/pdf/graph-based-deep-learning-for-communication-networks-a-2v9rx0ny.pdf

Graph-based deep learning for communication networks: A survey

Communication networks are important infrastructures in contemporary society. There are still many challenges that are not fully solved and new solutions are proposed continuously in this active research area. In recent years, to model the network topology, graph-based deep learning has achieved state-of-the-art performance in a series of problems in communication networks. In this survey, we review the rapidly growing body of research using different graph-based deep learning models, e.g. graph convolutional and graph attention networks, in various problems from different communication networks, e.g. wireless networks, wired networks, and software-defined networks. We also present a well-organized list of the problem and solution for each study and identify future research directions. To the best of our knowledge, this paper is the first survey that focuses on the application of graph-based deep learning methods in communication networks. To track the follow-up research, a public GitHub repository is created, where the relevant papers will be updated continuously.

Graph-based Deep Learning for Communication Networks: A Survey.

https://hal.archives-ouvertes.fr/hal-03326474/document

Deep reinforcement learning techniques for vehicular networks: Recent advances and future trends towards 6G

Cellular networks are important for the success of modern communication systems, which support billions of mobile users and devices. Powered by artificial intelligence techniques, cellular networks are becoming increasingly smarter, and cellular traffic prediction is an important basis for realizing various applications that have originated from this trend. In this survey, we review the relevant studies on cellular traffic prediction and classify the prediction problems as the temporal and spatiotemporal prediction problems. The prediction models with artificial intelligence are categorized into statistical, machine learning, and deep learning models and then compared. Various applications based on cellular traffic prediction are summarized along with their current progress. The potential research directions are pointed out for future research. To the best of our knowledge, this paper is the first comprehensive survey on cellular traffic prediction. 

Cellular traffic prediction with machine learning: A survey

Future Internet involves several emerging technologies such as 5G and beyond 5G networks, vehicular networks, unmanned aerial vehicle (UAV) networks, and Internet of Things (IoTs). Moreover, the future Internet becomes heterogeneous and decentralized with a large number of involved network entities. Each entity may need to make its local decision to improve the network performance under dynamic and uncertain network environments. Standard learning algorithms such as single-agent Reinforcement Learning (RL) or Deep Reinforcement Learning (DRL) have been recently used to enable each network entity as an agent to learn an optimal decision-making policy adaptively through interacting with the unknown environments. However, such an algorithm fails to model the cooperations or competitions among network entities, and simply treats other entities as a part of the environment that may result in the non-stationarity issue. Multi-agent Reinforcement Learning (MARL) allows each network entity to learn its optimal policy by observing not only the environments but also other entities&#x2019; policies. As a result, MARL can significantly improve the learning efficiency of the network entities, and it has been recently used to solve various issues in the emerging networks. In this paper, we thus review the applications of MARL in emerging networks. In particular, we provide a tutorial of MARL and a comprehensive survey of applications of MARL in next-generation Internet. In particular, we first introduce single-agent RL and MARL. Then, we review a number of applications of MARL to solve emerging issues in the future Internet. The issues consist of network access, transmit power control, computation offloading, content caching, packet routing, trajectory design for UAV-aided networks, and network security issues. Finally, we discuss the challenges, open issues, and future directions related to the applications of MARL in the future Internet. 

Applications of Multi-Agent Reinforcement Learning in Future Internet: A Comprehensive Survey

A 5G network is the key driving factor in the development of vehicle-to-vehicle (V2V) communication technology, and V2V communication in 5G has recently attracted great interest. In the V2V communication network, users can choose different transmission modes and power levels for communication, to guarantee their quality-of-service (QoS), high capacity of vehicle-to-infrastructure (V2I) links and ultra-reliability of V2Vlinks. Aiming atV2V communication mode selection and power adaptation in 5G communication networks, a reinforcement learning (RL) framework based on slow fading parameters and statistical information is proposed. In this paper, our objective is to maximize the total capacity of V2I links while guaranteeing the strict transmission delay and reliability constraints of V2V links. Considering the fast channel variations and the continuous-valued state in a high mobility vehicular environment, we use a multi-agent double deep Q-learning (DDQN) algorithm. Each V2V link is considered as an agent, learning the optimal policy with the updated Q-network by interacting with the environment. Experiments verify the convergence of our algorithm. The simulation results show that the proposed scheme can significantly optimize the total capacity of the V2I links and ensure the latency and reliability requirements of the V2V links.

A Reinforcement Learning Method for Joint Mode Selection and Power Adaptation in the V2V Communication Network in 5G

Cognitive radio (CR) is a critical technique to solve the conflict between the explosive growth of traffic and severe spectrum scarcity. Reasonable radio resource allocation with CR can effectively achieve spectrum sharing and co-channel interference (CCI) mitigation. In this paper, we propose a joint channel selection and power adaptation scheme for the underlay cognitive radio network (CRN), maximizing the data rate of all secondary users (SUs) while guaranteeing the quality of service (QoS) of primary users (PUs). To exploit the underlying topology of CRNs, we model the communication network as dynamic graphs, and the random walk is used to imitate the users’ movements. Considering the lack of accurate channel state information (CSI), we use the user distance distribution contained in the graph to estimate CSI. Moreover, the graph convolutional network (GCN) is employed to extract the crucial interference features. Further, an end-to-end learning model is designed to implement the following resource allocation task to avoid the split with mismatched features and tasks. Finally, the deep reinforcement learning (DRL) framework is adopted for model learning, to explore the optimal resource allocation strategy. The simulation results verify the feasibility and convergence of the proposed scheme, and prove that its performance is significantly improved.

A Graph Convolutional Network-Based Deep Reinforcement Learning Approach for Resource Allocation in a Cognitive Radio Network.

With digitization and globalization in the era of 5G and beyond, research on high-throughput satellites (HTS) to increase communication capacity and improve flexibility is becoming essential. To achieve efficient resource utilization and dynamic traffic demand matching, the multi-dimensional resource management (MDRM) problem of the HTS communication system has been studied in this paper. Since the MDRM problem is a non-convex mixed integer problem, we decompose it into two tractable sub-problems. First, the beam-domain resource configuration problem is formed to enable on-demand coverage. Next, the user-domain resource allocation problem is modeled to enable on-demand communication. Considering the two-domain optimization problem, a two-stage framework is developed based on the combination of self-supervised learning and deep reinforcement learning. Specifically, in the first stage, a maximum co-channel interference based self-supervised learning method is proposed to perform traffic demand matching through demand awareness. In the second stage, a soft frequency reuse based proximal policy optimization approach is presented to further increase the system capacity through interference coordination. The simulation results demonstrate that our proposed two-stage algorithm outperforms the benchmark schemes in terms of spectrum efficiency and demand satisfaction.

Di Zhao

Papers

A Reinforcement Learning Method for Joint Mode Selection and Power Adaptation in the V2V Communication Network in 5G

A Graph Convolutional Network-Based Deep Reinforcement Learning Approach for Resource Allocation in a Cognitive Radio Network.

Flexible Resource Management in High-Throughput Satellite Communication Systems: A Two-Stage Machine Learning Framework