Energy-Efficient Federated Learning With Resource Allocation for Green IoT Edge Intelligence in B5G
An edge intelligence-aided Internet-of-Things (IoT) network has been proposed to accelerate the response of IoT services by deploying edge intelligence near IoT devices. The transmission of data from IoT devices to the edge nodes leads to large network traffic in the wireless connections. Federatedm...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Ieee Acces
2023
|
| Subjects: | |
| Online Access: | http://eprints.uthm.edu.my/9177/1/J15916_cf78dab738eabff1c909c88fd9243b22.pdf |
| _version_ | 1825710714928496640 |
|---|---|
| author | ADEB SALH, ADEB SALH RAZALI NGAH, RAZALI NGAH LUKMAN AUDAH, LUKMAN AUDAH KWANG SOON KIM, KWANG SOON KIM QAZWAN ABDULLAH, QAZWAN ABDULLAH YAHYA M. AL-MOLIKI, YAHYA M. AL-MOLIKI KHALED A. ALJALOUD, KHALED A. ALJALOUD HAIRUL NIZAM TALIB, HAIRUL NIZAM TALIB |
| author_facet | ADEB SALH, ADEB SALH RAZALI NGAH, RAZALI NGAH LUKMAN AUDAH, LUKMAN AUDAH KWANG SOON KIM, KWANG SOON KIM QAZWAN ABDULLAH, QAZWAN ABDULLAH YAHYA M. AL-MOLIKI, YAHYA M. AL-MOLIKI KHALED A. ALJALOUD, KHALED A. ALJALOUD HAIRUL NIZAM TALIB, HAIRUL NIZAM TALIB |
| author_sort | ADEB SALH, ADEB SALH |
| collection | UTHM |
| description | An edge intelligence-aided Internet-of-Things (IoT) network has been proposed to accelerate the response of IoT services by deploying edge intelligence near IoT devices. The transmission of data from IoT devices to the edge nodes leads to large network traffic in the wireless connections. Federatedm Learning (FL) is proposed to solve the high computational complexity by training the model locally on IoT
devices and sharing the model parameters in the edge nodes. This paper focuses on developing an efficient
integration of joint edge intelligence nodes depending on investigating an energy-efficient bandwidth allocation, computing Central Processing Unit (CPU) frequency, optimization transmission power, and the desired level of learning accuracy to minimize the energy consumption and satisfy the FL time requirement for all IoT devices. The proposal efficiently optimized the computation frequency allocation and reduced energy consumption in IoT devices by solving the bandwidth optimization problem in closed form. The remaining computational frequency allocation, transmission power allocation, and loss could be resolved
with an Alternative Direction Algorithm (ADA) to reduce energy consumption and complexity at every iteration of FL time from IoT devices to edge intelligence nodes. The simulation results indicated that the proposed ADA can adapt the central processing unit frequency and power transmission control to reduce energy consumption at the cost of a small growth of FL time. |
| first_indexed | 2024-03-05T22:01:50Z |
| format | Article |
| id | uthm.eprints-9177 |
| institution | Universiti Tun Hussein Onn Malaysia |
| language | English |
| last_indexed | 2024-03-05T22:01:50Z |
| publishDate | 2023 |
| publisher | Ieee Acces |
| record_format | dspace |
| spelling | uthm.eprints-91772023-07-17T07:32:10Z http://eprints.uthm.edu.my/9177/ Energy-Efficient Federated Learning With Resource Allocation for Green IoT Edge Intelligence in B5G ADEB SALH, ADEB SALH RAZALI NGAH, RAZALI NGAH LUKMAN AUDAH, LUKMAN AUDAH KWANG SOON KIM, KWANG SOON KIM QAZWAN ABDULLAH, QAZWAN ABDULLAH YAHYA M. AL-MOLIKI, YAHYA M. AL-MOLIKI KHALED A. ALJALOUD, KHALED A. ALJALOUD HAIRUL NIZAM TALIB, HAIRUL NIZAM TALIB T Technology (General) An edge intelligence-aided Internet-of-Things (IoT) network has been proposed to accelerate the response of IoT services by deploying edge intelligence near IoT devices. The transmission of data from IoT devices to the edge nodes leads to large network traffic in the wireless connections. Federatedm Learning (FL) is proposed to solve the high computational complexity by training the