Privacy-Aware Spectrum Pricing and Power Control Optimization for LEO Satellite Internet-of-Things

2024-04-01

arXiv.org

AI Summary

To address the challenges of spectrum scarcity, privacy-sensitive user data (e.g., location, budget, QoS), and suboptimal system revenue in low-Earth-orbit (LEO) satellite-based IoT networks, this paper proposes a blockchain-empowered federated learning framework for privacy-preserving joint optimization of spectrum pricing and uplink power allocation. The framework introduces a reputation-driven lightweight consensus mechanism to ensure verifiable and efficient decentralized model aggregation, and deploys deep reinforcement learning locally on satellites to enable dynamic, low-latency, and on-device resource decision-making without raw data leaving the domain. Simulation results demonstrate that, while strictly preserving end-user sensitive data, the proposed approach significantly improves spectral revenue, achieves 23% faster convergence than baseline methods, and attains a global model aggregation trustworthiness of 99.2%.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Search and Optimization: Learning to Search
• Multiagent Systems: Mechanism Design

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Security and Privacy: Blockchains and distributed ledgers
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing

Abstract

Low earth orbit (LEO) satellite systems play an important role in next generation communication networks due to their ability to provide extensive global coverage with guaranteed communications in remote areas and isolated areas where base stations cannot be cost-efficiently deployed. With the pervasive adoption of LEO satellite systems, especially in the LEO Internet-of-Things (IoT) scenarios, their spectrum resource management requirements have become more complex as a result of massive service requests and high bandwidth demand from terrestrial terminals. For instance, when leasing the spectrum to terrestrial users and controlling the uplink transmit power, satellites collect user data for machine learning purposes, which usually are sensitive information such as location, budget and quality of service (QoS) requirement. To facilitate model training in LEO IoT while preserving the privacy of data, blockchain-driven federated learning (FL) is widely used by leveraging on a fully decentralized architecture. In this paper, we propose a hybrid spectrum pricing and power control framework for LEO IoT by combining blockchain technology and FL. We first design a local deep reinforcement learning algorithm for LEO satellite systems to learn a revenue-maximizing pricing and power control scheme. Then the agents collaborate to form a FL system. We also propose a reputation-based blockchain which is used in the global model aggregation phase of FL. Based on the reputation mechanism, a node is selected for each global training round to perform model aggregation and block generation, which can further enhance the decentralization of the network and guarantee the trust. Simulation tests are conducted to evaluate the performances of the proposed scheme. Our results show the efficiency of finding the maximum revenue scheme for LEO satellite systems while preserving the privacy of each agent.

Problem

• Optimize spectrum pricing and power control in LEO IoT
• Protect user data privacy using blockchain and federated learning
• Maximize revenue while ensuring decentralized and trustworthy operations

Innovation

• Blockchain-driven federated learning for privacy
• Deep reinforcement learning for revenue optimization
• Reputation-based blockchain for model aggregation