Federated learning framework for mobile edge computing networks
The continuous growth of smart devices needing processing has led to moving storage and computation from cloud to the network edges, giving rise to the edge computing paradigm. Owing to the limited capacity of edge computing nodes, the presence of popular applications in the edge nodes results in si...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-11-01
|
| Series: | CAAI Transactions on Intelligence Technology |
| Subjects: | |
| Online Access: | https://digital-library.theiet.org/content/journals/10.1049/trit.2019.0049 |
| _version_ | 1819122554124632064 |
|---|---|
| author | Romano Fantacci Benedetta Picano |
| author_facet | Romano Fantacci Benedetta Picano |
| author_sort | Romano Fantacci |
| collection | DOAJ |
| description | The continuous growth of smart devices needing processing has led to moving storage and computation from cloud to the network edges, giving rise to the edge computing paradigm. Owing to the limited capacity of edge computing nodes, the presence of popular applications in the edge nodes results in significant improvements in users’ satisfaction and service accomplishment. However, the high variability in the content requests makes prediction demand not trivial and, typically, the majority of the classical prediction approaches require the gathering of personal users' information at a central unit, giving rise to many users' privacy issues. In this context, federated learning gained attention as a solution to perform learning procedures from data disseminated across multiple users, keeping the sensitive data protected. This study applies federated learning to the demand prediction problem, to accurately forecast the more popular application types in the network. The proposed framework reaches high accuracy levels on the predicted applications demand, aggregating in a global and weighted model the feedback received by users, after their local training. The validity of the proposed approach is verified by performing a virtual machine replica copies and comparison with the alternative forecasting approach based on chaos theory and deep learning. |
| first_indexed | 2024-12-22T06:54:18Z |
| format | Article |
| id | doaj.art-1615ad3b95124a4f8ec474b2b9e41293 |
| institution | Directory Open Access Journal |
| issn | 2468-2322 |
| language | English |
| last_indexed | 2024-12-22T06:54:18Z |
| publishDate | 2019-11-01 |
| publisher | Wiley |
| record_format | Article |
| series | CAAI Transactions on Intelligence Technology |
| spelling | doaj.art-1615ad3b95124a4f8ec474b2b9e412932022-12-21T18:35:02ZengWileyCAAI Transactions on Intelligence Technology2468-23222019-11-0110.1049/trit.2019.0049TRIT.2019.0049Federated learning framework for mobile edge computing networksRomano Fantacci0Benedetta Picano1Department of Information Engineering, University of FlorenceDepartment of Information Engineering, University of FlorenceThe continuous growth of smart devices needing processing has led to moving storage and computation from cloud to the network edges, giving rise to the edge computing paradigm. Owing to the limited capacity of edge computing nodes, the presence of popular applications in the edge nodes results in significant improvements in users’ satisfaction and service accomplishment. However, the high variability in the content requests makes prediction demand not trivial and, typically, the majority of the classical prediction approaches require the gathering of personal users' information at a central unit, giving rise to many users' privacy issues. In this context, federated learning gained attention as a solution to perform learning procedures from data disseminated across multiple users, keeping the sensitive data protected. This study applies federated learning to the demand prediction problem, to accurately forecast the more popular application types in the network. The proposed framework reaches high accuracy levels on the predicted applications demand, aggregating in a global and weighted model the feedback received by users, after their local training. The validity of the proposed approach is verified by performing a virtual machine replica copies and comparison with the alternative forecasting approach based on chaos theory and deep learning.https://digital-library.theiet.org/content/journals/10.1049/trit.2019.0049data privacyneural netslearning (artificial intelligence)virtual machinesmobile computingcomputer networksfederated learning frameworkmobile edge computing networkssmart devicesmoving storagenetwork edgesedge computing paradigmedge computing nodescontent requestsprediction demandclassical prediction approachespersonal userscentral unitlearning proceduresmultiple userssensitive dataapplication demand prediction problempopular application typeshigh accuracy levelspredicted applications demandlocal training processdeep learning |
| spellingShingle | Romano Fantacci Benedetta Picano Federated learning framework for mobile edge computing networks CAAI Transactions on Intelligence Technology data privacy neural nets learning (artificial intelligence) virtual machines mobile computing computer networks federated learning framework mobile edge computing networks smart devices moving storage network edges edge computing paradigm edge computing nodes content requests prediction demand classical prediction approaches personal users central unit learning procedures multiple users sensitive data application demand prediction problem popular application types high accuracy levels predicted applications demand local training process deep learning |
| title | Federated learning framework for mobile edge computing networks |
| title_full | Federated learning framework for mobile edge computing networks |
| title_fullStr | Federated learning framework for mobile edge computing networks |
| title_full_unstemmed | Federated learning framework for mobile edge computing networks |
| title_short | Federated learning framework for mobile edge computing networks |
| title_sort | federated learning framework for mobile edge computing networks |
| topic | data privacy neural nets learning (artificial intelligence) virtual machines mobile computing computer networks federated learning framework mobile edge computing networks smart devices moving storage network edges edge computing paradigm edge computing nodes content requests prediction demand classical prediction approaches personal users central unit learning procedures multiple users sensitive data application demand prediction problem popular application types high accuracy levels predicted applications demand local training process deep learning |
| url | https://digital-library.theiet.org/content/journals/10.1049/trit.2019.0049 |
| work_keys_str_mv | AT romanofantacci federatedlearningframeworkformobileedgecomputingnetworks AT benedettapicano federatedlearningframeworkformobileedgecomputingnetworks |