FedSTDN: A Federated Learning-Enabled Spatial-Temporal Prediction Model for Wireless Traffic Prediction
- 9 April 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (9) , 8945-8958
Abstract
Wireless Traffic Prediction (WTP) plays a significant role in achieving intelligent resource management forcommunication systems. However, WTP still faces challenges such as inaccurate prediction resulting from the complex spatial-temporal characteristics due to user mobility, high communication overhead caused by the complexity of the prediction model, and user privacy issues stemming from Centralized Learning (CL). To address the aforementioned issues, this paper proposes a WTP framework under the Federated Learning (FL) strategy called Federated Spatial-Temporal Dual-attention based Network (FedSTDN). Aiming at improving communication efficiency and simultaneously representing various wireless traffic patterns, a data augmentation-based clustering algorithm is adopted, which groups cells into different regions using a small augmented dataset, facilitating subsequent processing. To improve prediction performance, a local prediction model based on Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) is proposed to capture the short- and long-term dependencies of traffic. Additionally, a novel Kolmogorov-Arnold Network (KAN) layer is introduced to replace the traditional Multi-Layer Perceptron (MLP) layer, further enhancing prediction performance. Simulations on two different real-world datasets verify the effectiveness and efficiency of FedSTDN. Compared to the well-performing baseline, the proposed FedSTDN achieves up to 32.83% and 24.30% improvements in Mean Square Error (MSE) and Mean Absolute Error (MAE) on the Milan dataset, respectively. For the Trentino dataset, FedSTDN achieves up to 17.25% and 5.86% improvements in MSE and MAE, respectively.Keywords
Funding Information
- National Natural Science Foundation of Chinaunder (62231020)
- Innovation Capability Support Program of Shaanxi (2024RS-CXTD-01)
- Technology Innovation Leading Program of Shaanxi (2023KXJ-116)
This publication has 44 references indexed in Scilit:
- Federated Client Selection and Attention-Based Aggregation Algorithm on Non-IID Data2024
- Distributed Core Network Traffic Prediction Architecture Based on Vertical Federated Learning2024
- A decentralized federated learning-based spatial–temporal model for freight traffic speed forecastingExpert Systems with Applications, 2023
- Federated Non-Intrusive Load Monitoring for Smart Homes Utilizing Attention-Based Aggregation2023
- FedAGCN: A traffic flow prediction framework based on federated learning and Asynchronous Graph Convolutional NetworkApplied Soft Computing, 2023
- Federated learning on non-IID data: A surveyNeurocomputing, 2021
- A deep learning method based on an attention mechanism for wireless network traffic predictionAd Hoc Networks, 2020
- A new perspective: Recognizing online handwritten Chinese characters via 1-dimensional CNNInformation Sciences, 2019
- A multi-source dataset of urban life in the city of Milan and the Province of TrentinoScientific Data, 2015
- On the representation of continuous functions of several variables by superpositions of continuous functions of a smaller number of variables1961