Auction-Based RIS Allocation With DRL: Controlling the Cost-Performance Trade-Off

Martin Mark Zan; Stefan Schwarz

cs.NIFeb 18, 2026

Auction-Based RIS Allocation With DRL: Controlling the Cost-Performance Trade-Off

Authors: Martin Mark Zan, Stefan Schwarz

Organizations: Institute of Telecommunications, TU Wien, Vienna, Austria

Abstract

We study the allocation of reconfigurable intelligent surfaces (RISs) in a multi-cell wireless network, where base stations compete for control of shared RIS units deployed at the cell edges. These RISs, provided by an independent operator, are dynamically leased to the highest bidder using a simultaneously ascending auction format. Each base station estimates the utility of acquiring additional RISs based on macroscopic channel parameters, enabling a scalable and low-overhead allocation mechanism. To optimize the bidding behavior, we integrate deep reinforcement learning (DRL) agents that learn to maximize performance while adhering to budget constraints. Through simulations in clustered cell-edge environments, we demonstrate that reinforcement learning (RL)-based bidding significantly outperforms heuristic strategies, achieving optimal trade-offs between cost and spectral efficiency. Furthermore, we introduce a tunable parameter that governs the bidding aggressiveness of RL agents, enabling a flexible control of the trade-off between network performance and expenditure. Our results highlight the potential of combining auction-based allocation with adaptive RL mechanisms for efficient and fair utilization of RISs in next-generation wireless networks.

Figures & tables

Fig. 1: System workflow of the proposed auction-based RIS allocation framework. Macroscopic SINR and utility estimates are used as inputs to a DRL-based bidding policy, which generates bids for the auction mechanism. The auction iterates over bidding rounds until a termination condition is met, after which data transmission is performed.

Fig. 2: Simulation geometry with two base stations (BS) at opposite ends, clustered users (UE), and RISs positioned along the cell boundary. The figure shows an example allocation of RISs obtained using a reinforcement learning agent with bid intensity parameter $\beta=3$ .

Carrier frequency	$f_{c}=26\,\text{GHz}$
Number of base stations	$N_{\text{BS}}=2$
Number of base station antennas	$M_{\text{BS}}=50$
Number of users	$N_{\text{UE}}=20$
Number of RISs	$N_{\text{RIS}}=10$
Number of RIS elements	$M_{\text{RIS}}=250$
Transmit power per subcarrier	$P=100\,\text{mW}$

TABLE I: Simulation Parameters

Fig. 3: Accuracy of the macroscopic SINR estimation as a function of the number of BS antennas $M_{\mathrm{BS}}$ . The figure reports the mean, median, and 90th percentile of the absolute error between the estimated and true SINR values.

Fig. 4: Training convergence of the PPO-based bidding agent with $\beta=2$ . The figure shows the evolution of the training reward over environment interaction steps, with a moving-average smoothed curve (window size 5).

Fig. 5: Performance comparison of heuristics and RL-based models using different bid intensity ( $\beta$ ) values. The figure illustrates the trade-off between cost and achievable rate.

Fig. 6: Impact of the bid intensity ( $\beta$ ) parameter on RL bidding behavior. Larger $\beta$ values make agents more selective, resulting in higher average bid values but fewer allocated RISs, while smaller $\beta$ values lead to broader bidding on lower-value RISs.

Wireless Resource Allocation

Wireless resource allocation assigns spectrum, power, beams, and computing capacity to meet throughput, latency, fairness, and energy goals.

See all 172 papers

Cooperative Deep Reinforcement Learning for Fair RIS Allocation
Mar 26, 2026Martin Mark Zan, Stefan SchwarzWireless Resource Allocation Fair Resource Allocation
Institute of Telecommunications, TU Wien, Vienna, Austria
DRL-AdaPart: DRL-Driven Adaptive STAR-RIS Partitioning for Fair and Efficient Resource Utilization
Jul 9, 2024Ashok S. Kumar, Nancy Nayak, Sheetal Kalyani +2Reconfigurable Intelligent Surfaces Fair Resource Allocation
Department of Electrical Engineering, Indian Institute of Technology Madras, Chennai, India · Department of Electrical and Electronic Engineering, Imperial College London, United Kingdom · Department of Electrical and Electronic Engineering, University of Peradeniya, Peradeniya 20400, Sri Lanka +1
Large Language Models as Bidding Agents in Repeated HetNet Auction
Mar 2, 2026Ismail Lotfi, Ali Ghrayeb, Samson Lasaulce +1Wireless Resource Allocation Automated Bidding
College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar · CNRS, Universite de Lorraine, CRAN, France · Department of Computer Science, Khalifa University, Abu Dhabi, UAE

Mar 26, 2026J/K move · Enter open · S save

Cooperative Deep Reinforcement Learning for Fair RIS Allocation

Martin Mark Zan, Stefan Schwarz

Institute of Telecommunications, TU Wien, Vienna, Austria

Wireless Resource Allocation Fair Resource Allocation Reconfigurable Intelligent Surfaces Cooperative MARL

Open paper AskPDF arXiv

The deployment of reconfigurable intelligent surfaces (RISs) introduces new challenges for resource allocation in multi-cell wireless networks, particularly when user loads are uneven across base stations. In this work, we consider RISs as shared infrastructure that must be dynamically assigned among competing base stations, and we address this problem using a simultaneous ascending auction mechanism. To mitigate performance imbalances between cells, we propose a fairness-aware collaborative multi-agent reinforcement learning approach in which base stations adapt their bidding strategies based on both expected utility gains and relative service quality. A centrally computed performance-dependent fairness indicator is incorporated into the agents' observations, enabling implicit coordination without direct inter-base-station communication. Simulation results show that the proposed framework effectively redistributes RIS resources toward weaker-performing cells, substantially improving the rates of the worst-served users while preserving overall throughput. The results demonstrate that fairness-oriented RIS allocation can be achieved through cooperative learning, providing a flexible tool for balancing efficiency and equity in future wireless networks.

Abstract

Wireless Resource Allocation

Explore similar work

Cooperative Deep Reinforcement Learning for Fair RIS Allocation

DRL-AdaPart: DRL-Driven Adaptive STAR-RIS Partitioning for Fair and Efficient Resource Utilization

Large Language Models as Bidding Agents in Repeated HetNet Auction