Cellular networks are becoming increasingly heterogeneous with higher base station (BS) densities and ever more frequency bands, making BS selection and band assignment key decisions in terms of user service rate and coverage. In this paper, we decompose the mobility-aware user association task into (i) forecasting of user data rate and then (ii) convex utility maximization for user association accounting for the effects of BS load and handover overheads. Using a linear combination of normalized mean-squared error (NMSE) and normalized discounted cumulative gain (NDCG) as a novel loss function, a recurrent deep neural network is trained to reliably forecast the mobile users’ future data rates. Based on the forecast, the controller optimizes the association decisions to maximize the service rate-based network utility using our computationally efficient (speed up of 100× versus generic convex solver) algorithm based on the Frank-Wolfe method. Using an industry-grade network simulator developed by Meta, we show that the proposed model predictive control (MPC) approach improves the 5th percentile service rate by 3.5× compared to the traditional signal strength-based association, reduces the median number of handovers by 7× compared to a handover agnostic strategy, and achieves service rates close to a genie-aided scheme. Furthermore, our model-based approach is significantly more sample-efficient (needs 100× less training data) compared to model-free reinforcement learning (RL), and generalizes well across different user drop scenarios.

Access to high-quality maternal health care services is limited in Kenya, which resulted in ∼36,000 maternal and neonatal deaths in 2018. To tackle this challenge, Jacaranda Health (a non-profit organization working on maternal health in Kenya) developed PROMPTS, an SMS based tele-triage system for pregnant and puerperal women, which has more than 350,000 active users in Kenya. PROMPTS empowers pregnant women living far away from doctors and hospitals to send SMS messages to get quick answers (through human helpdesk agents) to questions about their medical symptoms and pregnancy status. Unfortunately, ∼1.1 million SMS messages are received by PROMPTS every month, which makes it challenging for helpdesk agents to ensure that these messages can be interpreted correctly and evaluated by their level of emergency to ensure timely responses and/or treatments for women in need. This paper reports on a collaborative effort with Jacaranda Health to develop a state-of-the-art natural language processing (NLP) framework, TRIM-AI (TRIage for Mothers using AI), which can automatically predict the emergency level (or severity of medical condition) of a pregnant mother based on the content of their SMS messages. TRIM-AI leverages recent advances in multi-lingual pre-training and continual pre-training to tackle code-mixed SMS messages (between English and Swahili), and achieves a weighted F1 score of 0.774 on real-world datasets. TRIM-AI has been successfully deployed in the field since June 2022, and is being used by Jacaranda Health to prioritize the provision of services and care to pregnant women with the most critical medical conditions. Our preliminary A/B tests in the field show that TRIM-AI is ∼17% more accurate at predicting high-risk medical conditions from SMS messages sent by pregnant Kenyan mothers, which reduces the helpdesk’s workload by ∼12%.

As cellular networks embrace heterogeneity with higher base station (BS) densities and ever more frequency bands, BS selection and band assignment become increasingly key decisions in terms of rate and coverage optimization. In this paper, we propose a novel learning-based model predictive control (MPC) approach for BS selection and band assignment while accounting for user mobility. We formulate a convex utility maximization problem that accounts for the effects of BS load and handover overheads on the user's service rate. Using a linear combination of normalized mean-squared error (NMSE) and$\mathbf{top}-m$loss as a novel loss function, a recurrent deep neural network is trained to reliably forecast the mobile users' future rates. The MPC controller then uses this forecast to optimize the association decisions to maximize the service rate-based network utility. Using an industry-grade network simulator developed by Meta, we show that the proposed approach improves the 5th percentile service rate by$2.7\times$compared to the traditional signal strength-based association and its performance approaches that of a genie-aided scheme in terms of the achieved service rate and the number of handovers triggered.

Integrated access and backhaul (IAB) facilitates cost-effective deployment of millimeter wave (mmWave) cellular networks through multihop self-backhauling. Full-duplex (FD) technology, particularly for mmWave systems, is a potential means to overcome latency and throughput challenges faced by IAB networks. We derive practical and tractable throughput and latency constraints using queueing theory and formulate a network utility maximization problem to evaluate both full-duplex (FD)-IAB and half-duplex (HD)-IAB networks. We use this to characterize the network-level improvements seen when upgrading from conventional HD IAB nodes to FD ones by deriving closed-form expressions for (i) latency gain of FD-IAB over HD-IAB and (ii) the maximum number of hops that a HD- and FD-IAB network can support while satisfying latency and throughput targets. Extensive simulations illustrate that FD-IAB can facilitate reduced latency, higher throughput, deeper networks, and fairer service. Compared to HD-IAB, FD-IAB can improve throughput by$8\times $and reduce latency by$4\times $for a fourth-hop user. In fact, upgrading IAB nodes with FD capability can allow the network to support latency and throughput targets that its HD counterpart fundamentally cannot meet. The gains are more profound for users further from the donor and can be achieved even when residual self-interference is significantly above the noise floor.

Cellular networks continue to trend rapidly towards more bands and carrier frequencies, along with higher base station density, requiring complex decisions to be made when associating a mobile user with a band and cell. This paper develops a novel approach to optimizing frequency band and cell selection while taking into account user mobility and handovers. This is a complex problem because of the uncertain link failure events, handover related overheads, and the significant difference in the propagation characteristics between different frequency bands. The network dynamics due to user mobility are modeled as a Markov decision process, and we develop a recurrent Q-learning framework to exploit the relationship between user trajectories and the history of SINR measurements. The effective cell boundaries are therefore based on user trajectories and velocities rather than just position and signal strength. Detailed system-level simulations show that the proposed learning-based approach improves the throughput of the edge users by 54% and the median throughput by 34% compared to traditional SINR-based association and achieves a superior rate/coverage tradeoff (quantified as sum-log-rate) compared to SINR or signal-strength-based associations.

Multihop self-backhauling is a key enabling technology for millimeter wave cellular deployments. We consider the multihop link scheduling problem with the objective of minimizing the end-to-end delay experienced by a typical packet. This is a complex problem, and so we model the system as a network of queues and formulate it as a Markov decision process over a continuous action space. This allows us to leverage the deep deterministic policy gradient algorithm from reinforcement learning to learn the delay minimizing scheduling policy under two scenarios: 1) an ideal setup where a centralized scheduler performs all per slot scheduling decisions and has full instantaneous knowledge of network state and 2) a centralized scheduler, but where network state feedback and scheduling decisions are limited to once per frame, which is many slots. For the second scenario, we model the scheduler with a recurrent neural network to capture the evolution of the network state over the frame. Detailed system-level simulations show that for the more realistic second scenario, the delay experienced by the 5thpercentile packets under backpressure based scheduling and max-min scheduling can be up to 230% and 260%, respectively more than that under the proposed scheduler.