ICT Express最新文献

Federated learning (FL) has emerged as a promising distributed machine learning technique. It has the potential to play a key role in future Internet of Things (IoT) networks by ensuring the security and privacy of user data combined with efficient utilization of communication resources. This paper addresses the challenge of maximizing energy efficiency in FL systems. We employed simultaneous wireless information and power transfer (SWIPT) and multi-carrier non-orthogonal multiple access (MC-NOMA) techniques. Also, we jointly optimized power allocation and central processing unit (CPU) resource allocation to minimize latency-constrained energy consumption. We formulated an optimization problem using a Markov decision process (MDP) and utilized a deep deterministic policy gradient (DDPG) reinforcement learning algorithm to solve our MDP problem. We tested the proposed algorithm through extensive simulations and confirmed it converges in a stable manner and provides enhanced energy efficiency compared to conventional schemes.

Although estimating the azimuth using a geomagnetic sensor is very useful, the estimation error may be very large due to the surrounding geomagnetic disturbance. We proposed a novel method for preprocessing appropriately for geomagnetic and inertial sensor data to be suitable for the proposed Artificial Neural Network model and training method for the model. As a result, the probability of azimuth estimation error within 1 degree is 96.4% with regression estimation. For classification estimation, when the azimuth estimation probability is 90% or more, the probability that the azimuth estimation error is within 1 degree is 100%.

Digital twin (DT) technologies have been increasingly important and useful for wireless communications. In particular, to support soaring wireless traffic with limited frequency spectrum assigned to legacy cellular systems, efficient operation and management of wireless resources as well as preemptively prediction of future spectrum usage are crucially important. For such purpose, DT networks for current fourth-generation (4G) and fifth-generation (5G) networks are constructed in this paper, by simultaneously utilizing measurement data from user equipments (UEs) and geographical information and characteristics of 4G and 5G base stations (BSs) within a specific observation area. Representative case studies are provided to demonstrate the usefulness of DT enabled cellular network management and prediction. As a real or near real time DT application, the impact and benefit of dual connectivity and dynamic spectrum sharing between 4G and 5G networks are analyzed. As a non-real time DT application, long-term improvement of 5G networks such as densification of BSs, implementation of advanced multiple input and multiple output technologies, and assignment of additional spectrum are analyzed and compared.

Recently, QUIC for the secure and faster connections has standardized but it is unclear that QUIC can cope with website fingerprinting (WF), a technique to infer visited websites from network traffic, since most existing efforts targeted TCP-induced traffic. To this end, we propose a novel QUIC WF technique based on Automated Machine Learning (AutoML). In our approach, we revisit traffic features appeared in literature, but relies on an AutoML framework to achieve best practice without manual intervention. Through experiments, we show that our technique outperforms state-of-the-art WF techniques with an F1-score of 99.79% and a 20-precision of 92.60%.

The network of resource constraint devices, also known as the Low power and Lossy Networks (LLNs), constitutes the edge tire of the Internet of Things applications like smart homes, smart cities, and connected vehicles. The IPv6 Routing Protocol over Low power and lossy networks (RPL) ensures efficient routing in the edge tire of the IoT environment. However, RPL has inherent vulnerabilities that allow malicious insider entities to instigate several security attacks in the IoT network. As a result, the IoT networks suffer from resource depletion, performance degradation, and traffic disruption. Recent literature discusses several machine learning algorithms to detect one or more routing attacks. However, IoT infrastructures are expanding, and so are the attack surfaces. Therefore, it is essential to have a solution that can adapt to this change. This paper introduces a comprehensive framework to detect routing attacks within Low Power and Lossy Networks (LLNs). The proposed solution leverages deep learning by combining Restricted Boltzmann Machine (RBM) and Long Short-Term Memory (LSTM). The framework is trained on 11 network parameters to understand and predict normal network behavior. Anomalies, identified as deviations from the forecast trends, serve as indicators of potential routing attacks and thus address vulnerabilities in the RPL.

