Browsing by Author "Chen, Kuo-Ming"

Now showing 1 - 3 of 3

Lifetime Maximization for Uplink Transmission in UAV-Enabled Wireless Networks
(2019-01-01)
Chen, Kuo-Ming
;
Chang, Tsung-Hui
;
Lee, Ta-Sung
;
交大名義發表
;
電信工程研究所
The use of unmanned aerial vehicles (UAVs) as aerial wireless base stations has been recognized as an effective approach to on-demand deployment for providing services during a temporary event or emergency situation. High UAV mobility can be fully utilized to create line-of-sight connection and alleviate cross-link interference. While most of the prior works have studied UAV deployment, trajectory design and resource allocation strategies for improving the network throughput or energy efficiency, in this paper, we are interested in prolonging the lifetime of ground users for communications. The lifetime is defined as the communication time for the ground user before its battery is exhausted. We consider a frequency division multiplexing (FDM) uplink system where the ground users are served by multiple UAVs. We formulate a joint user association, power control, bandwidth allocation and UAV deployment problem for lifetime maximization, and propose an efficient approximation algorithm through judicious problem reformulation and successive convex approximation (SCA) techniques. For the scenario with only a single UAV, we show that the problem can be globally solved by simple bisection. Simulation results are presented to demonstrate that the proposed algorithms can achieve near-optimal performance and greatly outperform the heuristic methods.
Low-Complexity Beam Selection for Hybrid Precoded Multi-User mmWave Communications
(2018-01-01)
Chen, Kuo-Ming
;
Pan, Yun-Han
;
Lee, Ta-Sung
;
交大名義發表
;
電信工程研究所
Communications using the millimeter wave (mmWave) spectrum are a mainstream technology of the next generation systems. However, the mmWave band will experience much more propagation loss than a low frequency band. Therefore, a mmWave system will adopt beamforming techniques to compensate the high propagation. Moreover, hybrid beamforming which combines analog precoder and digital beamforming is a potential candidate for multi-input multi-output (MEMO) systems with massive scale for mmWave hand because of its low hardware complexity. In this paper, we propose a novel beam selection method that ensures the service quality of user equipment (LIE) and mitigates any interference between equipments to provide near performance upper bound and the method overcomes the high costs and complexity of mmWave systems. We evaluate the advantage of the proposed method via sum-rate and complexity computations. Simulation results show that the proposed method can offer significant reductions for massive-scale MIMO mmWave systems. In general, we show that the proposed method achieves a high quality solution, which is almost the same as the performance upper hound.
Machine Learning Based Automatic Diagnosis in Mobile Communication Networks
(2019-10-01)
Chen, Kuo-Ming
;
Chang, Tsung-Hui
;
Wang, Kai-Cheng
;
Lee, Ta-Sung
;
交大名義發表
The self-healing function in self-organizing networks can not only detect the presence of fault conditions but also diagnose the root causes in a fully autonomous fashion. In this paper, we propose a machine learning based diagnosis algorithm that uses network condition indicators such as key performance indicators and performance management counters for network condition diagnosis. The proposed algorithm judiciously combines the classical supervised softmax neural network (SNN) and support vector machine (SVM), and therefore can be efficiently implemented by off-the-shelf tools while achieving promising diagnosis performance. In particular, the proposed algorithm combines the features extracted from SNN and SVM, and is able to robustly diagnose fault conditions with different levels of severity. Besides, the proposed algorithm can also handle complex scenarios where there is more than one fault condition present at the same time. Considering that data with labels of multiple faults are not available in general, we further propose a simple retraining procedure which allows the proposed algorithm to perform multi-fault diagnosis even when the training data are only single labeled. Simulation results demonstrate that the proposed algorithms provide desired diagnosis performance in both single-fault and multi-fault scenarios and outperform the traditional scoring based methods.