This manuscript presents a comprehensive analysis of predictive modeling optimization in managed Wi-Fi networks through the integration of clustering algorithms and model evaluation techniques. The study addresses the challenges of deploying forecasting algorithms in large-scale environments managed by a central controller constrained by memory and computational resources. Feature-based clustering, supported by Principal Component Analysis (PCA) and advanced feature engineering, is employed to group time series data based on shared characteristics, enabling the development of cluster-specific predictive models. Comparative evaluations between global models (GMs) and cluster-specific models demonstrate that cluster-specific models consistently achieve superior accuracy in terms of Mean Absolute Error (MAE) values in high-activity clusters. The trade-offs between model complexity (and accuracy) and resource utilization are analyzed, highlighting the scalability of tailored modeling approaches. The findings advocate for adaptive network management strategies that optimize resource allocation through selective model deployment, enhance predictive accuracy, and ensure scalable operations in large-scale, centrally managed Wi-Fi environments.
Figures & tables
Fig. 1 : Proposed clustering and prediction analysis framework.
Feature Category
Count
Bytes Statistics
3
Mean, Std, Quantiles (per AP)
Active Users Statistics
2
Mean, Std (per AP)
Temporal Features
30
Bytes: Mean, Std × 3 periods † × 2 day types ‡
12
TABLE I : Extracted Features for Time Series Clustering (35 total)
Fig. 2 : Clusters visualization.
Fig. 3 : 10 min (a) and 60 min (b) future prediction for different clusters of data in a Wi-Fi campus network. The figure shows the results for a global and specialized model.
Fig. 4 : Improvement on MAE using Lkv2 (LSTMv2) model vs Lk (LSTM) (10 min case only).
KPI
C0
C1
C2
C3
C4
MAE GM(10 min)
0.009
0.0028
0.00085
0.00327
0.00064
MAE GM(60 min)
0.018
0.010
0.0039
0.0073
0.00043
MAE (10 min)
0.0050
0.0021
0.0008
0.0013
0.0003
MAE (60 min)
0.014
0.006
0.004
0.0044
0.00044
99%tile (10 min)
0.05
0.036
0.005
0.018
0.01
99%tile (60 min)
0.22
0.16
0.028
0.1
0.02
TABLE II: KPI results for GM and Lk across all clusters. The error in the 99% tile is in MB.
Models
Deployed
Storage
Average
Deployed
Models
Accuracy
One Global Model
1
1 MB
0.008
All Cluster-Specific ( Lkv2 )
5
17.5 MB
0.004
Scalable Deployment Strategy
3
5.5 MB
0.0044
TABLE III : Summary of the models cost in term of memory and computations.
Time series forecasting predicts future values from ordered observations using statistical, neural, and probabilistic models to support decisions under uncertainty.
Centrally-managed Wi-Fi solutions are increasingly leveraging Distributed Artificial Intelligence (AI) to predict key operational statistics of Access Points (APs) and proactively optimize network performance. In this context, Clustered Federated Learning (CFL) represents a fitting methodology, enabling the generation of multiple AI models that account for diverse statistical properties of the APs data distribution. However, identifying informative clusters for grouping APs models remains a significant challenge. In this paper, we address this problem by proposing a novel CFL tool integrating a two step clustering procedure. Initially, multiple clustering solutions are generated and filtered based on a minimum set of desired clustering criteria. Subsequently, if no solutions meet sufficient quality metrics, a global model is produced by aggregating all AP models. Otherwise, the final clustering solution is selected as the one that maximizes the informativeness (quantified via differential entropy) for the smallest cluster. Our results, focusing on a Wi-Fi traffic prediction problem, demonstrate that the developed CFL tool achieves the best predictive performance among all evaluated distributed strategies and the lowest communication and energy footprint among the clustered ones, exceeding the cost of single-model FL only in the regimes where it markedly improves accuracy.
Luca Barbieri, Gianluca Fontanesi, Lorenzo Galati Giordano +2
Radio Systems Research, Nokia Bell Labs, Stuttgart, Germany · Nokia Spain, Madrid
Enterprise wireless access points (APs) are promising platforms for predictive machine learning (ML), but their primary responsibility remains providing wireless connectivity and network services. Predictive inference must therefore share an AP's CPU and memory with packet processing, Wi-Fi and IoT radio operations, and client management. This resource contention creates two risks: a model that performs well on proxy hardware may be too slow on the target AP, while a model that fits in isolation may still degrade network services under load. We define network-aware deployability using two gates: qualification of the model and its execution path on the target AP, followed by validation of its execution profile under packet-service and forecasting constraints. Our benchmarks show that edge testbeds do not reliably capture target behavior. Across matched artifacts and serving settings, five model implementations run 6.1--19.1× slower on an AP than on a Raspberry Pi5, while peak memory usage differs by up to 22%. Moreover, two forecasting foundation models of similar size differ in AP latency by 19×. When serving a smaller model across 13 parallel streams at a 30s cadence under network saturation, default execution increases p99 round-trip time (RTT) by 76% and reduces throughput by 7.06%. Understanding these trade-offs is essential for live deployment if we aim to use APs for both networking and ML workloads.
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.