Predicting Wireless RSSI Using Machine Learning on Graphs

Rattaro, Claudina; Larroca, Federico; Capdehourat, Germán

doi:10.1109/urucon53396.2021.9647374

Cited by 3 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some previous works attempted to use graph structures for network optimization, where the nodes may represent users, BSs, or antennas, and edges can represent network coverage quality using Received Signal Strength Indication (RSSI), interference or other metrics [23]. A few approaches have attempted to apply GCNs to model wireless network planning and performance optimization problems, relying on graphs to represent individual BSs' features [24,25]. A very active research branch within GCNs is how to aggregate the node features at the graph level, aiming at predicting the label for the aggregated graph while providing interpretable explanations for the prediction.…”

Section: B Related Workmentioning

confidence: 99%

On the Use of Spatial Graphs for Performance Degradation Root-Cause Analysis Toward Self-Healing Mobile Networks

Mata,

Sousa,

Vieira

et al. 2024

IEEE Access

View full text Add to dashboard Cite

On the road to the sixth generation of cellular networks (6G), the need to ensure a sustainable usage of natural resources, amid increased competition and cost pressures, has driven the adoption of Self-Healing Mobile Networks to enhance operational efficiency of current and future wireless networks. This paradigm shift relies on Artificial Intelligence (AI) to increase automation of network functions, notably by applying predictive fault detection and automatic root-cause analysis. In this context, this paper proposes a Deep Learning (DL) model for self-healing operations based on a Spatial Graph Convolutional Neural Network (SGCN), which is applied to evaluate the performance degradation of Base Stations (BSs) and uncover the underlying root-causes. The advantages of the proposed DL model are threefold. Firstly, it is especially suited for wireless network applications, leveraging the SGCN to account for spatial dependencies among BSs and their physical characteristics. Secondly, the proposed model offers the flexibility to process diverse types of predictive features, including Performance Management (PM), Fault Management (FM), or other data types. Thirdly, it incorporates an explainability module that pinpoints the input features, such as PM counters, with the most significant influence on BS performance, thereby shedding light on its rootcause factors. The proposed model was evaluated on a live 4G network dataset and the results confirmed its effectiveness in identifying BS performance degradation. An F1-score of 89.6% was achieved in the classification of performance failures, which includes a 27% reduction in false negatives compared to prior research outcomes. In a live network environment, this reduction translates into substantial improvements in Quality of Experience (QoE) for the end users and cost savings for the Mobile Network Operators (MNOs).

show abstract

Section: B Related Workmentioning

confidence: 99%

On the Use of Spatial Graphs for Performance Degradation Root-Cause Analysis Toward Self-Healing Mobile Networks

Mata,

Sousa,

Vieira

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Studies shows that when signals are transmitted, they interact with tropospheric variables such as wind speed, relative humidity, and temperature. The prediction of the state of a channel on a given link was done by [11] by taking measurements on other links, thus causing a decline in the signaling overhead. The first representative approach considered was Random Dot Product Graphs while the second approach was Graph Neural Network.…”

Section: Introductionmentioning

confidence: 99%

Validation of Key Performance Indicators of Mobile Telecommunication Operators Using Ensemble Models and Artificial Neural Networks With Nigerian Communication Commission’s Thresholds

Awofolaju,

Lasisi,

Ajewole

et al. 2024

UJEES

View full text Add to dashboard Cite

This paper presents the comparative studies among the predictive models used for the validation of the key parameter indicators of mobile network operators with the Nigerian Communication Commission’s threshold. Four Key Performance Indicators were predicted using artificial neural networks and ensemble models which include bagging and LSBoost models. The Key Performance Indicators and weather parameters for six locations in Southwestern Nigeria were employed. MATLAB R2020a was employed to develop the three models. Microsoft Excel was used in the analysis of the dataset. The bagging model gave the best average compliance of 94% and 100% for CSSR and TCH Congestion Rate respectively while the ANN model yielded the best average compliance of 76.7% and 85.2% for DCR and SDCCH Congestion Rate respectively..

show abstract

Key performance indicators analysis for 4 G-LTE cellular networks based on real measurements

Shakir

Mjhool

Al-Thaedan

et al. 2023

Int. j. inf. tecnol.

View full text Add to dashboard Cite

Predicting Wireless RSSI Using Machine Learning on Graphs

Cited by 3 publications

References 10 publications

On the Use of Spatial Graphs for Performance Degradation Root-Cause Analysis Toward Self-Healing Mobile Networks

On the Use of Spatial Graphs for Performance Degradation Root-Cause Analysis Toward Self-Healing Mobile Networks

Validation of Key Performance Indicators of Mobile Telecommunication Operators Using Ensemble Models and Artificial Neural Networks With Nigerian Communication Commission’s Thresholds

Key performance indicators analysis for 4 G-LTE cellular networks based on real measurements

Contact Info

Product

Resources

About