Existing studies on federated learning (FL) are mostly focused on system orchestration forstatic snapshotsof the network and makingstatic control decisions(e.g., spectrum allocation). However, real-world wireless networks are susceptible totemporal variationsof wireless channel capacity and users’ datasets. In this paper, we study the impacts of the dynamics: 1) wireless channels and 2) users’ datasets on the FL execution. The former is captured by introducing a set of discrete time events while the latter is characterized by a novelordinary differential equationand the metric ofdynamic model drift, formulated via apartial differential inequality, drawing concrete analytical connections between the dynamics of users’ datasets and FL accuracy. We then proposedynamiccooperative FLwith dedicatedMAC schedulers (DCLM), exploiting the unique features of open radio access network (O-RAN) to execute FL.DCLMentails: 1) a hierarchical device-to-device (D2D)-assisted model training; 2) dynamic control decisions through dedicated O-RAN MAC schedulers; and 3) asymmetric user selection. We provide extensive theoretical analysis to study the convergence ofDCLMand then aim to optimize its degrees of freedom (e.g., user selection and spectrum allocation) through a non-convex optimization problem. We develop a systematic and generic approach to obtain the solution for this problem. We finally show the efficiency ofDCLMvia numerical simulations and provide a series of future directions.

Vehicular cloud (VC) is a promising technology for processing computation-intensive applications (CI-Apps) on smart vehicles. Implementing VCs over the network edge faces two key challenges: (C1) On-board computing resources of a single vehicle are often insufficient to process a CI-App; (C2) The dynamics of available resources, caused by vehicles’ mobility, hinder reliable CI-App processing. This work is among the first to jointly address (C1) and (C2), while considering two common CI-App graph representations, directed acyclic graph (DAG) and undirected graph (UG). To address (C1), we consider partitioning a CI-App with$m$dependent (sub-)tasks into$k\le m$groups, which are dispersed across vehicles. To address (C2), we introduce a generalized reliability metric called conditional mean time to failure (C-MTTF). Subsequently, we increase the C-MTTF of dependent sub-tasks processing via introducing a general framework of redundancy-based processing of dependent sub-tasks over semi-dynamic VCs (RP-VC). We demonstrate thatRP-VCcan be modeled as a non-trivial semi-Markov process (SMP). To analyze this SMP model and its reliability, we develop a novel mathematical framework, called event stochastic algebra ($\langle e\rangle $-algebra). Based on$\langle e\rangle $-algebra, we propose decomposition theorem (DT) to transform the presented SMP to a decomposed SMP (D-SMP). We subsequently calculate the C-MTTF of our methodology. We demonstrate that$\langle e\rangle $-algebra and DT are general mathematical tools that can be used to analyze other cloud-based networks. Simulation results reveal the exactness of our analytical results and the efficiency of our methodology in terms of acceptance and success rates of CI-App processing.