Browsing by Author "Li, Jiandong"
Now showing 1 - 2 of 2
- Results Per Page
- Sort Options
Item Distributed Interference-Aware Power Control in Ultra-Dense Small Cell Networks: A Robust Mean Field Game(IEEE Access, 1/26/2018) Yang, Chungang; Dai, Haoxiang; Li, Jiandong; Zhang, Yue; Han, ZhuIn ultra-dense small cell networks, interference mitigation is very important due to severe interference. Interference dynamics caused by time-varying environment should be aware and characterized when an interference-aware power control policy is designed to mitigate interference. Meanwhile, interference perception should not be naturally assumed to have complete information with certainty. Generally, it is known that a generic player will react to all the players actions and states in a power control game, which involves huge interference-related information exchange with dynamics and uncertainties. Therefore, to reduce requirements of complete information, we formulate a robust power control mean field game taking the uncertainties of both state dynamics and cost functions into consideration. To achieve the robust power control, we regard the power control problem as a game with players whose individual states are combined by a disturbance term and a Brownian motion. We derive the robust Fokker-Planck-Kolmogorov and Hamilton-Jacobi-Bellman equations, and based on which we propose the robust interference-aware power control algorithm. Simulation results demonstrate the improved performance and the robustness of the proposed algorithm.Item Intelligent User-Centric Network Selection: A Model-Driven Reinforcement Learning Framework(IEEE Access, 2/27/2019) Wang, Xinwei; Li, Jiandong; Wang, Lingxia; Yang, Chungang; Han, ZhuUltra-dense heterogeneous networks, as a novel network architecture in the fifth-generation mobile communication system (5G), promise ubiquitous connectivity and smooth experience, which take advantage of multiple radio access technologies (RATs), such as WiFi, UMTS, LTE, and WiMAX. However, the dense environment of multi-RATs challenges the network selection because of the more frequent and complex decision process along with increased complexity. Introducing artificial intelligence to ultra-dense heterogeneous networks can improve the way we address network selection today, and can execute efficient and intelligent network selection. Whereas, there still exist difficulties to be noted. On one hand, the contradiction between real-time communications and time-consuming learning is exacerbated, which can result in slow convergence. On the other hand, the black-box learning mode suffers from oscillation due to the diversity of multi-RATs, which can result in arbitrary convergence. In this paper, we propose a model-driven framework with a joint off-line and on-line way, which is able to achieve fast and optimal network selection through an alliance of machine learning and game theory. Further, we implement a distributed algorithm at the user side based on the proposed framework, which can reduce the number of frequent switching, increase the possibility of gainful switching, and provide the individual service. The simulation results confirm the performance of the algorithm in accelerating convergence rate, boosting user experience, and improving resource utilization.