Data-Driven Resource Management for Dynamic Small Cells

• Main Authors: Cheng, Shao-Hung, 鄭紹宏
• Other Authors: Wang, Li-Chun
• Format: Others
• Language: en_US
• Published: 2018
• Online Access: http://ndltd.ncl.edu.tw/handle/u42z8k

博士 === 國立交通大學 === 電機工程學系 === 107 === In this dissertation, we present a data-driven Bi-adaptive Self Organizing Network (Bi-SON) for operator deployed ultra-dense small cell (UDSC) network, 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 (PR) 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 simple power adaptation algorithm, a learning-based Bi-SON framework can improve the performance of UDSC by taking advantage of the pervasive availability of voluminous data. In the second part, we present a data-driven resource management (DDRM) framework to implement power control and channel rearrangement in plug-and-play 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 plug-and-play 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. In the final part, based on the frequently changed interference of the dynamic DSC networks needs to be understood, we present a learning-based multiple drones management (LBDM) framework to collect operation data and implement power control and Drones position rearrangement. We consider that the DSCs may be temporarily dispatched for the emergency situation, in which only the instantly operation data can be observed. Thus, we propose that the unsupervised learning techniques are utilized to find the hidden information of observed data for determining power level and position of DSCs. The affinity propagation clustering (APC) and K-means clustering (KMC) both belong to the unsupervised learning approaches. Firstly, we use the APC with power control to mitigate interference and energy consumption; secondly, we apply the KMC to decide the new position of Drones for high communication quality of users. The numerical results present that our proposed LBDM framework obviously enhance the energy efficiency and the available signal-to-interference-plus-noise ratio. In summary, the main contribution of this dissertation is to solve the complicated issues of interference and energy efficiency in the UDSC and DSC networks. The proposed solutions significantly improve the total cell throughput and the energy efficiency, while guaranteeing the quality of services.