In this paper, we design some new LDPC-coded orthogonal modulation (OM) schemes for high data rate transmissions (HDRT) in the navigation satellite systems. We analyze their error-performance utilizing soft-decision bit metrics and compare them with those of L61 and L62 signals in the quasi-zenith satellite system (QZSS) for centimeter-level augmentation services (CLAS). Compare to the L62 signals of QZSS, both schemes have higher data rates (14.6% increase) and essentially the better error performance at high SNR region. At the region where frame error rate (FER) $=10^{-3}$, one of the proposed schemes has better error performance of 1.4 dB in terms of carrier-to-noise ratio $(C/N_0)$.

In this paper, we have investigated the performance of energy efficiency (EE) for Intelligent Transportation Systems (ITS), which recently emerged and advanced to preserve speed as well as safe transportation expansion via a cooperative IRS-relay network. To improve the EE, the relay model has been integrated with an IRS block consisting of a number of passive reflective elements. We analyze the ITS in terms of EE, and achievable rate, with different signal-to-noise ratio (SNR) values under Nakagami-m fading channel conditions that help the system to implement in a practical scenario. From the numerical results it is noticed that the EE for the only relay, IRS, and proposed cooperative relay-IRS-aided network at SNR value of 100 dBm is 30, 17, and 48 bits/joule respectively. In addition, we compare the impact of multi-IRS with the proposed cooperative IRS-relay and conventional relay-supported ITS. Simulation results show that both the proposed cooperative IRS-relay-aided ITS network and multi-IRS-aided network outperform the relay-assisted ITS with the increase in SNR.

Despite the growing interest in using deep reinforcement learning (DRL) for drone control, several challenges remain to be addressed, including issues with generalization across task variations and agent training (which requires significant computational power and time). When the agent’s input changes owing to the drone’s sensors or mission variations, significant retraining overhead is required to handle the changes in the input data pattern and the neural network architecture to accommodate the input data. These difficulties severely limit their applicability in dynamic real-world environments. In this paper, we propose an efficient DRL method that leverages the knowledge of the source agent to accelerate the training of the target agent under task variations. The proposed method consists of three phases: collecting training data for the target agent using the source agent, supervised pre-training of the target agent, and DRL-based fine-tuning. Experimental validation demonstrated a remarkable reduction in the training time (up to 94.29%), suggesting a potential avenue for the successful and efficient application of DRL in drone control.

Computing-aware networking (CAN) is introduced to unite the computing resources distributed in different platforms. This paper proposes a joint routing and resource allocation model to minimize the total operational cost in CAN. We formulate the problem as an integer linear programming problem. We introduce a polynomial-time algorithm for larger-size problems. The numerical results reveal that the introduced algorithm reduces the computation time 9.18 times, with increasing the objective no more than 4% compared to the optimal solution; the proposed model can reduce 70% of the total cost compared to a baseline adopting a two-stage strategy in our examined cases.

Open Radio Access Network (RAN) is an important architecture design shift for 5G and next generation telecommunications networks. With open RAN, mobile network operators would be able to mix and match multi-vendor RAN solutions as long as the solutions comply with open standards. O-RAN Alliance is the global leader in standardizing the open RAN architecture, where RAN Intelligent Controller (RIC) is positioned centrally as the brain of a RAN to manage and optimize the RAN operations. Open-source projects play a key role in accelerating the adoption of open RAN architecture, especially the use of RIC. However, the fast pace of development and the lack of documentation in open-source projects create steep learning curve for beginners. In this paper, we first provide an overview of widely used open-source RIC projects and discuss their pros and cons. We then share our first-hand experience to use RIC in our campus 5G network that consists of commercial-grade RAN solutions. In particular, we developed a suite of three RAN control applications (i.e., energy efficiency, interference management, and predictive maintenance) on an open-source RIC, and we deploy and evaluate them on a commercial-grade 5G network in a university campus. For these RIC applications, we design and evaluate different ML models based on real-world data collected from our 5G network, which we publish together with this paper. Our experimental results show that AI-based RIC applications can achieve more than 90% of accuracy in inferring the situation of the RAN for each given task. Our energy-saving RIC application can reduce 65% of energy consumption of the RAN over a simulated period of one year. Our project also validates the feasibility to interfacing an open-source RIC with existing commercial-grade 5G solutions.