADQN)、多智能体Q学习(MAQL)和随机算法相比,所提算法在保证WiFi用户和蜂窝用户的QoS的情况下能够获得最大的吞吐量。     

Research on the interference control and resource allocation in D2D communication

In order to solve the problem of interference caused by D2D users reuse cellular resources in cellular network,an algorithm of interference control and resource allocation of D2D communication in single cell cellular system was proposed.Firstly,an interference graph was constructed according to the interference between users in the system to find the reusable channel resource for D2D users.Then,the channel resource pre-allocation and the channel switching policy were performed for D2D users in sequence according to the preset D2D user priority.The simulation results show that the proposed algorithm can significantly improve the system throughput and the access rate of D2D users so that the system can achieve better performance in the presence of small or large number of D2D users.     

全负载蜂窝网络下多复用D2D通信功率分配算法研究

针对全负载蜂窝网络中D2D通信的功率分配问题,该文提出了一种基于非合作完全信息博弈纳什均衡解的多复用D2D通信功率分配算法。以优先保证蜂窝用户通信质量与D2D用户接入率为前提,设置D2D通信系统上行链路帧结构,之后建立非合作完全信息博弈系统模型,引入定价机制到功率分配博弈模型中并分析纳什均衡解的存在性与唯一性,最后给出该模型的分布式迭代求解算法。仿真结果表明,随着D2D用户复用数量的增加,该算法在提升系统吞吐量的同时,能有效地控制系统内部干扰,大幅度降低系统总能耗。     

异构云无线接入网场景下D2D通信资源共享与分配

针对异构云无线接入网中的前向链路受限问题,提出了一种基于干扰阈值的设备到设备(Device-to-Device,D2D)多用户分簇方案,并对系统信道和功率资源的分配进行优化。首先根据D2D用户之间的干扰级别,利用着色图理论对多用户进行分簇;然后,在满足D2D用户和蜂窝用户服务质量约束下,建立了基于D2D用户和速率最大化的资源分配模型,并进一步采用二分法对已分簇的D2D用户进行功率优化分配。仿真实验结果验证了所提方案相比传统方案,系统频谱利用率提高了55%以上。     

UAV-assisted multi-hop D2D relaying for communication in large disaster area

An unmanned aerial vehicle (UAV)-assisted communication is a promising technique for enabling ground users in a non-functional area (NFA) or disaster area to communicate. All the base stations in the disaster area may be partially or fully damaged due to the natural calamity. Device-to-device (D2D) communication can be a viable solution for immediate connection between users in an NFA. We propose a UAV-assisted multi-hop D2D communication following a hybrid power-time switching (PTS) in this paper. Moreover, a D2D user of a cluster can communicate with another D2D user in a different cluster through UAVs. However, D2D users can harvest energy from their respective ad hoc energy stations and forward the information to the nearby D2D user following a hybrid PTS-based strategy. We propose a time frame for the same and show a node-based energy harvesting strategy. The expressions of outage probability, throughput, end-to-end energy consumption, and energy efficiency are developed for the Rician and Nakagami-m faded channel. The impact of several network parameters such as energy harvesting factor, energy harvesting efficiency, and fading parameter on the network performance is also indicated.     

Simultaneous wireless information and power transfer in heterogeneous cellular networks with underlay D2D communication

Wireless Networks - Device to device (D2D) communication that provides high data rate proximity based direct communication between users, along with simultaneous wireless information and power...     

Power allocation for device-to-device communication underlaying cellular networks under a probabilistic eavesdropping scenario

In this paper, we focus on the issue of security due to the open structure of the D2D Communication Underlaying Cellular Networks. In such an open scenario, the problem of interference is very serious. But luckily, the interference can be helpful from a perspective of the physical layer security. The interference caused by D2D communication could be helpful against eavesdroppers to enhance the secure communication of the cellular users when the value of the interference is proper. Note this, the physical layer security of the cellular users can be enhanced with the proper interference management based on the power allocation in D2D communication underlaying cellular networks in a probabilistic eavesdropping scenario. The problem is modeled as a Stackelberg game model. In the model, all cellular users are modeled as followers while the D2D pair is modeled as leader. A semi-centralized power allocation algorithm is proposed to converge to the Stackelberg Equilibrium. And the equilibrium is the final power allocation scheme we want. It is proved that the proposed algorithm can conclude in finite-time iterations. Numerical simulation results show that our proposed power allocation algorithm can obtain larger secrecy data rate, than the other two power allocation algorithms.     

D2D通信中一种资源分配与功率控制结合的方案

以underlay方式工作的D2D(Device-to-Device)通信通过资源共享复用蜂窝网络中的资源,在提高系统资源利用率的同时,对已有蜂窝链路带来了同频干扰。为了减小因无线资源复用带来的干扰,提出了一种资源分配与功率控制相结合的方法。以最小化系统干扰为目的,通过在D2 D链路之间合理地分配资源,保证了蜂窝链路的通信质量;同时动态地调整D2 D链路的发射功率,在保证相应蜂窝链路干扰可控的情况下,合理提高了D2 D链路的通信质量。仿真结果表明,与现有方案相比,所提出的算法能够有效地提高D2 D通信与蜂窝用户共存场景下的系统性能。     

Research on maximizing energy efficiency for relay-aided D2D communication

In order to optimize the energy efficiency for relay-aided D2D communication underlaying cellular network,an algorithm was proposed while guaranteeing the quality of service of D2D users and cellular users.Firstly,the problem was formulated as a mixed integer nonlinear fractional programming problem,with the goal of maximizing the energy efficiency of all D2D users.Then,the maximizing energy efficiency problem was divided into three sub-problems,such as power allocation,relay selection and subcarrier assignment.Finally,the power allocation problem,the relay selection problem and the subcarrier assignment problem were addressed by Dinkelbach method and Lagrange multiplier method,Q-learning and Hungarian algorithm,respectively.The simulation results show that the proposed algorithm can improve the total energy efficiency of D2D users compared with existing algorithms.