Wireless Resource Allocation
Overview
Wireless resource allocation decides how limited spectrum, transmission power, time slots, beams, and edge-computing capacity are shared among users and tasks, often under interference and changing channel conditions. Classical methods use convex or mixed-integer optimization, auctions, and scheduling rules; newer work applies bandits, deep and multi-agent reinforcement learning, graph neural networks, and generative models to make decisions quickly in settings such as cellular and O-RAN networks, vehicular and UAV links, reconfigurable intelligent surfaces, and wireless federated learning. These methods increasingly coordinate multiple resources and objectives, including quality of service, fairness, energy use, sensing accuracy, and learning performance. A central challenge is making learned policies generalize across network sizes, mobility, and hardware while enforcing hard constraints and remaining reliable, interpretable, and fast enough for real deployments.
Latest papers
175 papers18 papers in the last four weeks, down 5% on the four weeks before. 0.1% of all new papers.