The flexible architecture of the open radio access network (O-RAN) provides effective support for the deployment of federated learning (FL). However, existing FL schemes in wireless networks often suffer from packet errors, which lead to reduced model test accuracy and increased training delay. In this paper, we propose a robust FL scheme in O-RAN, named adaptive retransmission-based hierarchical FL (HFedAR), which improves model test accuracy and reduces training delay. Specifically, HFedAR first analyzes the similarity of local gradients using a clustering algorithm to associate users with edge servers. Subsequently, we employ an adaptive retransmission mechanism for both edge and global aggregation, thereby facilitating rapid convergence of FL on non-independent and identically distributed data. Considering the limitations of spectrum resources and user energy, we formulate a multi-objective optimization problem to minimize FL training loss and delay. Due to the implicit nature of the objective function, the coupling of decision variables, and network dynamics, it is difficult to solve the problem through traditional convex optimization and machine learning algorithms. Therefore, we derive a convergence upper bound for HFedAR and present a two-stage resource allocation algorithm. The algorithm can jointly make optimal user power and computing resource allocation decisions in the first stage, and user scheduling, retransmission selection, and radio resource block allocation decisions in the second stage. Extensive simulation results on the MNIST and CIFAR-10 datasets demonstrate that the HFedAR scheme significantly improves model test accuracy by 3.5% and 6.5% and reduces training delay by 40.1% and 34.2% compared with existing FL benchmarks.
Kai Qiao, Hongchao Wang, Zi-Hao Zhang et al.· IEEE Transactions on Mobile...· 0 citations
In large areas, mobile edge computing (MEC) systems enabled by drones, also known as unmanned aerial vehicles (UAVs), can provide flexible edge computing services and facilitate low-altitude inspection. Such systems are primarily limited by the computing resources and energy of the drone, as well as their reliance on cellular network infrastructure. To overcome these limitations, this paper investigates a cooperative drone-vehicle MEC system in which a ground vehicle (GV) carries an accompanying drone (AD) and a detached drone (DD) to visit multiple data collection nodes for low-altitude inspection. We develop a joint drone-vehicle model with path planning, data collection, and processing. The AD is carried by the GV to multiple nodes and collects data when the GV is stationed at a node. The DD can detach from the GV to visit other nodes and perform data collection independently. The GV and drones cooperate in data processing and energy replenishment. We propose a heuristic to minimize the low-altitude inspection mission completion time by jointly optimizing the route and the DD speeds. We analyze the relationship between the DD speed and the size of DD-processed data and design a method that includes flight power approximation to optimize the DD speed. Numerical results indicate that solutions optimized by the heuristic fully utilize the DD, thereby reducing the completion time of low-altitude inspection missions.
W. Qi, Wei-Feng Zhong, Jia-Wen Kang et al.· IEEE Transactions on Mobile...· 0 citations
Dispersed computing has emerged as a promising paradigm that leverages underutilized resources from massive Internet of Things devices (IoTDs) to enhance the computing capacity at the network edge. However, existing works about the dispersed computing overlook the heterogeneous computing environment with parallel and serial computations and task reliability requirements for the hardware-constrained IoTDs, and they lack multi-objective optimization approaches to optimize the task offloading. To address the challenges, we propose a comprehensive scheme to achieve a delay-aware and economic-aware dispersed computing paradigm by using a multi-objective optimization approach. Particularly, we consider parallel processing at an edge server and serial processing at the lightweight IoTDs, and leverage the task redundancy to satisfy the task reliability requirements on the IoTD side. We further formulate a constrained multi-objective optimization problem (CMOP) aiming at jointly optimizing the task assignment, bandwidth allocation, and CPU frequency allocation to simultaneously minimize the total delay cost and the total charge cost of the tasks. To address the CMOP, we propose an improved constrained multi-objective evolutionary algorithm that employs a dual-population cooperative mechanism between two populations and a repairing constraint-handling technique. The dual-population cooperative mechanism can balance convergence toward Pareto optimality and solution diversity maintenance. The repairing constraint-handling technique is designed to guide solutions toward feasible regions, achieving efficient exploration of complex constrained search spaces. Simulation results demonstrate the superiority of our algorithm in seeking the better-converged and better-distributed Pareto optimal solutions to well address the tradeoffs between the two objectives.
Xumin Huang, Zexiong Wu, Chaoda Peng et al.· IEEE Transactions on Mobile...· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
