Wibowo Hardjawana

Alva Kosasih, Vincent Onasis, Vera Miloslavskaya et al.

Multi-user multiple-input multiple-output (MU-MIMO) systems can be used to meet high throughput requirements of 5G and beyond networks. A base station serves many users in an uplink MU-MIMO system, leading to a substantial multi-user interference (MUI). Designing a high-performance detector for dealing with a strong MUI is challenging. This paper analyses the performance degradation caused by the posterior distribution approximation used in the state-of-the-art message passing (MP) detectors in the presence of high MUI. We develop a graph neural network based framework to fine-tune the MP detectors' cavity distributions and thus improve the posterior distribution approximation in the MP detectors. We then propose two novel neural network based detectors which rely on the expectation propagation (EP) and Bayesian parallel interference cancellation (BPIC), referred to as the GEPNet and GPICNet detectors, respectively. The GEPNet detector maximizes detection performance, while GPICNet detector balances the performance and complexity. We provide proof of the permutation equivariance property, allowing the detectors to be trained only once, even in the systems with dynamic changes of the number of users. The simulation results show that the proposed GEPNet detector performance approaches maximum likelihood performance in various configurations and GPICNet detector doubles the multiplexing gain of BPIC detector.

Yuhong Liu, Changyang She, Yi Zhong et al.

In this paper, we aim to improve the Quality-of-Service (QoS) of Ultra-Reliability and Low-Latency Communications (URLLC) in interference-limited wireless networks. To obtain time diversity within the channel coherence time, we first put forward a random repetition scheme that randomizes the interference power. Then, we optimize the number of reserved slots and the number of repetitions for each packet to minimize the QoS violation probability, defined as the percentage of users that cannot achieve URLLC. We build a cascaded Random Edge Graph Neural Network (REGNN) to represent the repetition scheme and develop a model-free unsupervised learning method to train it. We analyze the QoS violation probability using stochastic geometry in a symmetric scenario and apply a model-based Exhaustive Search (ES) method to find the optimal solution. Simulation results show that in the symmetric scenario, the QoS violation probabilities achieved by the model-free learning method and the model-based ES method are nearly the same. In more general scenarios, the cascaded REGNN generalizes very well in wireless networks with different scales, network topologies, cell densities, and frequency reuse factors. It outperforms the model-based ES method in the presence of the model mismatch.

Zhouyou Gu, Branka Vucetic, Kishore Chikkam et al.

Restricted access window (RAW) in Wi-Fi 802.11ah networks manages contention and interference by grouping users and allocating periodic time slots for each group's transmissions. We will find the optimal user grouping decisions in RAW to maximize the network's worst-case user throughput. We review existing user grouping approaches and highlight their performance limitations in the above problem. We propose formulating user grouping as a graph construction problem where vertices represent users and edge weights indicate the contention and interference. This formulation leverages the graph's max cut to group users and optimizes edge weights to construct the optimal graph whose max cut yields the optimal grouping decisions. To achieve this optimal graph construction, we design an actor-critic graph representation learning (AC-GRL) algorithm. Specifically, the actor neural network (NN) is trained to estimate the optimal graph's edge weights using path losses between users and access points. A graph cut procedure uses semidefinite programming to solve the max cut efficiently and return the grouping decisions for the given weights. The critic NN approximates user throughput achieved by the above-returned decisions and is used to improve the actor. Additionally, we present an architecture that uses the online-measured throughput and path losses to fine-tune the decisions in response to changes in user populations and their locations. Simulations show that our methods achieve $30\%\sim80\%$ higher worst-case user throughput than the existing approaches and that the proposed architecture can further improve the worst-case user throughput by $5\%\sim30\%$ while ensuring timely updates of grouping decisions.

Zhouyou Gu, Changyang She, Wibowo Hardjawana et al.

