Which Deep Learner? A Systematic Evaluation of Advanced Deep Forecasting Models Accuracy and Efficiency for Network Traffic Prediction
Organizations: Kyushu University, Fukuoka, Japan
Abstract
Network traffic prediction is an essential tool for automating modern network management. It is a difficult time series forecasting (TSF) problem that has been addressed by Deep Learning (DL) models due to their ability to capture complex patterns. Recent years have witnessed advances in deep forecasting models, from sophisticated transformer architectures to simple linear models, improving performance across diverse prediction tasks. However, given the diversity of these models, the variability of network traffic across environments and timescales, and the inherent challenges of network traffic prediction, it is essential to identify effective deployment choices and modeling directions. Henceforth, this study systematically identifies 12 deep forecasting models, comprising 8 advanced TSF models and 4 traditional deep learning architectures -- each with unique advantages for network traffic prediction -- against 3 statistical baselines, for a total of 15 forecasting methods and evaluate them on four real traffic datasets, across multiple time scales and horizons, assessing performance, robustness to anomalies, data gaps, external factors, data efficiency, and resource efficiency in terms of time, memory, and energy. Our results provide insights into model behaviour and guidelines for network management, highlighting performance regimes, efficiency thresholds, and promising architectures that balance accuracy, efficiency, and robustness to traffic challenges.
Figures & tables
| Work | NTP Task | Data Quality | Data Quantity | Deep Learning Models | TSF Models | Model Efficiency | ||||||||
| Time Scale | Horizon | Outliers | Missing Values | External Factors | MLP | RNN | CNN | Transf. | Size | Time | Energy | |||
| Oliveira et al. (2016) [ 23 ] | M, H, D | Short | ✓ | ✓ | ✓ | |||||||||
| Jiang (2022) [ 24 ] | H | Short | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ||||||
| Ferreira et al. (2023) [ 6 ] | H | Short | ✓ | ✓ | ✓ | |||||||||
| Saha et al. (2023) [ 22 ] | M | Short | ✓ | ✓ | ||||||||||
| Aouedi et al. (2025) [ 7 ] | M | Short | ✓ | ✓ | ✓ | |||||||||
| Contribution | Our Work | Existing Work |
| Identifying, Implementing, and Evaluating Advanced TSF Models for NTP | We identify promising TSF trends and implement and evaluate 12 deep forecasting models, each with unique advantages that address the challenges of network traffic prediction for multiscale and multi-horizon NTP. | Despite recent advances in the TSF field with diverse architectures and complexities, comparative studies on network traffic prediction mainly focus on RNN architectures evaluated on a single timescale. |
| Developing a Systematic Methodology and Comprehensive NTP Benchmark | We analyze the impact of traffic challenges—such as anomalies, missing data, and externally influenced variations—on distinct network traffic datasets, reflecting real-world challenges. | To our knowledge, there has been no comprehensive assessment of model performance on real-world traffic characteristics across various network environments and timescales in current traffic prediction research. |
| Model Behavior Insights and Selection Guidelines | We connect model behavior to traffic characteristics and deployment constraints, identifying performance regimes and efficiency thresholds that inform model selection and future development. | Existing work primarily compares predictive performance, with limited attention to data efficiency, tuning effort, and energy consumption or their implications for model selection. |
| Dataset Code | Scale (Minute) | Size (Points) | Missing (%) | Outlier (%) | Varient Days(%) | |
| Abilene | A5M | 5 | 55008 | 13.6 | 1.9 | – |
| A15M | 15 | 18336 | 13.6 | 1.9 | – | |
| A12H | 720 | 382 | 13.6 | 1.9 | – | |
| Geant | G15M | 15 | 11394 | 5.5 | 0.21 | – |
| Cesnet | C10M | 10 | 40308 | 0.6 | 0.31 | – |
| Model | Architectural Paradigm | Computation Complexity | Processing | Innovative Time Series Processing Logic | Key Hyperparamters |
| LSTM [ 46 , 47 ] | Sequential Recurrent | Sequential | Uses gated memory cells to retain long-term dependencies in sequential data. | Hidden Size, Number of Layers. | |
| Seq2Seq [ 48 ] | RNN Encoder–Decoder | Sequential | Encodes input sequence into a context vector for a decoder to generate variable-length outputs. | Hidden size, encoder layers, decoder layers. | |
| Seq2Seq_Attn [ 49 ] | RNN Encoder–Decoder with Attention | Sequential | Introduced Attention to dynamically access the entire input history at each decoding step. | Hidden size, encoder layers, decoder layers. | |
| N-BEATS [ 52 ] | Stack of MLP Blocks | Parallel | Stacked blocks that learn basis expansions for implicit trend-seasonality decomposition. | Block layers, layer size, block types. | |
| DLinear [ 21 ] | Decomposition with Linear Layer | Parallel | Decomposes series into trend and seasonal parts, each forecasted via a simple linear layer. | Moving average size | |
| TiDE [ 16 ] | MLP Encoder–Decoder | Parallel | Uses residual MLPs to transform historical and exogenous inputs into a hidden state projected over the future horizon. | Hidden size, encoder layers, decoder layers. |
| Time Scale | Datasets | Input Length | Output Length | Prediction Horizon |
| 5 minutes | A5M, K5M | 1 hour | ||
| 10 minutes | C10M | 6 hours | ||
| 15 minutes | G15M, A15M, K15M | 6 hours | ||
| 1 hours | K1H, C1H | 168 | 24 | 1 Day |
| 12 hours | A12H, K12H | 14 | 60 | 1 month |
| 1 Day | C1D | 7 | 30 | 1 month |
| Unique Model Hyperparameters | ||
| Model | Hyperparameter | Range |
| LSTM, Seq2Seq, Seq2Seq_Attn | Hidden Size | {32, 64, 128 , 256} |
| LSTM Layers | ( 1 , 4) | |
| TCN | TCN Layers | (1, 4 ) |
| Kernel Size | { 3 , 5, 6} | |
| Model | Mean Skill Score (%) | Significance | |
| DLinear | +31.0% | 0.000038 | |
| PatchTST | +28.8% | 0.005329 | ** |
| TiDE | +26.6% | 0.044559 | |
| TimeXer | +18.5% | 0.049366 | |
| TFT | +17.9% | 0.018082 | |
| Transformer | +17.6% | 0.022987 |
| Model | Tunability (%) | Evaluated configs. | HPO time (min) | HPO cost (min/config.) |
| LSTM | [-1pt] | [-1pt] | [-1pt] | [-1pt] |
| Seq2Seq | [-1pt] | [-1pt] | [-1pt] | [-1pt] |
| Seq2SeqAttn | [-1pt] | [-1pt] | [-1pt] | [-1pt] |
| TCN | [-1pt] | [-1pt] | [-1pt] | [-1pt] |
| Transformer | [-1pt] | [-1pt] | [-1pt] | [-1pt] |
| NBeats | [-1pt] | [-1pt] | [-1pt] | [-1pt] |
| a5m | k5m | c10m | g15m | |
| a5m | 1.0 n.s. | 0.006 ** | 0.006 ** | 0.01 * |
| k5m | 0.006 ** | 1.0 n.s. | 1.0 n.s. | 0.999 n.s. |
| c10m | 0.006 ** | 1.0 n.s. | 1.0 n.s. | 0.999 n.s. |
| g15m | 0.01 * | 0.999 n.s. | 0.999 n.s. | 1.0 n.s. |
Traffic Forecasting
Traffic forecasting predicts future flows, speeds, demand, travel times, and congestion from spatial, temporal, and contextual data.
See all 91 papers