Differential Privacy and IRS Empowered Intelligent Energy Harvesting for 6G Internet of Things

Pan, Qianqian; Wu, Jun; Zheng, Xi; Yang, Wu; Li, Jianhua

doi:10.1109/jiot.2021.3104833

Cited by 28 publications

(10 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Selecting devices with sufficient resources [15] • Partial work scheme: FedProx [14] • Pre-designing local models with varying structures: FedET [16] • Energy Harvesting: [17], [18] Section IV-A: Feature-extractor sharing.…”

Section: Computation Heterogeneitymentioning

confidence: 99%

Federated Learning in Heterogeneous Wireless Networks With Adaptive Mixing Aggregation and Computation Reduction

Li,

Liu,

Mahmoodi

2024

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

Despite the recent advancements achieved by federated learning (FL), its real-world deployment is significantly impeded by the heterogeneous learning environment, specifically manifesting as devices with various computing capabilities, non-I.I.D. (Independent Identically and Distributed) data distribution and dynamic wireless transmission conditions. Such learning heterogeneity greatly harms the learning performance, e.g., convergence and learning accuracy. Therefore, we introduce the AMA-FES (adaptive-mixing aggregation, feature-extractor sharing) framework with an asynchronous aggregation scheme to address these challenges. To mitigate the impact of the non-I.I.D. data, we propose the AMA scheme to maintain the training stability by compromising between the previous global model and the synchronised local model updates, avoiding abrupt changes to a completely new model. To reduce computation load, we introduce the FES scheme, enabling the computing-limited devices to update only the classifier. To address the asynchronous model updates caused by the transmission delay, we perform asynchronous aggregation with staleness-based weighting. We implement the AMA-FES framework in a practical scenario where mobile UAVs act as FL training clients to conduct image classification tasks. The experimental results validate the effectiveness of the AMA-FES scheme in restoring training stability and learning accuracy without causing extra computation or communication expenditures in heterogeneous wireless networks.

show abstract

Section: Computation Heterogeneitymentioning

confidence: 99%

Federated Learning in Heterogeneous Wireless Networks With Adaptive Mixing Aggregation and Computation Reduction

Li,

Liu,

Mahmoodi

2024

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

show abstract

“…In particular, the UAVs are powered by onboard batteries that usually have limited capacity and lifetime. Then, energy harvesting technologies [63], such as wireless power transfer [64], can be used to mitigate the impact of limited energy and battery lifetimes. These technologies can be empowered by RL-based algorithms to achieve efficiently a trade-off between the high energy demand of the UAV and the limited battery capacities, even under scenarios with high mobility.…”

Section: Reinforcement Learning In Airs-noma Networkmentioning

confidence: 99%

Aerial Intelligent Reflecting Surfaces in MIMO-NOMA Networks: Fundamentals, Potential Achievements, and Challenges

Lima

Sena

Dinis

et al. 2022

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

Non-orthogonal multiple access (NOMA) technique and unmanned aerial vehicles (UAVs) have been recognized as promising technologies for enabling the stringent requirements of the different network infrastructures expected for the next generation of wireless networks. In parallel, intelligent reconfigurable surfaces (IRSs) have been widely pointed out as an auspicious solution to further improve spectral efficiency, coverage range, and connectivity. By integrating IRS with UAV and NOMA schemes with multiple-input multiple-output (MIMO) it is possible to smartly improve the overall network performance. In order to explore some of these potentials, this paper provides a comprehensive discussion about the interplay of aerial IRS in MIMO-NOMA (AIRS-NOMA) networks, as well its architecture, functionality principles, and performance gains. In particular, attractive gains related to the data rate maximization, user fairness, energy efficiency, and coverage range are highlighted. Simulation results are provided to support our insightful discussions, in which it is revealed that the performance gains of AIRS-NOMA networks are superior when compared to terrestrial deployment. In addition, to guide new studies perspectives, it is addressed some issues and research opportunities associated with this potential integration.

show abstract

“…The simplified version of IRS will have the opportunity for initially commercial deployment and standardization in the 5G-Advanced stage, especially to improve the 5G millimeter wave coverage problem [21], [22]. The authors of [23] studied a communication system based on IRS-assisted SWIPT under QoS constraints by jointly designing active and passive beamforming. In [24], the author jointly optimized the minimum total transmit power of the system by designing active and passive beamforming, significantly improving network energy consumption and increasing the achievable rate.…”

Section: A Related Work and Motivationmentioning

confidence: 99%

“…where p, μ, ω represent the updated value of the parameters p, μ, ω, respectively, Äj [n] and Bj [n] in formula (23) are expressed as…”

Section: A Resource Allocationmentioning

confidence: 99%

IRS Empowered UAV Wireless Communication With Resource Allocation, Reflecting Design and Trajectory Optimization

Zhang

et al. 2022

IEEE Trans. Wireless Commun.

View full text Add to dashboard Cite

As revolutionary technologies that can actively change the communication link signal, intelligent reflecting surface (IRS) and unmanned aerial vehicle (UAV) have emerged as reliable, economical and convenient wireless communication solutions for a variety of practical scenarios. Therefore, this paper focuses on an IRS empowered UAV downlink communication network, where the dynamic UAV establishes a cascade link via IRS to provide signal enhancement services for multiple users. Considering constraints of transmit power, flight speed and area at the UAV and the reflecting constraints at the IRS, the block coordinate descent (BCD) method based on resource allocation, reflecting design and trajectory optimization is adopted to maximize the sum-rate of all users. The proposed problem is converted by using quadratic transformation and Lagrangian dual transformation. Then applying for the approximate linear method and Iterative Rank Minimization (IRM) to optimize the transmit power of UAV and phase shift of IRS respectively. Since additional reflection propagation paths by IRS, the complexity of the channel model makes the trajectory design difficult. To tackle this problem, this paper proposes a UAV trajectory optimization method based on enhanced reinforcement learning with the fixed initial location and destination. In the end, the convergence of the proposed scheme is effectively verified X. Zhang, H. Zhang, and K. Long are with the

show abstract

Differential Privacy and IRS Empowered Intelligent Energy Harvesting for 6G Internet of Things

Cited by 28 publications

References 37 publications

Federated Learning in Heterogeneous Wireless Networks With Adaptive Mixing Aggregation and Computation Reduction

Federated Learning in Heterogeneous Wireless Networks With Adaptive Mixing Aggregation and Computation Reduction

Aerial Intelligent Reflecting Surfaces in MIMO-NOMA Networks: Fundamentals, Potential Achievements, and Challenges

IRS Empowered UAV Wireless Communication With Resource Allocation, Reflecting Design and Trajectory Optimization

Contact Info

Product

Resources

About