We consider decentralized federated learning (DFL) in mobile computing networks (MCNs), where dynamically changing neighborhood sets among devices arise from mobility and environmental perturbations. The time-varying topology coupled with inherent system heterogeneity poses significant challenges to achieve stable and efficient convergence in DFL. However, existing studies rarely consider both dynamic connectivity and statistical heterogeneity. To close this gap, this paper proposes a novel DFL framework enhanced with topology learning (DFL-TL) to mitigate the spatio-temporal volatility induced by MCNs, where each mobile device faces coupled constraints on its temporal windows for local updates and spatial scopes for model interaction. We introduce a new bounded neighborhood heterogeneity to jointly measure and constrain both the inter-device heterogeneity and the spectral properties of the topologies. Additionally, we formulate a mixed-integer nonlinear programming (MINLP) problem to jointly optimize learning costs and neighborhood heterogeneity. Through problem decomposition, DFL-TL efficiently identifies optimal resource allocations and adaptive mixing matrices, thereby enabling the selection of optimal training time windows while reducing the adverse effects of dynamic topologies in heterogeneous networks. Furthermore, we establish the iteration complexity of DFL-TL under non-convex settings and show that solving the proposed MINLP formulation leads to a tighter convergence bound. Extensive experiments demonstrate that DFL-TL achieves a faster convergence performance and reduces the wall-clock training time compared to the state-of-the-art baselines.

Federated Learning (FL) empowers Industrial Internet of Things (IIoT) with distributed intelligence of industrial automation thanks to its capability of distributed machine learning without any raw data exchange. However, it is rather challenging for lightweight IIoT devices to perform computation-intensive local model training over large-scale deep neural networks (DNNs). Driven by this issue, we develop a communication-computation efficient FL framework for resource-limited IIoT networks that integrates DNN partition technique into the standard FL mechanism, wherein IIoT devices perform local model training over the bottom layers of the objective DNN, and offload the top layers to the edge gateway side. Considering imbalanced data distribution, we derive the device-specific participation rate to involve the devices with better data distribution in more communication rounds. Upon deriving the device-specific participation rate, we propose to minimize the training delay under the constraints of device-specific participation rate, energy consumption and memory usage. To this end, we formulate a joint optimization problem of device scheduling and resource allocation (i.e. DNN partition point, channel assignment, transmit power, and computation frequency), and solve the long-term min-max mixed integer non-linear programming based on the Lyapunov technique. In particular, the proposed dynamic device scheduling and resource allocation (DDSRA) algorithm can achieve a trade-off to balance the training delay minimization and FL performance. We also provide the FL convergence bound for the DDSRA algorithm with both convex and non-convex settings. Experimental results demonstrate the derived device-specific participation rate in terms of feasibility, and show that the DDSRA algorithm outperforms baselines in terms of test accuracy and convergence time.

Blockchain technology has been extensively studied to enable distributed and tamper-proof data processing in federated learning (FL). Most existing blockchain assisted FL (BFL) frameworks have employed a third-party blockchain network to decentralize the model aggregation process. However, decentralized model aggregation is vulnerable to pooling and collusion attacks from the third-party blockchain network. Driven by this issue, we propose a novel BFL framework that features the integration of training and mining at the client side. To optimize the learning performance of FL, we propose to maximize the long-term time average (LTA) training data size under a constraint of LTA energy consumption. To this end, we formulate a joint optimization problem of training client selection and resource allocation (i.e., the transmit power and computation frequency at the client side), and solve the long-term mixed integer non-linear program based on a Lyapunov technique. In particular, the proposed dynamic resource allocation and client scheduling (DRACS) algorithm can achieve a trade-off of [$\mathcal {O}(1/V)$,$\mathcal {O}(\sqrt {V})$] to balance the maximization of the LTA training data size and the minimization of the LTA energy consumption with a control parameter$V$. Our experimental results show that the proposed DRACS algorithm achieves better learning accuracy than benchmark client scheduling strategies with limited time or energy consumption.

Wireless powered mobile edge computing (WP-MEC) has been widely studied as a promising technology to liberate wireless terminals from the computation-intensive and energy-consuming tasks. This article considers a WP-MEC system consisting of multiple base stations (BSs) and mobile devices (MDs), where the MDs offload tasks to the BSs for computational resources and the BSs charge the MDs using wireless power transfer (WPT). In practice, each BS and MD are equipped with a task buffer with limited size and a battery with limited capacity. First, we develop a time slotted WP-MEC system with task and energy queuing dynamics to study long-term system performance under time-varying fading channels and stochastic task and energy arrivals. Second, we propose a dynamic throughput maximum (DTM) algorithm based on perturbed Lyapunov optimization to maximize the system throughput under task and energy queue stability constraints, by optimizing the allocation of communication, computation, and energy resources. For the DTM algorithm, we characterize a throughput-backlog trade-off of [$\mathcal {O}(1/V)$,$\mathcal {O}(V)$] to indicate that the system throughput goes up as the queue backlog increases, where$V$is a control parameter between the system throughput and the queue backlog. However, we find that, as$V$goes large, the system throughput can be pushed arbitrarily close to the optimum at the cost of linearly increasing queue backlog (i.e.,$\mathcal {O}(V)$). To reduce the cost, we further develop an improved dynamic throughput maximum (IDTM) algorithm, and verify that the IDTM algorithm can achieve a trade-off of [$\mathcal {O}(1/V)$,$\mathcal {O}((\log (V))^2)$] between the system throughput and the queue backlog. The simulation results demonstrate that IDTM retains close system throughput to DTM with only$\mathcal {O}((\log (V))^2)$queue backlog.

In this paper, we expand the generalised Heronian mean (GHM) operator, generalised weighted Heronian mean (GWHM), geometric Heronian mean (GHM) operator, and weighted geometric Heronian mean (WGHM) operator with 2-tuple linguistic Pythagorean fuzzy numbers (2TLPFNs) to propose generalised 2-tuple linguistic Pythagorean fuzzy Heronian mean (G2TLPFHM) operator, generalised 2-tuple linguistic Pythagorean fuzzy weighted Heronian mean (G2TLPFWHM) operator, 2-tuple linguistic Pythagorean fuzzy geometric Heronian mean (2TLPFGHM) operator, 2-tuple linguistic Pythagorean fuzzy weighted geometric Heronian mean (2TLPFWGHM) operator. Then, the MADM methods are proposed with these operators. In the end, we utilise an applicable example for green supplier selection to prove the proposed methods.