Double DQN-based secrecy energy efficiency and fairness performance in IRS-assisted NOMA systems with friendly jamming

Hong Nguyen-Thi, Ngan Chu-Thi, Sang Quang-Nguyen, Dung Tran-Tien, Anh Le-Thi · 2026

Read Double DQN-based secrecy energy efficiency and fairness performance in IRS-assisted NOMA systems with friendly jamming by Hong Nguyen-Thi, Ngan Chu-Thi, Sang Quang-Nguyen, Dung Tran-Tien, Anh Le-Thi (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0352324.txt.

Description

Hong Nguyen-Thi and four colleagues tackle secure, energy-saving wireless design in a 2026 engineering study. Their setting is a future 6G network. Smart reflecting surfaces bounce signals to where they are needed. Several users share the same channel under a scheme called NOMA. A friendly jammer interferes with a hidden eavesdropper.

The goal is twofold: keep messages secret while wasting little energy, and treat the worst-off user fairly. The team trained a Double Deep Q-Network, a reinforcement learning method, to set power levels and surface angles. Its performance was compared with a standard learning method and with random settings. Simulations covered both shared-channel and separate-channel designs. The results highlight the shared design's edge in balancing secrecy against energy use.

Catalog record

CREATORHong Nguyen-Thi, Ngan Chu-Thi, Sang Quang-Nguyen, Dung Tran-Tien, Anh Le-Thi
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE70365
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0352324

Browse the full library · About the Tower of Babel