Mobility Prediction and Resource-Aware Client Selection for Federated Learning in IoT
This paper presents the Mobility-Aware Client Selection (MACS) strategy, developed to address the challenges associated with client mobility in Federated Learning (FL). FL enables decentralized machine learning by allowing collaborative model training without sharing raw data, preserving privacy. Ho...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Future Internet |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-5903/17/3/109 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849341916682911744 |
|---|---|
| author | Rana Albelaihi |
| author_facet | Rana Albelaihi |
| author_sort | Rana Albelaihi |
| collection | DOAJ |
| description | This paper presents the Mobility-Aware Client Selection (MACS) strategy, developed to address the challenges associated with client mobility in Federated Learning (FL). FL enables decentralized machine learning by allowing collaborative model training without sharing raw data, preserving privacy. However, client mobility and limited resources in IoT environments pose significant challenges to the efficiency and reliability of FL. MACS is designed to maximize client participation while ensuring timely updates under computational and communication constraints. The proposed approach incorporates a Mobility Prediction Model to forecast client connectivity and resource availability and a Resource-Aware Client Evaluation mechanism to assess eligibility based on predicted latencies. MACS optimizes client selection, improves convergence rates, and enhances overall system performance by employing these predictive capabilities and a dynamic resource allocation strategy. The evaluation includes comparisons with advanced baselines such as Reinforcement Learning-based FL (RL-based) and Deep Learning-based FL (DL-based), in addition to Static and Random selection methods. For the CIFAR dataset, MACS achieved a final accuracy of 95%, outperforming Static selection (85%), Random selection (80%), RL-based FL (90%), and DL-based FL (93%). Similarly, for the MNIST dataset, MACS reached 98% accuracy, surpassing Static selection (92%), Random selection (88%), RL-based FL (94%), and DL-based FL (96%). Additionally, MACS consistently required fewer iterations to achieve target accuracy levels, demonstrating its efficiency in dynamic IoT environments. This strategy provides a scalable and adaptable solution for sustainable federated learning across diverse IoT applications, including smart cities, healthcare, and industrial automation. |
| format | Article |
| id | doaj-art-9f6f6e932dc14f64a04e3499f58033e4 |
| institution | Kabale University |
| issn | 1999-5903 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Future Internet |
| spelling | doaj-art-9f6f6e932dc14f64a04e3499f58033e42025-08-20T03:43:31ZengMDPI AGFuture Internet1999-59032025-03-0117310910.3390/fi17030109Mobility Prediction and Resource-Aware Client Selection for Federated Learning in IoTRana Albelaihi0Department of Computer Science, College of Engineering and Information Technology, Onaizah Colleges, Qassim 56447, Saudi ArabiaThis paper presents the Mobility-Aware Client Selection (MACS) strategy, developed to address the challenges associated with client mobility in Federated Learning (FL). FL enables decentralized machine learning by allowing collaborative model training without sharing raw data, preserving privacy. However, client mobility and limited resources in IoT environments pose significant challenges to the efficiency and reliability of FL. MACS is designed to maximize client participation while ensuring timely updates under computational and communication constraints. The proposed approach incorporates a Mobility Prediction Model to forecast client connectivity and resource availability and a Resource-Aware Client Evaluation mechanism to assess eligibility based on predicted latencies. MACS optimizes client selection, improves convergence rates, and enhances overall system performance by employing these predictive capabilities and a dynamic resource allocation strategy. The evaluation includes comparisons with advanced baselines such as Reinforcement Learning-based FL (RL-based) and Deep Learning-based FL (DL-based), in addition to Static and Random selection methods. For the CIFAR dataset, MACS achieved a final accuracy of 95%, outperforming Static selection (85%), Random selection (80%), RL-based FL (90%), and DL-based FL (93%). Similarly, for the MNIST dataset, MACS reached 98% accuracy, surpassing Static selection (92%), Random selection (88%), RL-based FL (94%), and DL-based FL (96%). Additionally, MACS consistently required fewer iterations to achieve target accuracy levels, demonstrating its efficiency in dynamic IoT environments. This strategy provides a scalable and adaptable solution for sustainable federated learning across diverse IoT applications, including smart cities, healthcare, and industrial automation.https://www.mdpi.com/1999-5903/17/3/109federated learningclient selectionmobility predictiondynamic IoT environments |
| spellingShingle | Rana Albelaihi Mobility Prediction and Resource-Aware Client Selection for Federated Learning in IoT Future Internet federated learning client selection mobility prediction dynamic IoT environments |
| title | Mobility Prediction and Resource-Aware Client Selection for Federated Learning in IoT |
| title_full | Mobility Prediction and Resource-Aware Client Selection for Federated Learning in IoT |
| title_fullStr | Mobility Prediction and Resource-Aware Client Selection for Federated Learning in IoT |
| title_full_unstemmed | Mobility Prediction and Resource-Aware Client Selection for Federated Learning in IoT |
| title_short | Mobility Prediction and Resource-Aware Client Selection for Federated Learning in IoT |
| title_sort | mobility prediction and resource aware client selection for federated learning in iot |
| topic | federated learning client selection mobility prediction dynamic IoT environments |
| url | https://www.mdpi.com/1999-5903/17/3/109 |
| work_keys_str_mv | AT ranaalbelaihi mobilitypredictionandresourceawareclientselectionforfederatedlearninginiot |