Browsing by Author "Cheng, Shao-Hung"

Now showing 1 - 6 of 6

Affinity Propagation Clustering for Interference Management in Aerial Small Cells
(2019-01-01)
Cheng, Shao-Hung
;
Chao, Yung-Sheng
;
Wang, Li-Chun
;
Tsai, Ang-Hsun
;
電機工程學系
The drone small cell (DSC) network has become a key technology for air-to-ground wireless communications in a variety of temporary or emergency situations. Based on mobile users, frequently changing DSC topologies have important challenges such as severe co-channel interference and limited battery capacity. However, temporarily dispatched drones cannot obtain labeled and historical data in advance, while they only obtain real-time operational data. The observed data can be analyzed by unsupervised learning methods to find useful information for resource management. In this paper, an interference-aware power control (IPC) framework is designed using affinity propagation clustering (APC). The APC method is one of the unsupervised learning methods. The numerical results show that our proposed IPC framework using the APC method can reduce system interference and significantly improve the energy efficiency of DSC networks.
An Integrated Affinity Propagation and Machine Learning Approach for Interference Management in Drone Base Stations
(2020-03-01)
Wang, Li-Chun
;
Chao, Yung-Sheng
;
Cheng, Shao-Hung
;
Han, Zhu
;
電機工程學系
Drone small cells (DSCs) can provide on-demand air-to-ground wireless communications in various unexpected situations, such as traffic jam or natural disasters. However, a DSC needs to face the challenges such as severe co-channel interference, limited battery capacity, and fast topology changes. Aiming to improve energy efficiency of DSCs and quality of services of customers, this paper presents a learning-based multiple drone management (LDM) framework by controlling the transmission power and the 3-dimension location of DSCs based on location data, and reference signal received power of users. Since the labeled throughput data are typically not available in emergency situations, we develop unsupervised learning DSC management techniques: 1) affinity propagation interference management scheme to mitigate interference and energy consumption, and 2) K-means position adjustment to adjust the new 3-dimension positions of drones. Our numerical results show that the proposed LDM framework combining with affinity propagation clustering and k-means clustering can enhance the energy efficiency of DSCs by 25% and the signal-to-interference-plus-noise ratio of ground users by 56%, respectively.
Bi-SON: Big-Data Self Organizing Network for Energy Efficient Ultra-Dense Small Cells
(2016-01-01)
Wang, Li-Chun
;
Cheng, Shao-Hung
;
Tsai, Ang-Hsun
;
電機工程學系
;
Department of Electrical and Computer Engineering
In this paper, we present a big-data self organizing network (Bi-SON) framework aiming to optimize energy efficiency of ultra-dense small cells. Although small cell can enhance the capacity of cellular mobile networks, ultra-dense small cells suffer from severe interference and poor energy efficiency. The self organizing network (SON) can automatically manage and optimize the system performance. However, current SON-enable mechanisms mostly focus on indoor femtocells. Our proposed Bi-SON suggests a data flow framework from data collection, analysis and optimization to reconfiguration. We adopt the statistics analysis approach to determine the optimal system parameters to improve the energy efficiency of a huge number of outdoor small cells. The Bi-SON mechanism periodically collects the management data of small cells, e.g. transmission power, reference signal receiving power and the number of users per cell. We find that simple sorting and filtering data analysis from huge number of small cells can already effectively find the almost optimal solution. Our simulation results show that Bi-SON can improve throughput and energy efficiency by 50% and 135% respectively, compared to the scheme without energy saving approach.
Data-Driven Power Control of Ultra-Dense Femtocells: A Clustering Based Approach
(2017-01-01)
Wang, Li-Chun
;
Cheng, Shao-Hung
;
Tsai, Ang-Hsun
;
電機工程學系
;
Department of Electrical and Computer Engineering
In this paper we present a data-driven power control (DDPC) approach to improve total cell throughput and energy efficiency of ultra-dense femtocells. Although femtocells can increase the capacity and coverage in an indoor environment, ultra-dense femtocells may consume a lot of energy and generate severe interference. We investigate a data-driven clustering approach to reduce co-tier interference among femtocells in a dense deployment scenario. The proposed DDPC approach periodically collects the operation data of dense femtocells, including reference signal received power (RSRP) from each user, the transmission power and the number of users per femtocell, and so on. The collected data are processed via the affinity propagation (AP) clustering algorithm to determine the cluster centers to perform power control. The AP clustering algorithm can automatically determine appropriate the number of clusters and the corresponding cluster centers for various femtocell densities. Simulation results show that the proposed DDPC approach can increase 41% higher total cell throughput and 64% higher energy efficiency respectively, compared to the approach without power control in the ultra-dense femtocells.
Data-Driven Resource Management for Ultra-Dense Small Cells: An Affinity Propagation Clustering Approach
(2019-07-01)
Wang, Li-Chun
;
Cheng, Shao-Hung
;
電機工程學系
;
Department of Electrical and Computer Engineering
Deploying dense small cells is the key to providing high capacity, but raise the serious issue of energy consumption and inter-cell interference. To understand the behaviors of ultra-dense small cells (UDSC) with dynamic interference and traffic patterns, this paper presents a data-driven resource management (DDRM) framework to implement power control and channel rearrangement in UDSC. We find that the inter-cell interference can be used to describe the affinity of cells. Thus, we propose an unsupervised learning algorithm for UDSC, called affinity propagation power control (APPC) mechanism. In principle, APPC first groups small cells into different clusters and identifies cluster centers. Next, the transmission power of a cluster center is decreased to reduce the interference to the neighboring cells' users in this cluster. Since lowering transmission power of a cluster center cell may cause the performance degradation to the users at the cell edge, a victim-aware channel rearrangement (VACR) mechanism is further designed to adjust the channel usage bandwidth of the neighboring cells in order to guarantee the quality of service of these victimized users. Our simulation results show that the DDRM framework can significantly improve energy efficiency and throughput in UDSC compared to the existing approaches.
Self-Organizing Ultra-Dense Small Cells in Dynamic Environments: A Data-Driven Approach
(2019-06-01)
Wang, Li-Chun
;
Cheng, Shao-Hung
;
電機工程學系
;
Department of Electrical and Computer Engineering
This paper presents a data-driven biadaptive selforganizing network (Bi-SON) for ultra-dense small cells (UDSC), which can improve energy efficiency and reduce interference in dynamic environments, taking account of cell switching ON/OFF, transmission power adjustment, and traffic loads simultaneously. In the first adaptation of Bi-SON, a joint traffic load and interference aware cell ranking mechanism first determines the necessary active small cells based on traffic loads, and then ranks all the active small cells based on their carried traffic load and resulting interference. Top ranked cells will transmit at the maximum power. The last ranked K cells will adjust the transmission power for interference reduction in the second adaptation function of Bi-SON, while maintaining the required quality of service. According to a polynomial regression learning approach, the total system throughput of UDSC is characterized as a function of K. Compared to the baseline case when all the cells transmit with the maximum power, our proposed Bi-SON framework can improve the throughput and energy efficiency of UDSC by 73% and 169%, respectively. However, the pure switching ON/OFF approach can only improve the throughput and the energy efficiency of UDSC by 52% and 115%, respectively. As demonstrated, even with a simple power adaptation algorithm, a learningbased Bi-SON framework can improve the performance of UDSC by taking advantage of the pervasive availability of voluminous data.