Key Takeaways & Executive Findings
- •• Proposed an FL-based computation offloading algorithm for an LEO satellite edge computing system (LSECS) that combines federated learning and mobile edge computing. • Achieves weighted sum-rate maximization for downlink and uplink cellular networks with full-duplex base stations and half-duplex users while ensuring user data privacy. • Utilizes deep reinforcement learning for joint sub-channel assignment and power allocation, exploiting global search capabilities. • Simulation results demonstrate superior weighted sum-rate performance and excellent convergence compared with baseline algorithms.
Abstract
Recent studies have shown that system capacity is very important for cellular networks. In this paper, we consider maximizing the weighted sum-rate of the cellular network downlink and uplink, where each cell consists of a full-duplex (FD) base station (BS) and half-duplex (HD) users. Federated learning (FL) can train models in the absence of centralized data, which can achieve privacy protection of user data. A low Earth orbit (LEO) satellite edge computing system (LSECS) can be formed by placing the mobile edge computing (MEC) servers on LEO satellites, which greatly increases the processing capacities of the satellites. Therefore, we consider a combination of FL and MEC and propose an FL-based computation offloading algorithm to maximize the weighted sum-rate while ensuring the security of user data. We consider solving the sub-channel assignment and power allocation problems using deep reinforcement learning (DRL) algorithms with excellent global search capabilities. The simulation results show that our proposed algorithm achieves the maximum weighted sum-rate compared with the baseline algorithms and excellent convergence.
1. Introduction
In wireless communication, full-duplex (FD) technology can significantly improve spectral efficiency, attracting considerable attention from academia and industry. Recent work has analyzed FD-assisted multi-user MIMO systems and proposed precoding schemes to combat interference and improve energy efficiency. Other studies have addressed self-interference cancellation in integrated access and backhaul networks and developed optimal queue-aware joint scheduling and power allocation algorithms for multi-cell FD networks. However, these approaches have not considered user data privacy and secure transmission.
Federated learning (FL) has emerged as a distributed machine learning paradigm that can effectively ensure data transmission security by sending local model parameters to FL servers for global aggregation. In the traditional cloud computing paradigm, FL servers are located in remote cloud centers, which imposes heavy pressure on the central infrastructure and introduces significant communication delay and privacy concerns. To preserve the privacy of each base station, global aggregation servers are not placed on the base stations. Instead, the concept of mobile edge computing is applied to low Earth orbit satellite networks, forming a low Earth orbit satellite edge computing system (LSECS) that provides global aggregation services for base stations.
For FL scenarios spanning geographically separated remote clusters or devices lacking ground communication infrastructure, such as rural and maritime areas, existing FL techniques rely on ground networks and cannot aggregate local model parameters without non-terrestrial networks. LEO satellites, with low orbital altitudes and speeds up to 7.8 km/s, offer fast communication (e.g., propagation delay from ground BSs to LEO satellites is about 5 ms) and enable highly flexible and rapid FL services. Recent studies have widely applied FL to LEO satellite networks and proposed distributed approaches based on FL to defend against malicious intrusions.
Loading authentic research manuscript (Pages 1–5)...
Min JIA, Jian WU, Xinyu WANG, Qing GUO (2025). Federated deep reinforcement learning based computation offloading in a low Earth orbit satellite edge computing system. Frontiers of Information Technology & Electronic Engineering. https://doi.org/10.1631/FITEE_2400448
Research & Educational Purpose Only:The translations, structured abstracts, analytical annotations, and data reports provided by SinoTechIntel are intended exclusively for academic research, internal corporate R&D, and educational benchmarking. They do not constitute formal engineering, chemical safety, legal, or professional advice.
Copyright & Intellectual Property Notice: Original copyright of the underlying source articles and experimental data remains with the respective authors, institutions, and original publishing journals. SinoTechIntel claims intellectual property only over its proprietary translations, analytical syntheses, and AEO structured enhancements in accordance with international fair use and academic citation principles.
Frequently Asked Questions
What problem does this paper address?
The paper addresses computation offloading and resource allocation in a low Earth orbit satellite edge computing system (LSECS), aiming to maximize the weighted sum-rate while ensuring user data privacy through federated learning.
How does the proposed algorithm balance privacy and performance?
It combines federated learning (FL) with mobile edge computing (MEC) on LEO satellites. FL sends only local model parameters to the server for aggregation, protecting raw user data, while deep reinforcement learning optimizes sub-channel assignment and power allocation to maximize weighted sum-rate.
What role do LEO satellites play in this system?
LEO satellites carry MEC servers to form an LSECS, providing global aggregation for federated learning. Their low orbit altitude enables fast communication, with propagation delay from ground base stations of about 5 ms, supporting flexible and rapid FL services.
What optimization techniques are used?
Deep reinforcement learning (DRL) algorithms are used to solve sub-channel assignment and power allocation problems, leveraging their excellent global search capabilities.
What are the key simulation findings?
The proposed FL-based computation offloading algorithm achieves the maximum weighted sum-rate compared with baseline algorithms and exhibits excellent convergence.
Related Technical Papers & Translations
Design and optimization of a high-efficiency distillation process for cellulosic fuel ethanol integrated with thermal coupling and molecular sieve adsorption
To address the challenges of high energy consumption and prominent costs in the traditional three-columns distillation process for cellulosic fuel ethanol, a distillation—molecular sieve coupling separation process is proposed. This process integrates a three-column (crude distillation column, first distillation column, second distillation column) system with a 3A molecular sieve adsorption deep dehydration unit. A thermal coupling network is constructed via differential pressure design (steam from medium/high-pressure columns as mutual heat sources, reboiler liquid waste heat for feed preheating), and molecular sieve adsorption conditions are optimized. The study first performs a thermodynamic consistency test on the ethanol—water system, determines optimal non-random two-liquid (NRTL) model binary interaction parameters via experimental data regression for Aspen Plus simulation. Aiming at minimum total annual cost (TAC), Aspen Plus is used to optimize process parameters (theoretical tray number, feed location, reflux ratio, side-draw position, etc.). Economic analysis shows this process reduces CO2 emission costs by 27.56%, TAC by 15.58% (to 5.123 × 106 USD·a-1), and increases ethanol purity to ＞99.6%, providing an effective solution for green, efficient separation.
A cohesion loss model for determining residual strength of deep bedded sandstone
Rock residual strength, as an important input parameter, plays an indispensable role in proposing the reasonable and scientific scheme about stope design, underground tunnel excavation and stability evaluation of deep chambers. Therefore, previous residual strength models of rocks established were reviewed. And corresponding related problems were stated. Subsequently, starting from the effects of bedding and whole life-cycle evolution process, series of triaxial mechanical tests of deep bedded s
Federated model with contrastive learning and adaptive control variates for human activity recognition
Recent attention to privacy issues demands a communication-safe method for training human activity recognition (HAR) models on client activity data. Federated learning (FL) has become a compelling technique to facilitate model training between the server and clients while preserving data privacy. However, classical FL methods often assume independent and identically distributed (IID) data among clients. This assumption does not hold true in practical scenarios. Human activity in real-world scena