A Reinforcement Learning Approach to Power Control and Rate Adaptation\n in Cellular Networks

2016/11/20 by Euhanna Ghadimi, Francesco Calabrese, Ghadimi, Euhanna +5 · 1 citation
Computer Science · Engineering · #Advanced MIMO Systems Optimization #Advanced Wireless Network Optimization #Energy Harvesting in Wireless Networks #FOS: Computer and information sciences #FOS: Mathematics #Information Theory (cs.IT) #Optimization and Control (math.OC) #Wireless Networks and Protocols

paper · pdf · doi:10.48550/arxiv.1611.06497

openalex publication_date 2016/11/20 · openalex created_date 2022/09/26 · openalex updated_date 2026/07/28

Abstract

Optimizing radio transmission power and user data rates in wireless systems\nvia power control requires an accurate and instantaneous knowledge of the\nsystem model. While this problem has been extensively studied in the\nliterature, an efficient solution approaching optimality with the limited\ninformation available in practical systems is still lacking. This paper\npresents a reinforcement learning framework for power control and rate\nadaptation in the downlink of a radio access network that closes this gap. We\npresent a comprehensive design of the learning framework that includes the\ncharacterization of the system state, the design of a general reward function,\nand the method to learn the control policy. System level simulations show that\nour design can quickly learn a power control policy that brings significant\nenergy savings and fairness across users in the system.\n

Cited by

• Generalization in Reinforcement Learning for Radio Access Networks

Related

• Average Reward Reinforcement Learning for Wireless Radio Resource Management
• Transmit Power Control for Indoor Small Cells: A Method Based on Federated Reinforcement Learning
• Reinforcement Learning Based Power Control for Reliable Mission-Critical Wireless Transmission
• Deep Reinforcement Learning Based Power control for Wireless Multicast Systems
• Power Allocation in Multi-User Cellular Networks: Deep Reinforcement Learning Approaches