Spatial Deep Learning for Site-Specific Movement Optimization of Aerial Base Stations

Unmanned aerial vehicles (UAVs) can be utilized as aerial base stations (ABSs) to provide wireless connectivity for ground users (GUs) in various emergency scenarios. However, it is a NP-hard problem with exponential complexity in $M$ and $N$, in order to maximize the coverage rate of $M$ GUs by jointly placing $N$ ABSs with limited coverage range. The problem is further complicated when the coverage range becomes irregular due to site-specific blockages (e.g., buildings) on the air-ground channel, and/or when the GUs are moving. To address the above challenges, we study a multi-ABS movement optimization problem to maximize the average coverage rate of mobile GUs in a site-specific environment. The Spatial Deep Learning with Multi-dimensional Archive of Phenotypic Elites (SDL-ME) algorithm is proposed to tackle this challenging problem by 1) partitioning the complicated ABS movement problem into ABS placement sub-problems each spanning finite time horizon; 2) using an encoder-decoder deep neural network (DNN) as the emulator to capture the spatial correlation of ABSs/GUs and thereby reducing the cost of interaction with the actual environment; 3) employing the emulator to speed up a quality-diversity search for the optimal placement solution; and 4) proposing a planning-exploration-serving scheme for multi-ABS movement coordination. Numerical results demonstrate that the proposed approach significantly outperforms the benchmark Deep Reinforcement Learning (DRL)-based method and other two baselines in terms of average coverage rate, training time and/or sample efficiency. Moreover, with one-time training, our proposed method can be applied in scenarios where the number of ABSs/GUs dynamically changes on site and/or with different/varying GU speeds, which is thus more robust and flexible compared with conventional DRL-based methods.

IRS-Aided Sectorized Base Station Design and 3D Coverage Performance Analysis

Intelligent reflecting surface (IRS) is regarded as a revolutionary paradigm that can reconfigure the wireless propagation environment for enhancing the desired signal and/or weakening the interference, and thus improving the quality of service (QoS) for communication systems. In this paper, we propose an IRS-aided sectorized BS design where the IRS is mounted in front of a transmitter (TX) and reflects/reconfigures signal towards the desired user equipment (UE). Unlike prior works that address link-level analysis/optimization of IRS-aided systems, we focus on the system-level three-dimensional (3D) coverage performance in both single-/multiple-cell scenarios. To this end, a distance/angle-dependent 3D channel model is considered for UEs in the 3D space, as well as the non-isotropic TX beam pattern and IRS element radiation pattern (ERP), both of which affect the average channel power as well as the multi-path fading statistics. Based on the above, a general formula of received signal power in our design is obtained, along with derived power scaling laws and upper/lower bounds on the mean signal/interference power under IRS passive beamforming or random scattering. Numerical results validate our analysis and demonstrate that our proposed design outperforms the benchmark schemes with fixed BS antenna patterns or active 3D beamforming. In particular, for aerial UEs that suffer from strong inter-cell interference, the IRS-aided BS design provides much better QoS in terms of the ergodic throughput performance compared with benchmarks, thanks to the IRS-inherent double pathloss effect that helps weaken the interference.

Placement Optimization of Aerial Base Stations with Deep Reinforcement Learning

Unmanned aerial vehicles (UAVs) can be utilized as aerial base stations (ABSs) to assist terrestrial infrastructure for keeping wireless connectivity in various emergency scenarios. To maximize the coverage rate of N ground users (GUs) by jointly placing multiple ABSs with limited coverage range is known to be a NP-hard problem with exponential complexity in N. The problem is further complicated when the coverage range becomes irregular due to site-specific blockage (e.g., buildings) on the air-ground channel in the 3-dimensional (3D) space. To tackle this challenging problem, this paper applies the Deep Reinforcement Learning (DRL) method by 1) representing the state by a coverage bitmap to capture the spatial correlation of GUs/ABSs, whose dimension and associated neural network complexity is invariant with arbitrarily large N; and 2) designing the action and reward for the DRL agent to effectively learn from the dynamic interactions with the complicated propagation environment represented by a 3D Terrain Map. Specifically, a novel two-level design approach is proposed, consisting of a preliminary design based on the dominant line-of-sight (LoS) channel model, and an advanced design to further refine the ABS positions based on site-specific LoS/non-LoS channel states. The double deep Q-network (DQN) with Prioritized Experience Replay (Prioritized Replay DDQN) algorithm is applied to train the policy of multi-ABS placement decision. Numerical results show that the proposed approach significantly improves the coverage rate in complex environment, compared to the benchmark DQN and K-means algorithms.