# Game-Theoretic Mode Scheduling for Dynamic TDD in 5G Systems

arXiv: https://arxiv.org/abs/2104.12367 · HTML: https://mlsanity.com/paper/2104.12367/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Apr 2021.

## Built on by (most cited first, 2 of 2)

- [Decentralized Federated Reinforcement Learning for User-Centric Dynamic TFDD Control](https://mlsanity.com/paper/2211.02296/) (2022)
- [Graph Neural Networks for Physical-Layer Security in Multi-User Flexible-Duplex Networks](https://mlsanity.com/paper/2402.05378/) (2024)

## Abstract (arXiv)

Dynamic time-division duplexing (TDD) enables independent uplink/downlink mode scheduling at each cell, based on the local traffic. However, this creates cross-interference among cells. Thus, the joint power allocation and scheduling problem becomes mixed-integer non-convex and turns out to be NP-hard. We propose a low-complexity and decentralized solution, where power allocation and scheduling are decoupled. First, power is allocated in a decentralized fashion, and then modes are scheduled by a non-cooperative game to achieve the mixed-strategy Nash equilibrium. We consider two possible approaches to compute the payoffs in the game, according to the cross-interference power model and the entailed communication overhead among cells. Simulation results are presented for an outdoor dense small-cell scenario, showing that our approaches outperform static TDD significantly.