As technologies for 4G and 5G networks become increasingly complex, user equipment's (UE) energy consumption also increased significantly. The 4G and 5G systems employ connected-mode discontinuous reception (C-DRX) to save UEs energy consumption by intermittently suspending network connections. However, optimizing the C-DRX operation is complex that requires considering various network conditions, including traffic patterns of each UE and the scheduling algorithms of a base station (BS). In this paper, we introduce a novel approach, a Multi-Agent Deep Reinforcement Learning (MADRL) algorithm with an integrated self-attention mechanism. This approach empowers the model to optimize C-DRX parameters independent of BSs' scheduling algorithms, enhancing its adaptability to dynamically changing network conditions. Simulation results illustrate that our MADRL-based C-DRX optimization algorithm consistently outperforms traditional methods under varying network conditions, affirming its robustness and efficacy for real- world network optimization.

https://ieeexplore.ieee.org/document/10437057