With the exponential growth of the Internet of things (IoT) in remote sensing image applications, network resource orchestration and data privacy are significant aspects to handle in bigdata cellular networks. The image data sharing procedure toward central cloud servers in order to perform real-time classifications has leaked client personalization and heavily burdened the communication networks. Thus, the deployment of IoT image sensors in privacy-constrained sectors requires an optimized federated learning (FL) scheme to efficiently consider both aspects of securing data privacy and maximizing the model accuracy with sufficient communication and computation resources. In this article, an adaptive model communication scheme with virtual resource optimization for edge FL is proposed by converging a deep qlearning algorithm to enforce a self-learning agent interacting with network functions virtualization orchestrator and software-defined networking based architecture. The agent targets to optimize the resource control policy of virtual multi-access edge computing entities in virtualized infrastructure manager. The proposed scheme trains the learning model and weighs the optimal actions for particular network states by using an epsilon-greedy strategy. In the exploitation phase, the scheme considers multiple spatial-resolution sensing conditions and allocates computation offloading resources for global multiconvolutional neural networks model aggregation based on the congestion states. In the simulation results, the quality of service and global collaborative model performance metrics were evaluated in terms of delay, packet drop ratios, packet delivery ratios, loss values, and overall accuracy.
Federated learning (FL) activates distributed on-device computation techniques to model a better algorithm performance with the interaction of local model updates and global model distributions in aggregation averaging processes. However, in large-scale heterogeneous Internet of Things (IoT) cellular networks, massive multi-dimensional model update iterations and resource-constrained computation are challenging aspects to be tackled significantly. This paper introduces the system model of converging softwaredefined networking (SDN) and network functions virtualization (NFV) to enable device/resource abstractions and provide NFV-enabled edge FL (eFL) aggregation servers for advancing automation and controllability. Multi-agent deep Q-networks (MADQNs) target to enforce a self-learning softwarization, optimize resource allocation policies, and advocate computation offloading decisions. With gathered network conditions and resource states, the proposed agent aims to explore various actions for estimating expected longterm rewards in a particular state observation. In exploration phase, optimal actions for joint resource allocation and offloading decisions in different possible states are obtained by maximum Q-value selections. Action-based virtual network functions (VNF) forwarding graph (VNFFG) is orchestrated to map VNFs towards eFL aggregation server with sufficient communication and computation resources in NFV infrastructure (NFVI). The proposed scheme indicates deficient allocation actions, modifies the VNF backup instances, and reallocates the virtual resource for exploitation phase. Deep neural network (DNN) is used as a value function approximator, and epsilongreedy algorithm balances exploration and exploitation. The scheme primarily considers the criticalities of FL model services and congestion states to optimize long-term policy. Simulation results presented the outperformance of the proposed scheme over reference schemes in terms of Quality of Service (QoS) performance metrics, including packet drop ratio, packet drop counts, packet delivery ratio, delay, and throughput.
The 5th generation (5G) communications evolved with heterogeneous user terminals and applications. A convergence of Mobile Edge Computing (MEC) and Software-Defined Networks (SDN) delivers gigantic challenges and opportunities for enhancing computing resources and user Quality of Service (QoS) in fronthaul and backhaul networks. Due to the precipitous expansion of user media in the 5G epoch, efficient media forensics methods are mandatory for specifying and offering effective safety handling based on individual application requirements. According to the exponential increment of Heterogeneous Internet of Things (HetIoT) devices, gigantic traffic will generate through bottleneck 5G fronthaul gateways. 5G fronthaul network environments consist of inadequate resources to surmount the enormous user traffic and communications, QoS will be reduced when the existence of traffic congestion occurs. To confront the aforementioned issues, this paper proposed intelligent media forensics and traffic handling scheme for controlling the Uplink (UL) transmission according to the Downlink (DL) statuses. Support Vector Machine (SVM) algorithm was applied to conduct the media forensics and MEC server integrated into fronthaul gateways, in which gateways resources are divided into UL and DL. Caching technology will be a part of 5G environments, and DL will be utilized for traffic caching. So, it is compulsory to adjust the communication traffic according to UL/DL resource utilization and control the forwarding traffic which relies on resource availability. The experiment was conducted by using computer software, and the proposed scheme illustrated a noteworthy outperformance over the conventional method in terms of diverse significant QoS factors including reliability, latency, and communication throughput.
Edge intelligence brings the deployment of applied deep learning (DL) models in edge computing systems to alleviate the core backbone network congestions. The setup of programmable software-defined networking (SDN) control and elastic virtual computing resources within network functions virtualization (NFV) are cooperative for enhancing the applicability of intelligent edge softwarization. To offer advancement for multi-dimensional model task offloading in edge networks with SDN/NFV-based control softwarization, this study proposes a DL mechanism to recommend the optimal edge node selection with primary features of congestion windows, link delays, and allocatable bandwidth capacities. Adaptive partial task offloading policy considered the DL-based recommendation to modify efficient virtual resource placement for minimizing the completion time and termination drop ratio. The optimization problem of resource placement is tackled by a deep reinforcement learning (DRL)-based policy following the Markov decision process (MDP). The agent observes the state spaces and applies value-maximized action of available computation resources and adjustable resource allocation steps. The reward formulation primarily considers taskrequired computing resources and action-applied allocation properties. With defined policies of resource determination, the orchestration procedure is configured within each virtual network function (VNF) descriptor using topology and orchestration specification for cloud applications (TOSCA) by specifying the allocated properties. The simulation for the control rule installation is conducted using Mininet and Ryu SDN controller. Average delay and task delivery/drop ratios are used as the key performance metrics.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.