Adaptive Resource Optimized Edge Federated Learning in Real-Time Image Sensing Classifications
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-tim...
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
IEEE
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/d4fbb6f14bb64e78a81101f8fc2a147f |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| Sumario: | 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 q-learning 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. |
|---|