{"title":"Multi-Agent Reinforcement Learning-Based User Pairing in Multi-Carrier NOMA Systems","authors":"Shaoyang Wang, Tiejun Lv, Xuewei Zhang","doi":"10.1109/ICCW.2019.8757016","DOIUrl":"https://doi.org/10.1109/ICCW.2019.8757016","url":null,"abstract":"This paper investigates the problem of user pairing in multi-carrier non-orthogonal multiple access (MC-NOMA) systems. Firstly, the hard channel capacity and soft channel capacity are presented. The former depicts the transmission capability of the system that depends on the channel conditions, and the latter refers to the effective throughput of the system that is determined by the actual user demands. Then, two optimization problems to maximize the hard and soft channel capacities are established, respectively. Inspired by the multiagent deep reinforcement learning (MADRL) and convolutional neural network, the user paring network (UP-Net), based on the cooperative game and deep deterministic policy gradient, is designed for solving the optimization problems. Simulation results demonstrate that the performance of the designed UP-Net is comparable to that obtained from the exhaustive search method via the end-to-end low complexity method, which is superior to the common method, and corroborate that the UP-Net focuses more on the actual user demands to improve the soft channel capacity. Additionally and more importantly, the paper makes a useful exploration on the use of MADRL to solve the resource allocation problems in communication systems. Meanwhile, the design method has strong universality and can be easily extended to other issues.","PeriodicalId":426086,"journal":{"name":"2019 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131717387","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Data-Driven Beam Selection for mmWave Communications with Machine and Deep Learning: An Angle of Arrival-Based Approach","authors":"C. Antón-Haro, X. Mestre","doi":"10.1109/ICCW.2019.8756991","DOIUrl":"https://doi.org/10.1109/ICCW.2019.8756991","url":null,"abstract":"This paper investigates the applicability of deep and machine learning techniques to perform beam selection in the uplink of a mmWave communication system. Specifically, we consider a hybrid beamforming setup comprising an analog beamforming (ABF) network followed by a zero-forcing baseband processing block. The goal is to select the optimal configuration for the ABF network bsed on the estimated angles-of-arrival (AoAs) and received powers. To that aim, we consider three machine/deep learning schemes: k-nearest neighbors (kNN), support vector classifiers (SVC), and the multilayer perceptron (MLP). We conduct an extensive performance evaluation to assess the impact of using the Capon or MUSIC methods to estimate the AoAs and powers, the size of the training dataset, the number of beamformers in the codebook, their beamwidth, or the number of active users. Computer simulations reveal that performance, in terms of classification accuracy and sum-rate, is very close to that achievable via exhaustive search.","PeriodicalId":426086,"journal":{"name":"2019 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127763315","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"UAV Beamwidth Design for Ultra-Reliable and Low-Latency Communications with NOMA","authors":"Aitong Han, Tiejun Lv, Xuewei Zhang","doi":"10.1109/ICCW.2019.8756803","DOIUrl":"https://doi.org/10.1109/ICCW.2019.8756803","url":null,"abstract":"In this paper, we investigate the non-orthogonal multiple access (NOMA) based unmanned aerial vehicle (UAV) assisted ultra-reliable and low-latency communications (URLLC) without the presence of base station. To achieve URLLC, we minimize the block error probability by appropriately reducing the beamwidth. Since the user grouping approach can reduce the coverage of user-free area to achieve the beamwidth reduction by only covering the users in each group, we propose two user grouping algorithms for UAV-assisted NOMA transmission. The first one is the improved K-means algorithm. It needs to set the number of groups in advance and has good performance in solving the problem considered in this paper. The second one is an extended affinity propagation (AP) clustering algorithm. This algorithm is easier to implement than the first one because it does not need to pre-define the number of groups, but the performance is inferior to the first algorithm. After user grouping, we introduce a location-based beamwidth design for each group to further minimize the beamwidth and solve the optimization problem. Numerical results show that the performance of the proposed user grouping algorithms with the location-based beamwidth design schemes are superior to the benchmark schemes under the URLLC constraints.","PeriodicalId":426086,"journal":{"name":"2019 