Reliable Federated Learning Systems Based on Intelligent Resource Sharing Scheme for Big Data Internet of Things
Federated learning (FL) is the up-to-date approach for privacy constraints Internet of Things (IoT) applications in next-generation mobile network (NGMN), <inline-formula> <tex-math notation="LaTeX">$5^{\mathrm {th}}$ </tex-math></inline-formula> generation (5G), an...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9503402/ |
| _version_ | 1818584124889235456 |
|---|---|
| author | Sa Math Prohim Tam Seokhoon Kim |
| author_facet | Sa Math Prohim Tam Seokhoon Kim |
| author_sort | Sa Math |
| collection | DOAJ |
| description | Federated learning (FL) is the up-to-date approach for privacy constraints Internet of Things (IoT) applications in next-generation mobile network (NGMN), <inline-formula> <tex-math notation="LaTeX">$5^{\mathrm {th}}$ </tex-math></inline-formula> generation (5G), and <inline-formula> <tex-math notation="LaTeX">$6^{\mathrm {th}}$ </tex-math></inline-formula> generation (6G), respectively. Due to 5G/6G is based on new radio (NR) technology, the multiple-input and multiple-output (MIMO) of radio services for heterogeneous IoT devices have been performed. The autonomous resource allocation and the intelligent quality of service class identity (IQCI) in mobile networks based on FL systems are obligated to meet the requirements of privacy constraints of IoT applications. In massive FL communications, the heterogeneous local devices propagate their local models and parameters over 5G/6G networks to the aggregation servers in edge cloud areas. Therefore, the assurance of network reliability is compulsory to facilitate end-to-end (E2E) reliability of FL communications and provide the satisfaction of model decisions. This paper proposed an intelligent lightweight scheme based on the reference software-defined networking (SDN) architecture to handle the massive FL communications between clients and aggregators to meet the mentioned perspectives. The handling method adjusts the model parameters and batches size of the individual client to reflect the apparent network conditions classified by the k-nearest neighbor (KNN) algorithm. The proposed system showed notable experimented metrics, including the E2E FL communication latency, throughput, system reliability, and model accuracy. |
| first_indexed | 2024-12-16T08:16:12Z |
| format | Article |
| id | doaj.art-e316861ad4ab4afbbff99ce8c1a8623c |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-16T08:16:12Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-e316861ad4ab4afbbff99ce8c1a8623c2022-12-21T22:38:15ZengIEEEIEEE Access2169-35362021-01-01910809110810010.1109/ACCESS.2021.31018719503402Reliable Federated Learning Systems Based on Intelligent Resource Sharing Scheme for Big Data Internet of ThingsSa Math0https://orcid.org/0000-0002-8690-4750Prohim Tam1https://orcid.org/0000-0002-3842-7689Seokhoon Kim2https://orcid.org/0000-0002-7919-6557Department of Software Convergence, Soonchunhyang University, Asan-si, Republic of KoreaDepartment of Software Convergence, Soonchunhyang University, Asan-si, Republic of KoreaDepartment of Software Convergence, Soonchunhyang University, Asan-si, Republic of KoreaFederated learning (FL) is the up-to-date approach for privacy constraints Internet of Things (IoT) applications in next-generation mobile network (NGMN), <inline-formula> <tex-math notation="LaTeX">$5^{\mathrm {th}}$ </tex-math></inline-formula> generation (5G), and <inline-formula> <tex-math notation="LaTeX">$6^{\mathrm {th}}$ </tex-math></inline-formula> generation (6G), respectively. Due to 5G/6G is based on new radio (NR) technology, the multiple-input and multiple-output (MIMO) of radio services for heterogeneous IoT devices have been performed. The autonomous resource allocation and the intelligent quality of service class identity (IQCI) in mobile networks based on FL systems are obligated to meet the requirements of privacy constraints of IoT applications. In massive FL communications, the heterogeneous local devices propagate their local models and parameters over 5G/6G networks to the aggregation servers in edge cloud areas. Therefore, the assurance of network reliability is compulsory to facilitate end-to-end (E2E) reliability of FL communications and provide the satisfaction of model decisions. This paper proposed an intelligent lightweight scheme based on the reference software-defined networking (SDN) architecture to handle the massive FL communications between clients and aggregators to meet the mentioned perspectives. The handling method adjusts the model parameters and batches size of the individual client to reflect the apparent network conditions classified by the k-nearest neighbor (KNN) algorithm. The proposed system showed notable experimented metrics, including the E2E FL communication latency, throughput, system reliability, and model accuracy.https://ieeexplore.ieee.org/document/9503402/Big datafederated learningmassive Internet of Thingsmachine learningsoftware-defined network |
| spellingShingle | Sa Math Prohim Tam Seokhoon Kim Reliable Federated Learning Systems Based on Intelligent Resource Sharing Scheme for Big Data Internet of Things IEEE Access Big data federated learning massive Internet of Things machine learning software-defined network |
| title | Reliable Federated Learning Systems Based on Intelligent Resource Sharing Scheme for Big Data Internet of Things |
| title_full | Reliable Federated Learning Systems Based on Intelligent Resource Sharing Scheme for Big Data Internet of Things |
| title_fullStr | Reliable Federated Learning Systems Based on Intelligent Resource Sharing Scheme for Big Data Internet of Things |
| title_full_unstemmed | Reliable Federated Learning Systems Based on Intelligent Resource Sharing Scheme for Big Data Internet of Things |
| title_short | Reliable Federated Learning Systems Based on Intelligent Resource Sharing Scheme for Big Data Internet of Things |
| title_sort | reliable federated learning systems based on intelligent resource sharing scheme for big data internet of things |
| topic | Big data federated learning massive Internet of Things machine learning software-defined network |
| url | https://ieeexplore.ieee.org/document/9503402/ |
| work_keys_str_mv | AT samath reliablefederatedlearningsystemsbasedonintelligentresourcesharingschemeforbigdatainternetofthings AT prohimtam reliablefederatedlearningsystemsbasedonintelligentresourcesharingschemeforbigdatainternetofthings AT seokhoonkim reliablefederatedlearningsystemsbasedonintelligentresourcesharingschemeforbigdatainternetofthings |