Scholarlink

<p>Distributed sixth-generation (6G) mobile networks face two unresolved and interdependent challenges: how to dynamically price network resources in real time under non-stationary demand conditions without sacrificing quality of service or economic fairness, and how to enforce these pricing decisions securely and transparently across a multi-operator ecosystem in the absence of a trusted central authority. Existing approaches address these challenges in isolation. Static and rule-based pricing mechanisms fail to adapt to demand fluctuations, causing up to 30% resource underutilization during off-peak periods and significant quality-of-service degradation at peak times. Blockchain-secured allocation frameworks, while offering tamper resistance, have relied on fixed pricing logic that cannot learn from evolving network conditions. No existing solution simultaneously provides adaptive economic intelligence and decentralized security enforcement within a single coherent framework. We address this gap by presenting a novel reinforcement learning (RL)-based economic framework for dynamic pricing and secure resource allocation in distributed 6G mobile networks. The proposed model integrates a Q-learning algorithm with a decentralized smart contract architecture built on a permissioned blockchain to ensure efficient, fair, and tamper-resistant allocation of network bandwidth and computing resources. Unlike static or rule-based pricing systems, our model dynamically learns optimal pricing policies by interacting with a non-stationary user demand environment, balancing network operator revenue with user satisfaction under latency and throughput constraints. The smart contracts enforce these economic decisions securely across geographically dispersed base stations and edge nodes, mitigating risks of false demand inflation, resource monopolization, and denial-of-service attacks. The system is formalized using Markov Decision Processes (MDP) and evaluated using realistic network scenarios simulated in NS-3, Python, and Solidity-based smart contract environments. Simulation results demonstrate that the proposed model outperforms baseline approaches by up to 38% in average resource utilization, 29% in latency reduction, and 24% in pricing fairness under fluctuating demand conditions. The blockchain layer introduces only minimal computational overhead while significantly enhancing transactional trust and accountability. Scalability is achieved through distributed per-BS agents and lightweight consensus contracts, handling increases from 20 to 200 base stations with less than 10% latency rise. This study contributes to the growing body of knowledge at the intersection of AI-driven economic systems and secure wireless communication infrastructure.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A reinforcement learning-based economic model for dynamic pricing and secure resource allocation in distributed 6G mobile networks

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月20日

查看全文
  • Milad Rahmati,
  • Nima Rahmati

摘要

Distributed sixth-generation (6G) mobile networks face two unresolved and interdependent challenges: how to dynamically price network resources in real time under non-stationary demand conditions without sacrificing quality of service or economic fairness, and how to enforce these pricing decisions securely and transparently across a multi-operator ecosystem in the absence of a trusted central authority. Existing approaches address these challenges in isolation. Static and rule-based pricing mechanisms fail to adapt to demand fluctuations, causing up to 30% resource underutilization during off-peak periods and significant quality-of-service degradation at peak times. Blockchain-secured allocation frameworks, while offering tamper resistance, have relied on fixed pricing logic that cannot learn from evolving network conditions. No existing solution simultaneously provides adaptive economic intelligence and decentralized security enforcement within a single coherent framework. We address this gap by presenting a novel reinforcement learning (RL)-based economic framework for dynamic pricing and secure resource allocation in distributed 6G mobile networks. The proposed model integrates a Q-learning algorithm with a decentralized smart contract architecture built on a permissioned blockchain to ensure efficient, fair, and tamper-resistant allocation of network bandwidth and computing resources. Unlike static or rule-based pricing systems, our model dynamically learns optimal pricing policies by interacting with a non-stationary user demand environment, balancing network operator revenue with user satisfaction under latency and throughput constraints. The smart contracts enforce these economic decisions securely across geographically dispersed base stations and edge nodes, mitigating risks of false demand inflation, resource monopolization, and denial-of-service attacks. The system is formalized using Markov Decision Processes (MDP) and evaluated using realistic network scenarios simulated in NS-3, Python, and Solidity-based smart contract environments. Simulation results demonstrate that the proposed model outperforms baseline approaches by up to 38% in average resource utilization, 29% in latency reduction, and 24% in pricing fairness under fluctuating demand conditions. The blockchain layer introduces only minimal computational overhead while significantly enhancing transactional trust and accountability. Scalability is achieved through distributed per-BS agents and lightweight consensus contracts, handling increases from 20 to 200 base stations with less than 10% latency rise. This study contributes to the growing body of knowledge at the intersection of AI-driven economic systems and secure wireless communication infrastructure.