English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Edge machine learning involves the deployment of learning algorithms at thenetwork edge to leverage massive distributed data and computation resources totrain artificial intelligence (AI) models. Among others, the framework offederated edge learning (FEEL) is popular for its data-privacy preservation.FEEL coordinates global model training at an edge server and local modeltraining at edge devices that are connected by wireless links. This workcontributes to the energy-efficient implementation of FEEL in wireless networksby designing joint computation-and-communication resource management($\text{C}^2$RM). The design targets the state-of-the-art heterogeneous mobilearchitecture where parallel computing using both a CPU and a GPU, calledheterogeneous computing, can significantly improve both the performance andenergy efficiency. To minimize the sum energy consumption of devices, wepropose a novel $\text{C}^2$RM framework featuring multi-dimensional controlincluding bandwidth allocation, CPU-GPU workload partitioning and speed scalingat each device, and $\text{C}^2$ time division for each link. The key componentof the framework is a set of equilibriums in energy rates with respect todifferent control variables that are proved to exist among devices or betweenprocessing units at each device. The results are applied to designing efficientalgorithms for computing the optimal $\text{C}^2$RM policies faster than thestandard optimization tools. Based on the equilibriums, we further designenergy-efficient schemes for device scheduling and greedy spectrum sharing thatscavenges "spectrum holes" resulting from heterogeneous $\text{C}^2$ timedivisions among devices. Using a real dataset, experiments are conducted todemonstrate the effectiveness of $\text{C}^2$RM on improving the energyefficiency of a FEEL system.

Energy-Efficient Resource Management for Federated Edge Learning with CPU-GPU Heterogeneous Computing