Aug 2026· International Conference on Circuit, Power and Computing Technologies· pp. 1702-1706· 0 citations· 20 references
Abstract
Accurate network traffic forecasting is fundamental to Quality of Service enforcement, proactive congestion control, and dynamic resource allocation in modern backbone and software-defined networks. However, existing approaches often lack adaptability to non-stationary traffic patterns and fail to provide a consistent comparative evaluation across diverse models under unified experimental conditions. This paper presents an adaptive, data-driven framework that integrates Bidirectional LSTM (Bi-LSTM), LSTM, Gated Recurrent Units (GRU), Random Forest, XGBoost, Support Vector Regression (SVR), and classical ARIMA regressors for short- and medium-term traffic forecasting. The proposed architecture couples multi-scale temporal feature extraction with a feedback-driven online retraining loop, enabling continuous adaptation to distributional shifts. Extensive experiments are conducted on two publicly available datasets CAIDA Equinix backbone traces and the MAWI traffic archive comprising over 72 hours of flow-level measurements at one-minute resolution. Bi-LSTM achieves the lowest RMSE of 0.0287 Gbps and the highest $R^{2}=0.9714$, outperforming ARIMA by $\mathbf{7 5 . 2 \%}$ and vanilla LSTM by $\mathbf{8 . 0 \%}$. All results are confirmed via paired Diebold-Mariano (DM) tests and Student’s t-tests $(p \lt 0.01)$. System inference latency of 2.3 ms per batch satisfies real-time SDN control-plane requirements. Code and preprocessing scripts will be made publicly available to ensure full reproducibility.
The rapid proliferation of data-intensive applications, cloud infrastructure, and IoT ecosystems has made proactive resource provisioning critical for maintaining optimal network performance. However, network administrators face a constant battle against capacity constraints, where traditional reactive approaches fail to accurately anticipate traffic fluctuations. This inability to foresee demand leads to costly over-provisioning, unexpected downtime, and degraded quality of service directly impacting operational budgets and business continuity. To achieve efficient capacity planning, accurate forecasting of bandwidth utilization is essential. This study addresses the challenge by evaluating a diverse spectrum of models including seasonal decomposition, Prophet, Random Forest, XGBoost, Support Vector Regression, and advanced deep learning architectures like bidirectional and Convolutional LSTMs - using a common interface dataset benchmarked across MAPE, NRMSE, and R-square metrics. Ultimately, this research delivers actionable insights into the trade-offs between model accuracy and computational efficiency, empowering engineers, operators, and business owners to select the optimal forecasting model for their specific infrastructure needs.
Niraj Gadhe, K. Bhardwaj, M. Jain et al.· arXiv.org· 0 citations
The rapid growth in traffic volumes has increased the demand for traffic-flow forecasting models with stronger prediction capability. Traditional methods that rely on local feature extraction and static spatial graph construction can no longer fully meet these requirements. To address the short- and long-term fluctuations in freeway traffic flow and the dynamic correlations among node flows, this study proposes ASGF-TAGCN, a traffic-flow forecasting model based on a component-specific multi-source graph fusion mechanism. The model integrates CEEMDAN-based multiscale decomposition, multi-source graph construction (physical topology, DTW-based semantic similarity, and node-adaptive learning), a learnable fusion mechanism for multi-source spatial modeling, Transformer-based temporal modeling, and IHPO hyperparameter optimization. Across three independent training runs at the 30 min forecasting horizon, ASGF-TAGCN achieved a mean MAE of 2.2982 ± 0.1181 and a mean RMSE of 3.1147 ± 0.1059, where the variability is reported as the sample standard deviation. In the fixed seed-42 run used for the baseline comparison, ASGF-TAGCN achieved an MAE of 2.219 and an RMSE of 3.063, reducing the two errors by 14.72% and 11.58%, respectively, relative to T-AGCN, the strongest baseline among the selected models. These results demonstrate that ASGF-TAGCN consistently reduces prediction errors and effectively captures complex spatiotemporal dependencies, offering a reliable solution for short-term freeway traffic-flow forecasting.
Traffic congestion prediction is essential for congestion mitigation, but the COVID-19 pandemic and related control measures altered travel behavior and increased prediction complexity. This study predicts congestion in Alameda County, California, during pre-lockdown, lockdown, and post-lockdown periods. Weather, seasonality, and COVID-19 variables are incorporated, and Recursive Feature Elimination with Cross-Validation is used to select important features and reduce overfitting. Support vector regression, multiple linear regression, recurrent neural networks, and long short-term memory networks are trained and optimized. Because LSTM is more sensitive to hyperparameter settings, an adaptive parameter selection approach is used, while SVR and RNN are manually tuned. Performance is evaluated using Normalized Root Mean Square Error. Bidirectional LSTM consistently performs best across all periods because it captures temporal dependence in both directions. Integrated Gradients is used to interpret Bi-LSTM predictions, and SHapley Additive exPlanations is applied to SVR. New COVID-19 cases have a mainly negative effect on congestion during lockdown and post-lockdown, likely due to greater risk awareness, voluntary travel reduction, and compliance with mobility restrictions. In the post-pandemic period, higher hospitalization reduces travel and congestion, while higher fuel prices do not prevent a shift toward private vehicles and therefore increase congestion.
Danmiao Zhu, Chi-Sin Ng, Litian Xie et al.· Communications in Transporta...· 2 citations
A key contribution of this study lies in its comparative synthesis of ML and DL models, revealing that hybrid and graph-based DL architectures consistently outperform traditional ML methods when handling large-scale, heterogeneous traffic datasets.
Thabo Matue, A. A. Akinyelu, Mase Mokotsolane· International Journal of Dat...· 0 citations
Short-term traffic flow forecasting is essential for travel safety, congestion avoidance, and effective traffic management as an integral part of intelligent transport systems. Long short-term memory (LSTM) has become a promising technique for forecasting traffic flow. Unfortunately, the LSTM model does not achieve adequate forecast accuracy due to noisy traffic data and poor selection of hyperparameter optimization values. To address these limitations, this study proposes a composite SFFSDF-LSTM model that integrates sinusoidal firefly feature selection (SFFS) and dragonfly (DF) algorithms with an LSTM network. The SFFS algorithm performs adaptive feature selection, while the DF algorithm optimizes hyperparameters to improve convergence and prediction accuracy. The proposed model efficiently identifies the optimal set of LSTM features, weights, biases, and hyperparameters for domain traffic flow prediction while minimizing training errors. From the perspective of error analysis and predictive analytics, the predictive accuracy of the combined model is evaluated and found to be superior to traditional nonparametric and baseline deep learning models.
The rapid growth of Internet applications has led to increasingly complex network traffic, posing new challenges for accurate long-term forecasting. To address the limitations of traditional linear models in capturing nonlinear temporal dependencies, this paper proposes an improved TSM-Transformer model that introduces a Trend Attention module for long-term tendencies and a Seasonal Attention module for periodic variations. The model also optimizes encoder–decoder fusion to enhance information interaction. Experiments on the Traffic_One_Cell dataset demonstrate that the proposed model achieves the lowest MAE (1.2 × 10⁻3) and RMSE (2.9 × 10⁻3) with an R2 of 92.1%, outperforming ARIMA, GRU, and SVM baselines. The results confirm the model’s superiority in long-horizon network traffic prediction, providing reliable support for proactive resource allocation and network management.
Yuanxin Gao, Jianping Wu, Lei Liu et al.· 2026 IEEE International Conf...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