model locally on IoT devices and sharing the model parameters in the edge nodes. This paper focuses on developing an efficient integration of joint edge intelligence nodes depending on investigating an energy-efficient bandwidth allocation, computing Central Processing Unit (CPU) frequency, optimization transmission power, and the desired level of learning accuracy to minimize the energy consumption and satisfy the FL time requirement for all IoT devices. The proposal efficiently optimized the computation frequency allocation and reduced energy consumption in IoT devices by solving the bandwidth optimization problem in closed form. The remaining computational frequency allocation, transmission power allocation, and loss could be resolved with an Alternative Direction Algorithm (ADA) to reduce energy consumption and complexity at every iteration of FL time from IoT devices to edge intelligence nodes. The simulation results indicated that the proposed ADA can adapt the central processing unit frequency and power transmission control to reduce energy consumption at the cost of a small growth of FL time. Ieee Acces 2023 Article PeerReviewed text en http://eprints.uthm.edu.my/9177/1/J15916_cf78dab738eabff1c909c88fd9243b22.pdf ADEB SALH, ADEB SALH and RAZALI NGAH, RAZALI NGAH and LUKMAN AUDAH, LUKMAN AUDAH and KWANG SOON KIM, KWANG SOON KIM and QAZWAN ABDULLAH, QAZWAN ABDULLAH and YAHYA M. AL-MOLIKI, YAHYA M. AL-MOLIKI and KHALED A. ALJALOUD, KHALED A. ALJALOUD and HAIRUL NIZAM TALIB, HAIRUL NIZAM TALIB (2023) Energy-Efficient Federated Learning With Resource Allocation for Green IoT Edge Intelligence in B5G. Digital Object Identifier, 11. https://doi.org/10.1109/ACCESS.2023.3244099 |
| spellingShingle | T Technology (General) ADEB SALH, ADEB SALH RAZALI NGAH, RAZALI NGAH LUKMAN AUDAH, LUKMAN AUDAH KWANG SOON KIM, KWANG SOON KIM QAZWAN ABDULLAH, QAZWAN ABDULLAH YAHYA M. AL-MOLIKI, YAHYA M. AL-MOLIKI KHALED A. ALJALOUD, KHALED A. ALJALOUD HAIRUL NIZAM TALIB, HAIRUL NIZAM TALIB Energy-Efficient Federated Learning With Resource Allocation for Green IoT Edge Intelligence in B5G |
| title | Energy-Efficient Federated Learning With Resource Allocation for Green IoT Edge Intelligence in B5G |
| title_full | Energy-Efficient Federated Learning With Resource Allocation for Green IoT Edge Intelligence in B5G |
| title_fullStr | Energy-Efficient Federated Learning With Resource Allocation for Green IoT Edge Intelligence in B5G |
| title_full_unstemmed | Energy-Efficient Federated Learning With Resource Allocation for Green IoT Edge Intelligence in B5G |
| title_short | Energy-Efficient Federated Learning With Resource Allocation for Green IoT Edge Intelligence in B5G |
| title_sort | energy efficient federated learning with resource allocation for green iot edge intelligence in b5g |
| topic | T Technology (General) |
| url | http://eprints.uthm.edu.my/9177/1/J15916_cf78dab738eabff1c909c88fd9243b22.pdf |
| work_keys_str_mv | AT adebsalhadebsalh energyefficientfederatedlearningwithresourceallocationforgreeniotedgeintelligenceinb5g AT razalingahrazalingah energyefficientfederatedlearningwithresourceallocationforgreeniotedgeintelligenceinb5g AT lukmanaudahlukmanaudah energyefficientfederatedlearningwithresourceallocationforgreeniotedgeintelligenceinb5g AT kwangsoonkimkwangsoonkim energyefficientfederatedlearningwithresourceallocationforgreeniotedgeintelligenceinb5g AT qazwanabdullahqazwanabdullah energyefficientfederatedlearningwithresourceallocationforgreeniotedgeintelligenceinb5g AT yahyamalmolikiyahyamalmoliki energyefficientfederatedlearningwithresourceallocationforgreeniotedgeintelligenceinb5g AT khaledaaljaloudkhaledaaljaloud energyefficientfederatedlearningwithresourceallocationforgreeniotedgeintelligenceinb5g AT hairulnizamtalibhairulnizamtalib energyefficientfederatedlearningwithresourceallocationforgreeniotedgeintelligenceinb5g |