Wireless Traffic Prediction Based on a Gradient Similarity Federated Aggregation Algorithm
Wireless traffic prediction is critical to the intelligent operation of cellular networks, such as load balancing, congestion control, value-added service promotion, etc. However, the BTS data in each region has certain differences and privacy, and centralized prediction needs to transmit a large am...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/6/4036 |
| _version_ | 1797613553328324608 |
|---|---|
| author | Luzhi Li Yuhong Zhao Jingyu Wang Chuanting Zhang |
| author_facet | Luzhi Li Yuhong Zhao Jingyu Wang Chuanting Zhang |
| author_sort | Luzhi Li |
| collection | DOAJ |
| description | Wireless traffic prediction is critical to the intelligent operation of cellular networks, such as load balancing, congestion control, value-added service promotion, etc. However, the BTS data in each region has certain differences and privacy, and centralized prediction needs to transmit a large amount of traffic data, which will not only cause bandwidth consumption, but may also cause privacy leakage. Federated learning is a kind of distributed learning method with multi-client joint training and no sharing between clients. Based on existing related research, this paper proposes a gradient similarity-based federated aggregation algorithm for wireless traffic prediction (Gradient Similarity-based Federated Aggregation for Wireless Traffic Prediction) (FedGSA). First of all, this method uses a global sharing enhanced data strategy to overcome the data heterogeneity challenge of multi-client collaborative training in federated learning. Secondly, the sliding window scheme is used to construct the dual channel training data to improve the feature learning ability of the model; In addition, to improve the generalization ability of the final global model, a two-layer aggregation scheme based on gradient similarity is proposed. The personalized model is generated by comparing the gradient similarity of each client model, and the central server aggregates the personalized model to finally generate the global model. Finally, the FedGSA algorithm is applied to wireless network traffic prediction. Experiments are conducted on two real traffic datasets. Compared with the mainstream Federated Averaging (FedAvg) algorithm, FedGSA performs better on both datasets and obtains better prediction results on the premise of ensuring the privacy of client traffic data. |
| first_indexed | 2024-03-11T06:57:23Z |
| format | Article |
| id | doaj.art-50950647980a4f03a03c6ea4709e7e54 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T06:57:23Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-50950647980a4f03a03c6ea4709e7e542023-11-17T09:30:37ZengMDPI AGApplied Sciences2076-34172023-03-01136403610.3390/app13064036Wireless Traffic Prediction Based on a Gradient Similarity Federated Aggregation AlgorithmLuzhi Li0Yuhong Zhao1Jingyu Wang2Chuanting Zhang3School of Information Engineering, Inner Mongolia University of Science and Technology, Baotou 014010, ChinaSchool of Information Engineering, Inner Mongolia University of Science and Technology, Baotou 014010, ChinaSchool of Information Engineering, Inner Mongolia University of Science and Technology, Baotou 014010, ChinaDepartment of Electrical and Electronic Engineering, University of Bristol, Bristol BS8 1UB, UKWireless traffic prediction is critical to the intelligent operation of cellular networks, such as load balancing, congestion control, value-added service promotion, etc. However, the BTS data in each region has certain differences and privacy, and centralized prediction needs to transmit a large amount of traffic data, which will not only cause bandwidth consumption, but may also cause privacy leakage. Federated learning is a kind of distributed learning method with multi-client joint training and no sharing between clients. Based on existing related research, this paper proposes a gradient similarity-based federated aggregation algorithm for wireless traffic prediction (Gradient Similarity-based Federated Aggregation for Wireless Traffic Prediction) (FedGSA). First of all, this method uses a global sharing enhanced data strategy to overcome the data heterogeneity challenge of multi-client collaborative training in federated learning. Secondly, the sliding window scheme is used to construct the dual channel training data to improve the feature learning ability of the model; In addition, to improve the generalization ability of the final global model, a two-layer aggregation scheme based on gradient similarity is proposed. The personalized model is generated by comparing the gradient similarity of each client model, and the central server aggregates the personalized model to finally generate the global model. Finally, the FedGSA algorithm is applied to wireless network traffic prediction. Experiments are conducted on two real traffic datasets. Compared with the mainstream Federated Averaging (FedAvg) algorithm, FedGSA performs better on both datasets and obtains better prediction results on the premise of ensuring the privacy of client traffic data.https://www.mdpi.com/2076-3417/13/6/4036wireless traffic predictionfederal learningFedAvgdeep learninggradient similarity |
| spellingShingle | Luzhi Li Yuhong Zhao Jingyu Wang Chuanting Zhang Wireless Traffic Prediction Based on a Gradient Similarity Federated Aggregation Algorithm Applied Sciences wireless traffic prediction federal learning FedAvg deep learning gradient similarity |
| title | Wireless Traffic Prediction Based on a Gradient Similarity Federated Aggregation Algorithm |
| title_full | Wireless Traffic Prediction Based on a Gradient Similarity Federated Aggregation Algorithm |
| title_fullStr | Wireless Traffic Prediction Based on a Gradient Similarity Federated Aggregation Algorithm |
| title_full_unstemmed | Wireless Traffic Prediction Based on a Gradient Similarity Federated Aggregation Algorithm |
| title_short | Wireless Traffic Prediction Based on a Gradient Similarity Federated Aggregation Algorithm |
| title_sort | wireless traffic prediction based on a gradient similarity federated aggregation algorithm |
| topic | wireless traffic prediction federal learning FedAvg deep learning gradient similarity |
| url | https://www.mdpi.com/2076-3417/13/6/4036 |
| work_keys_str_mv | AT luzhili wirelesstrafficpredictionbasedonagradientsimilarityfederatedaggregationalgorithm AT yuhongzhao wirelesstrafficpredictionbasedonagradientsimilarityfederatedaggregationalgorithm AT jingyuwang wirelesstrafficpredictionbasedonagradientsimilarityfederatedaggregationalgorithm AT chuantingzhang wirelesstrafficpredictionbasedonagradientsimilarityfederatedaggregationalgorithm |