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130356017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"User Scheduling for Full-Duplex Cellular Networks","authors":"Bin Li, Cheng Li, Chenchen Yang, Bin Xia","doi":"10.1109/ICCW.2019.8757172","DOIUrl":"https://doi.org/10.1109/ICCW.2019.8757172","url":null,"abstract":"In this paper, the problem of user scheduling in full-duplex (FD) wireless cellular networks is considered. Considering that without modestly planning, the inter-user interference in FD transmissions limits the potential FD gains. User scheduling becomes a significant issue in FD systems. Different from previous works where users are scheduled according to the first-come first-served rule, we propose a user selection scheduling scheme to alleviate the inter-user interference. Then, probabilities of base stations (BSs) operating in FD, half-duplex (HD) downlink, HD uplink and idle modes are calculated so as to obtain the corresponding interference. Moreover, we analyze the performance of the system with the proposed scheduling scheme in terms of outage probability and average sum rate. The simulation results show that downlink outage probability is improved compared to that with the first-come first-served rule.","PeriodicalId":426086,"journal":{"name":"2019 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128636333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Ultrareliable SWIPT using Unscheduled Short Packet Transmissions","authors":"S. Kisseleff, S. Chatzinotas, B. Ottersten","doi":"10.1109/ICCW.2019.8756657","DOIUrl":"https://doi.org/10.1109/ICCW.2019.8756657","url":null,"abstract":"Large communication networks, e.g. Internet of Things (IoT), are known to be vulnerable to the co-channel interference from simultaneous transmissions. In the recent time, this problem has been extensively studied in various contexts. Due to a potentially very long duty cycle, orthogonal multiple access techniques are not well suited for such schemes. Instead, random medium access (RMA) seems promising, since it guarantees a lower bound for the network throughput even in presence of an infinite number of simultaneous transmissions while reducing the average length of the duty cycle. Such an RMA scheme is based on transmission of short data packets with unknown scheduling. Of course, a reliable symbol detection for this type of communication is very challenging not only due to a large amount of interference from the adjacent nodes, but also because of the uncertainty related to the presence or absence of overlapping packets. Interestingly, with increasing number of network nodes also the amount of energy, which can be harvested from the received signal, increases. This is especially beneficial for powering of a relay device, which may utilize the energy for further information processing and retransmission. In this paper, we address the design of a simultaneous information and power transfer scheme based on unscheduled short packet transmissions for ultrareliable communication.","PeriodicalId":426086,"journal":{"name":"2019 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":"48 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120903827","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Exploiting NLOS Bias Correlation in Cooperative Localization","authors":"Yunlong Wang, Kai Gu, Ying Wu, Wei Dai, Yuan Shen","doi":"10.1109/ICCW.2019.8756706","DOIUrl":"https://doi.org/10.1109/ICCW.2019.8756706","url":null,"abstract":"Network localization is challenging in line-of-sight (LOS)/non-line-of-sight (NLOS) mixed environments since the statistics information of NLOS biases is generally unknown. In this paper, we investigate the cooperative localization in LOS/NLOS mixed environments with spatial correlation. A maximum-likelihood estimator (MLE) based algorithm for joint agent localization and bias estimation is proposed without knowing statistics information of NLOS biases. The non-convex MLE is relaxed into a semidefinite programming and spatial correlation constraints are used to improve the localization accuracy. Furthermore, a bias-induced optimization is implemented to improve the localization performance by identifying LOS links. Finally, numerical results validate our theoretical analysis and the performance of the proposed algorithm.","PeriodicalId":426086,"journal":{"name":"2019 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127090515","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Management Optimization of Mobile Edge Computing (MEC) in 5G Networks","authors":"Zhi Wang, Yigang Cai","doi":"10.1109/ICCW.2019.8756650","DOIUrl":"https://doi.org/10.1109/ICCW.2019.8756650","url":null,"abstract":"MEC is shaping a new era for communications. Operation and management of MEC with 5G network face new challenges. This paper presents several key areas of MEC