Deep Reinforcement Learning :Applications to 6G RAN

Description

Building on the history and development of ORAN standards, this handbook explains how wireless engineers can define, train, and evaluate Deep Reinforcement Learning controllers for radio resource optimization, slicing, and random-access congestion. Chapter 5 connects those learning problems to OpenRAN Gym’s experimental workflow. The Python appendices provide accessible starting environments; moving an agent into a RIC requires compatible telemetry, an implemented actuator, and measured closed-loop validation. The examples and the integration proposals are identified separately throughout this revision.

About the Authors

Rao S Yenamandra began his telecom career in 1967 with India's Department of Telecommunications. He then spent 20 years at Qualcomm, San Diego (1995–2014), retiring as Vice President, Engineering, where he advised Reliance on CDMA introduction in India and led CDMA/UMTS operator support across Africa. He holds 18 granted patents in UMTS/LTE. Since 2022 he has focused on ML/AI applications to network problems. He holds a Ph.D., is a Fellow of the IETE, and lives in Mountain View, California.

Mubanga Nsofu has 20 years of experience in wireless engineering at Qualcomm and wth 3G/4G wireless operators in SA, with his most recent work being in data science. He has published many technical papers on deep reinforcement learning and active algorithm development in DRL and RL, with PPO and DQN applications in particular.

Ratings & Reviews