The content discusses the utilization of Integrated Access and Backhauling (IAB) as a cost-effective alternative to fiber-wired links for achieving higher data rates in future networks. The design of such networks presents optimization challenges due to non-convex and combinatorial nature. To address this, the paper proposes a multi-agent Deep Reinforcement Learning (DeepRL) framework for joint optimization of power and subchannel allocation in an IAB network. The framework utilizes DDQN (Double Deep Q-Learning Network) to handle computationally expensive problems with multiple users and nodes. Unlike traditional methods, the DeepRL approach requires less network information. Simulation results demonstrate the promising performance of the proposed scheme compared to baseline schemes such as Deep Q-Learning Network and Random.
Joint Power and Subchannel Allocation in IAB Networks using Multi-Agent Deep Reinforcement Learning
