Learned decentralized power allocation boosts communication in multi channel wireless ad hoc networks
MANET-GNN: Learned Decentralized Optimization of Power Allocation in Multi-Channel MANETs
Machine Learning
Summary
Managing how much power each device uses to send signals in multi-channel wireless ad hoc networks is hard, especially without centralized control. The authors created a method called MANET-GNN, which learns how to do this power allocation smartly by only sharing limited local information with nearby devices. This approach works well across different network setups and types of communication, keeps up performance even with noisy channel info, and adapts to networks of various sizes. Essentially, it helps wireless devices talk to each other more efficiently without a central controller.
What this means in practice
- •For wireless network engineers: Implement decentralized algorithms for power control in multi-hop wireless networks with multiple channels to improve throughput and robustness under uncertain conditions.
- •For military communication teams: Enable low-latency, flexible communication among mobile units in infrastructure-free environments by using learned decentralized power allocation strategies.
Authors
Tomer Alter, Nir Shlezinger, Michael Segal
Abstract
MANETs enable flexible infrastructure-less wireless connectivity in dynamic and resource-constrained environments. As modern MANETs exploit multiple frequency channels and support heterogeneous traffic patterns, decentralized transmit-power allocation becomes increasingly challenging. We develop a unified learned optimization framework for decentralized power allocation in dynamic multi-hop, multi-channel MANETs. We formulate a constrained end-to-end throughput maximization problem covering unicast, multicast, multicommodity, convergecast, and many-to-many communication. Although centralized and non-convex, this problem serves as an unsupervised training objective for MANET-GNN, a message-passing GNN that operates as a distributed learned optimizer. MANET-GNN uses only local, possibly noisy, CSI and a prescribed number of neighbor message exchanges, enabling low-latency decentralized inference while generalizing across topologies and network sizes. Numerical results show that MANET-GNN achieves centralized-competitive performance across communication frameworks, remains robust to channel uncertainty, and scales effectively across MANET configurations.