management optimization with intelligent controls including MEC dynamic user profiles, QoS policy and control, credit quota control and third-party application control.","PeriodicalId":426086,"journal":{"name":"2019 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124933940","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An Effective Suppression Method for 802.11 Transmission with Experimental Verification","authors":"Zhiwen Liu, Peiliang Zuo, Tao Peng, Wenbo Wang","doi":"10.1109/ICCW.2019.8756992","DOIUrl":"https://doi.org/10.1109/ICCW.2019.8756992","url":null,"abstract":"Extensive, unmanaged IEEE 802.11 deployments may become sources of interference in emergency communications scenarios. In this paper, we consider the goal of protecting public safety by suppressing the transmission of 802.11. In order to develop a suppression method that can be effective in practice, we propose a new spoofing method which utilizes the channel detection mechanism in physical layer of 802.11 protocol. Besides, numerous experiments are conducted for commercial off-the-shelf (COTS) 802.11 devices (i.e. WiFi). Based on the experiment results, we finally present a reasonable and efficient method for preventing WiFi transmission. Further experiments and analysis show that the proposed method is superior to the state of the art suppression methods in terms of energy consumption and applicability to all 802.11 devices.","PeriodicalId":426086,"journal":{"name":"2019 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125160896","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jincan Xin, Hui Gao, Yuande Tan, Ruohan Cao, Yueming Lu
{"title":"Energy-Efficient Power Control for Ultra-Dense Networks with Distributed Antenna Arrays","authors":"Jincan Xin, Hui Gao, Yuande Tan, Ruohan Cao, Yueming Lu","doi":"10.1109/ICCW.2019.8757032","DOIUrl":"https://doi.org/10.1109/ICCW.2019.8757032","url":null,"abstract":"We study the energy efficiency (EE) optimization problem of a ultra-dense small cell network. In each cell, based on the fog radio access network architecture, multiple distributed antenna arrays are connected to a mobile edge computing server to provide collaborative service to the users. We optimize the network EE by a novel distributed non-cooperative power control game with leakage interference-to-signal ratio constraints (NPG-LSC). Considering the backhaul power consumption, each cell independently optimizes its own EE while limiting the interference to other cells through the LSC. The proposed scheme enjoys lower complexity compared with the centralized method while achieving better network EE over the conventional game solution without leakage interference constraints. We prove that the formulated NPG-LSC scheme has a unique Nash equilibrium. Finally, simulation results show that the proposed scheme effectively improves the network EE.","PeriodicalId":426086,"journal":{"name":"2019 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":"395 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125281173","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Secrecy Transmission Capacity of Large-Scale UAV-Enabled Wireless Networks","authors":"Jianping Yao, Jie Xu","doi":"10.1109/ICCW.2019.8756908","DOIUrl":"https://doi.org/10.1109/ICCW.2019.8756908","url":null,"abstract":"This paper considers the secrecy transmission in a large-scale unmanned aerial vehicle (UAV)-enabled wireless network, in which a set of UAVs in the sky transmit confidential information to their respective legitimate receivers on the ground, in the presence of another set of randomly distributed suspicious ground eavesdroppers. We assume that the horizontal locations of legitimate receivers and eavesdroppers are distributed as two independent homogeneous Possion point processes (PPPs), and each of the UAVs is positioned exactly above its corresponding legitimate receiver for efficient secrecy communication. Furthermore, we consider an elevation-angle-dependent line-of-sight (LoS)/non-LoS (NLoS) path-loss model for air-to-ground (A2G) wireless channels and employ the wiretap code for secrecy transmission. Under this setup, we first characterize the secrecy communication performance (in terms of the connection probability (CP), secrecy outage probability (SOP), and secrecy transmission capacity (STC)) in mathematically tractable forms. Next, we optimize the system configurations (i.e., the wiretap code rates and UAV positioning altitude) to maximize the STC, subject to a maximum SOP constraint. Finally, we present numerical results to validate the theoretical analysis.","PeriodicalId":426086,"journal":{"name":"2019 IEEE International Conference on Communications Workshops (ICC Workshops)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126939539","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}