Compositional Learning for Modular Multi-Agent Self-Organizing Networks
This work addresses complex parameter interdependencies and conflicting objectives in multi-agent self-organizing networks, offering incremental improvements in performance and scalability.
The study tackled challenges in self-organizing networks by introducing compositional learning approaches (CDRL and CPDM) in a modular multi-agent framework, resulting in reduced handover failures and improved throughput and latency compared to conventional methods.
Self-organizing networks face challenges from complex parameter interdependencies and conflicting objectives. This study introduces two compositional learning approaches-Compositional Deep Reinforcement Learning (CDRL) and Compositional Predictive Decision-Making (CPDM)-and evaluates their performance under training time and safety constraints in multi-agent systems. We propose a modular, two-tier framework with cell-level and cell-pair-level agents to manage heterogeneous agent granularities while reducing model complexity. Numerical simulations reveal a significant reduction in handover failures, along with improved throughput and latency, outperforming conventional multi-agent deep reinforcement learning approaches. The approach also demonstrates superior scalability, faster convergence, higher sample efficiency, and safer training in large-scale self-organizing networks.