In this paper, we develop a knowledge-assisted deep reinforcement learning (DRL) algorithm to design wireless schedulers in the fifth-generation (5G) cellular networks with time-sensitive traffic. Since the scheduling policy is a deterministic mapping from channel and queue states to scheduling actions, it can be optimized by using deep deterministic policy gradient (DDPG). We show that a straightforward implementation of DDPG converges slowly, has a poor quality-of-service (QoS) performance, and cannot be implemented in real-world 5G systems, which are non-stationary in general. To address these issues, we propose a theoretical DRL framework, where theoretical models from wireless communications are used to formulate a Markov decision process in DRL. To reduce the convergence time and improve the QoS of each user, we design a knowledge-assisted DDPG (K-DDPG) that exploits expert knowledge of the scheduler design problem, such as the knowledge of the QoS, the target scheduling policy, and the importance of each training sample, determined by the approximation error of the value function and the number of packet losses. Furthermore, we develop an architecture for online training and inference, where K-DDPG initializes the scheduler off-line and then fine-tunes the scheduler online to handle the mismatch between off-line simulations and non-stationary real-world systems. Simulation results show that our approach reduces the convergence time of DDPG significantly and achieves better QoS than existing schedulers (reducing 30% ~ 50% packet losses). Experimental results show that with off-line initialization, our approach achieves better initial QoS than random initialization and the online fine-tuning converges in few minutes.

Rui Dong, Changyang She, Wibowo Hardjawana et al.

To accommodate diverse Quality-of-Service (QoS) requirements in the 5th generation cellular networks, base stations need real-time optimization of radio resources in time-varying network conditions. This brings high computing overheads and long processing delays. In this work, we develop a deep learning framework to approximate the optimal resource allocation policy that minimizes the total power consumption of a base station by optimizing bandwidth and transmit power allocation. We find that a fully-connected neural network (NN) cannot fully guarantee the QoS requirements due to the approximation errors and quantization errors of the numbers of subcarriers. To tackle this problem, we propose a cascaded structure of NNs, where the first NN approximates the optimal bandwidth allocation, and the second NN outputs the transmit power required to satisfy the QoS requirement with given bandwidth allocation. Considering that the distribution of wireless channels and the types of services in the wireless networks are non-stationary, we apply deep transfer learning to update NNs in non-stationary wireless networks. Simulation results validate that the cascaded NNs outperform the fully connected NN in terms of QoS guarantee. In addition, deep transfer learning can reduce the number of training samples required to train the NNs remarkably.

Changyang She, Rui Dong, Zhouyou Gu et al.

In the future 6th generation networks, ultra-reliable and low-latency communications (URLLC) will lay the foundation for emerging mission-critical applications that have stringent requirements on end-to-end delay and reliability. Existing works on URLLC are mainly based on theoretical models and assumptions. The model-based solutions provide useful insights, but cannot be directly implemented in practice. In this article, we first summarize how to apply data-driven supervised deep learning and deep reinforcement learning in URLLC, and discuss some open problems of these methods. To address these open problems, we develop a multi-level architecture that enables device intelligence, edge intelligence, and cloud intelligence for URLLC. The basic idea is to merge theoretical models and real-world data in analyzing the latency and reliability and training deep neural networks (DNNs). Deep transfer learning is adopted in the architecture to fine-tune the pre-trained DNNs in non-stationary networks. Further considering that the computing capacity at each user and each mobile edge computing server is limited, federated learning is applied to improve the learning efficiency. Finally, we provide some experimental and simulation results and discuss some future directions.

Rui Dong, Changyang She, Wibowo Hardjawana et al.

In this work, we consider a mobile edge computing system with both ultra-reliable and low-latency communications services and delay tolerant services. We aim to minimize the normalized energy consumption, defined as the energy consumption per bit, by optimizing user association, resource allocation, and offloading probabilities subject to the quality-of-service requirements. The user association is managed by the mobility management entity (MME), while resource allocation and offloading probabilities are determined by each access point (AP). We propose a deep learning (DL) architecture, where a digital twin of the real network environment is used to train the DL algorithm off-line at a central server. From the pre-trained deep neural network (DNN), the MME can obtain user association scheme in a real-time manner. Considering that real networks are not static, the digital twin monitors the variation of real networks and updates the DNN accordingly. For a given user association scheme, we propose an optimization algorithm to find the optimal resource allocation and offloading probabilities at each AP. Simulation results show that our method can achieve lower normalized energy consumption with less computation complexity compared with an existing method and approach to the performance of the global optimal solution.